Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

arXiv cs.CLOct 12
PIG: Parallel Inconsistency Guidance for Accelerating Diffusion Language Models
Quentin Fruytier, Anton Xue, Sanjay Shakkottai, Sujay Sanghavi
Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequential counterparts, which are slow and expensive "oracles" that adhere to the joint distribution of language. In this paper, we propose Parallel Inconsistency Guidance (PIG), a new paradigm that uses a trained auxiliary model to directly estimate the inconsistency between parallel and sequential generation from a single model forward pass. During inference, masked positions are traversed by decreasing confidence, and tokens are added to the parallel decode set one-at-a-time until the total estimated inconsistency between the parallel and sequential generation exceeds a threshold. Surprisingly, it suffices to train a lightweight ~2M parameter auxiliary model on a small mixture drawn from OpenCoder, GSM8K-train, MATH-train, and MBPP-train. For LLaDA-8B Instruct and NemotronDiffusion-3B Instruct, PIG extends the accuracy-TPF frontier on GSM8K, MATH500, MBPP, HumanEval, and MMLU, when compared to the industry standard Fast-dLLM and measures favorably on LLaDA-8B Instruct against DAPD,…
PDF
arXiv cs.LGOct 12
HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery
Yingzi Ma, Yulong Cao, Nanxi Li, Fang Wu, Yizhe Zhang +3
Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this search can improve the procedure used to conduct it. We introduce HarnessTTT, a test-time learning framework that trains a harness proposer while keeping the executor frozen. The proposer generates executable harnesses comprising system prompts, reusable skills, tools, middleware, and execution controls. Each harness guides a budgeted discovery rollout, whose outcome provides feedback for updating the proposer. A discovery-oriented policy-gradient objective combines gap-normalized rewards, leave-one-out advantages (RLOO), and max-sharpening to favor high-performing proposals. Generated components are validated before execution, and the search retains the best valid solution and selected harnesses across rounds. Across fourteen discovery tasks in mathematics, systems, GPU kernels, heuristic programming, astrodynamics, and biology, HarnessTTT with a frozen 9B executor improves on OpenEvolve with the same executor on all eleven benchmark tasks (e.g., from 1.17 to 2.64 on circle packing), improves on the discovery-fine-tuned Finch-9B…
PDF
arXiv cs.IROct 12
HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation
Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff +1
Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We introduce an approach showing that explicitly incorporating hierarchical and attribute-level supervision into generative recommendation can simultaneously improve training efficiency and long-tail recommendation performance. Existing approaches typically optimize semantic ID prediction with a standard causal cross-entropy objective, which does not explicitly exploit the hierarchical structure of semantic IDs and can require substantial training to learn effective item representations. Moreover, data-sparse tail items often suffer from poor representations due to limited supervision, resulting in weaker long-tail recommendation performance. We address these challenges with HASTE (Hierarchical and Attribute-aware Supervision for generaTive rEcommendation), a unified training framework that introduces hierarchical and attribute-specific supervision. HASTE's Hierarchical Loss explicitly exploits the multi-level structure of semantic IDs, providing supervision at each level of the item hierarchy and substantially accelerating training…
PDF
arXiv cs.AIOct 12
When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions
Saloni Gupta, Sébastien Krier, Glenn Matlin
As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent maintains shared inference state across these interactions, information associated with one relationship may influence decisions made for another. We test OLMo-3-7B-Instruct in a controlled two-client environment with 20 market scenarios, where each client is assigned an opposing objective. With shared conversational memory, the model deviates from the current client's objective in 22% of eligible decisions. We then investigate how these goals are represented in the KV cache. Linear probes show that client-goal ownership becomes highly recoverable in middle layers and is concentrated in particular attention heads. We use these results to identify where to intervene in the cache and test whether these representations affect the model's decisions. Ablating the competitor's cached goal representations at these locations shifts the model toward the current client. The effect is larger for heads identified by probing than for randomly selected heads, and larger when ablating goal tokens than matched non-goal tokens from the same…
PDF
arXiv cs.CLOct 12
UMCR: Universal Medical Concept Recognition through Guideline Integration and Agentic Linking
Fabrice Lamarche, Amal Zouaq
Medical Concept Recognition is the task of extracting and grounding spans in medical text to entries in a standard ontology. Current methods are generally developed towards a single ontology and source text type (clinical notes, drug labels, etc.) The central challenge is therefore to build methods that adapt to any target ontology without requiring ontology-specific retraining. More recent approaches like REAL and AutoPCR make direct use of Large Language Models and can theoretically adapt to any ontology choice but suffer from a lack of generalization. We propose UMCR, a pipeline that allows extraction and linking to any target ontology using any source text variety, utilizing direct guideline integration and an agentic linking module. We evaluate our method on the recent MedPath benchmark, covering a wide variety of medical text types and vocabularies, and show that our method achieves strong performance across these tasks. This ability unlocks interoperability in the healthcare domain, allowing for extraction and alignment between different medical standards. Our method also reduces dependence on parametric LLM memory, thanks to improved interaction with the target ontology…
PDF
arXiv cs.CLOct 12
claimcheck: Measuring and Improving Specification Faithfulness
Martin Amster, One An, Holly Baker, Fernanda Graciolli, Simon Henniger +1
Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant. As LLMs increasingly write both code and specifications, a gap between the author's natural-language requirement and the specification becomes a live risk. A machine-checked proof of a property narrower than the one requested is worthless but passes every check. Closing this gap is solving the spec formalization problem: given a natural-language requirement, produce a formal artifact whose meaning matches it. To measure the gap, we curate an end-to-end benchmark for spec formalization spanning four formal languages: Dafny contracts and Lean 4, Isabelle and Rocq theorem statements. Each of its 3,234 rows pairs a natural-language requirement with a formal artifact and a label established by execution, by proof, or by the benchmark it is drawn from. A third of the rows are meaning-preserving rewrites of the artifact that keep the faithful label, so a judge cannot score by detecting that a row was edited. We introduce claimcheck, a tool that detects incorrect formalizations: the formal artifact is translated back into plain English by…
PDF
arXiv cs.CVOct 12
Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars
Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia, Maurice Rekrut, Christian Theobalt +1
Driving digital head avatars is classically done by hand-crafted artist design or by image-based facial performance capture. In this work, we ask whether spatio-temporal tracking of the humans's head geometry and appearance can be performed solely from brain signals, i.e., Electroencephalography (EEG). Since prior work mostly focused on activity and emotion recognition, this task is relatively unexplored without even having publicly available high-quality datasets and benchmarks. Thus, we contribute a dataset featuring paired EEG and human head geometry as well as appearance annotations. We synchronize 64-channel EEG with per-frame expression latent codes of a personalized Gaussian head avatar. Second, we introduce a baseline to the task of expression recovery of a head avatar from EEG signals. To this end, we propose a dedicated EEG-to-expression model that takes a temporal sequence of EEG signals as input and regresses the latent expression parameters of the 3D Gaussian head avatar. Lastly, we validate our capture and algorithmic design choices through a benchmark protocol that we introduce to this task. We believe this work paves the way towards better understanding of the…
PDF
arXiv cs.CVOct 12
WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs
Ameen Ali, Tamim Zoabi, Lior Wolf, Chaim Baskin
Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decoder layer during prefill, stored in the key value cache, and attended by every generated token, so a long video raises prefill, memory, and generation cost at once. We present WIRE (Weight Space Implicit Representation Encoding), which reduces this recurring cost by moving part of the video conditioned computation of a frozen video language model from its input activations into a temporary low rank update of its weights. WIRE keeps a short explicit visual context, so the update acts as a correction rather than a replacement of the video. WIRE first compresses the full resolution embeddings of each frame into a small set of carrier tokens using a question conditioned bidirectional selective scan, and physically contracts the decoder input so every decoder layer, cache entry, and decoding step operates on the shorter sequence. Hypernetworks at selected decoder layers read the compressed forward pass together with a readout of the full resolution features removed by contraction and generate LoRA updates to the attention and…
PDF
arXiv cs.CVOct 12
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo, Michela Antonelli, Sebastien Ourselin +1
Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice…
PDF
arXiv cs.CVOct 12
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Yating Wang, Kui Wu, Ran Yi, Zixuan Lu, Tongtong Wang +3
Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer broader hairstyle priors, but their outputs are not directly usable for strand-based rendering and simulation. Existing approaches require costly per-instance optimization to fit hair priors to meshes from foundation models and 2D orientations from specialized predictors trained on limited hair data, restricting efficiency and generalization. We present HairFlow, a multimodal conditioned diffusion framework for efficient and controllable hair strands modeling. HairFlow conditions strand generation on two complementary representations: a coarse mesh that constrains global shape and multi-view sketches that specify local strand flow. HairFlow combines an Orientation VAE with a conditioned diffusion transformer to generate volumetric fields that are traced into explicit strands. To overcome the lack of paired sketch-strand training data, we introduce an automatic synthesis pipeline that generates geometrically aligned multi-view sketches with diverse styles representative of inference-time inputs.…
PDF
arXiv cs.LGOct 12
On the Statistical Mechanics of Attention
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su, Han Liu
We revisit the statistical mechanics of Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter regimes and critical thresholds for robust attention inference. The resulting free-energy landscape incorporates randomness in query states and attention weights. Attention then emerges as the equation of motion of the corresponding statistical-mechanical system (i.e., modern Hopfield model) through the standard free-energy minimization principle. This allows us to identify first-order phase transitions in attention between glassy and robust-inference phases. We further extend to attentions with stochastic queries and keys. Together, our results provide a rigorous statistical-mechanics framework for characterizing phase structure and inference reliability across a family of Transformer attention mechanisms.
PDF
arXiv stat.MLOct 12
Monitoring for Shifts at Unknown Times: Parameter-Free Conditional Conformal Martingales
Tuo Liu, Drew Prinster, Francesco Orabona
Conditional conformal test martingales provide sequential tests for detecting distribution shifts, using a fixed reference dataset to avoid contamination from test-time samples. Prior work used a penalized betting function via online optimization with smoothing, clipping, and other hyperparameters, which can adapt slowly when a shift occurs after a long stationary period. In this work, we introduce an approach that requires no hyperparameters and provably adapts quickly to shifts occurring at unknown times. Our key idea is to frame the penalized betting problem as portfolio selection in a three-asset market. Then, we use a restarting universal portfolio, with a heavy-tailed wealth allocation over time. We establish anytime false-alarm control and derive optimal finite-sample bounds on detection delay under detectable alternatives. We also develop an FFT-based implementation that computes the portfolio sequence over $T$ rounds in $\mathcal{O}(T^2\ln T)$ time, instead of $\mathcal{O}(T^3)$ of the naive implementation. Synthetic and real-world experiments suggest that the proposed approach adapts rapidly after long periods of null samples, with detection delays depending…
PDF
arXiv cs.AIOct 12
Budgeted KV-Cache Repair for Evolving Contexts
Han Yu, Wenhui Zhu, Jincheng Cao, Rui Cai, Yuanda Xu +13
Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) states remain conditioned on the deleted content, while recomputing the entire retained suffix can be costly. We introduce budgeted KV-cache repair: recovering task performance by recomputing a user-chosen fraction of the retained suffix. Comparing repair allocations under identical relevance scores and token budgets, we find that refreshing coherent regions can substantially outperform refreshing isolated tokens. This finding motivates Semantic-Unit Refresh (SUR), which allocates the budget to query-relevant text regions using inexpensive embedding scores, without training or an auxiliary transformer forward. To execute these repairs efficiently, a layer-packed executor processes selected states together at each layer while preserving full causal cache access. Across five models, SUR achieves strong recovery in controlled deletion tasks while recomputing only 2-5% of the suffix. On four natural multi-hop QA datasets, it achieves near-full-recompute exact match at a 5% budget with lower post-edit latency.…
PDF
arXiv stat.MLOct 12
Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Marc Bocquet, Tobias S. Finn, Sibo Cheng
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which…
PDF
arXiv cs.LGOct 12
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Damien Lo, Hong Kyu Lee, Ruixuan Liu, Li Xiong
Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude…
PDF
arXiv cs.AIOct 12
Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean
Tomas Ortega, Simon Park, Ayush Khaitan, Liam Fowl, Alex Kontorovich +1
General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. This makes it difficult to determine which components of theorem-proving agents provide benchmark gains: an improved base model, a specialized harness, a specific tool, or a combination of any of them. We introduce mini-Lean-agent, a deliberately minimal agent for Lean tasks whose only model-visible tool is bash. The model must use bash to inspect and edit the repository, search local libraries, invoke Lean, and manage its own intermediate work, while a separate trusted evaluator verifies the final artifact. We compare mini-Lean-agent against AxProverBase and Numina-Lean-Agent on the Putnam 2025 benchmark. Experiments with Gemini 3.8 Flash as the base model show that mini-Lean-agent solves 7/12 problems at \$2 per problem limit, compared with AxProverBase's 4/12. With Astra as the base model, mini-Lean-agent solves 12/12 problems at an average cost of \$1.28 per problem. This suggests that a generic coding agent with a minimal harness can already achieve strong performance on Lean benchmarks. Our results motivate using…
PDF
arXiv cs.CLOct 12
The Curse of Knowledge in Role-Playing Language Models
Xiao Zhang
Role-playing language models speak as characters in games and agent simulations, where the system records what each character can hear, see and understand. We test whether characters respect these boundaries in 480 scenes, each with a counterfactual twin that changes only the hidden fact, so mentions of the twin's fact measure guessing. Across 11 open-weight models, characters use content from speech they cannot understand or hear at 67 and 72 percentage points (pp) above this baseline, although most models correctly state what the character perceives. This is a curse of knowledge. The leak extends to hidden actions and private messages and changes where characters search. Five of six proprietary models rarely leak, but compliance in strong models depends on input format. Changing only the scene layout or character description raises the rate in two otherwise compliant open-weight models from under 10 to over 60 pp, and combined changes raise two proprietary models from near zero to 13 and 21~pp. Writing the line as the scene's author leaks nearly as much as role-play, and thinking rarely helps. Giving models only what the character observes stops the leak without hiding what it…
PDF
arXiv cs.CLOct 12
Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior
Kibum Moon, Dan R. Johnson, Kostadin Kushlev, Benjamin Lira, Indre Viskontas +4
AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and less effective thinking that AI avoids? We developed Expansion of Divergent Generative Expression (EDGE) to map AI's semantic "blind spots" by assessing how strongly/weakly individual human ideas were represented in a task-matched AI semantic comparison set. Specifically, we compared human-generated vs. AI-generated ideas across three open-ended tasks: college admissions essays, alternative uses for everyday objects, and interpersonal advice. Across all three tasks, human responses extended into semantic regions sparsely covered by AI outputs. These distinctively human responses showed no meaningful deficits in creativity, quality, or effectiveness, were associated with equal-or-better academic performance, and with credibly superior ratings and achievement for some outcomes. These ideas were thus not merely poor-performing variation; they performed as well as or…
PDF
arXiv cs.CVOct 12
SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy
Tunahan Parlayıcı, Erchan Aptoula, Yücel Saygın
Face recognition systems are deployed widely enough that a photograph shared online can be matched without its subject's consent. Generator-based protection methods rely on heavy pretrained backbones, multi-stage inference or visible semantic edits. We introduce SSM-Attack, a black-box face privacy framework built on Selective State Space Models. Rather than synthesizing the perturbation, the state-space model predicts in one linear-time pass a spatial allocation of the perturbation budget, marking which facial locations carry identity evidence; a short projected refinement then sets the values within this per-pixel budget. Against published benchmark results, SSM-Attack attains the highest average black-box attack success rate on all three evaluation sets: 87.10 percent on CelebA-HQ, 86.90 on LADN and 81.15 on FFHQ, the last from a network that never saw that dataset. The allocation network holds 5.73 million parameters, or 16.13 million with the frozen networks used by its quality terms. Under the same cap of 0.10 on the maximum per-pixel change, allocation improves structural similarity by 0.044, peak signal-to-noise ratio by 1.62 decibels and Frechet Inception Distance by…
PDF
arXiv cs.DCOct 12
GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference
Rithik Sharma, Reese Levine, Zheyuan Chen, Ananthajit Srikanth, Yanwen Xu +1
As demand for LLM inference grows and consumer GPUs grow more capable, edge deployment is becoming increasingly attractive. WebGPU is compelling in this setting because it offers cross-platform portability and browser accessibility. However, these same strengths also make high performance difficult to achieve, as an implementation that performs well in one context may not perform well in another. To address this, we present GPU Goldmines, a framework for specifying, executing, and tuning WebGPU kernels. We instantiate GPU Goldmines with kernels for key LLM building blocks: matrix multiplication, matrix-vector multiplication, and flash attention. We characterize performance across diverse devices, shapes, and browsers, and use the resulting database to accelerate subsequent autotuning and configuration selection. On shapes drawn from Llama and Qwen models, our matrix multiplication kernels outperform ONNX Runtime and llama.cpp WebGPU kernels by 7.0x and 1.41x geometric mean, respectively, and deliver end-to-end improvements of 1.48x in the prefill stage of llama.cpp for chat workloads.
PDF

Papers

Open problems across fields

Lack of benchmarks for agent harness reliability1 paper raises it · 1 addresses it
Existing benchmarks focus on model capabilities rather than the reliability of the systems that support agent operation.
- Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
Unclear net value of agent memory1 paper raises it · 1 addresses it
Dedicated memory systems often underperform naive retrieval, making their benefits uncertain.
- Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
Token collapse in graph soft prompting1 paper raises it · 0 address it
Graph-specific tokens become indistinguishable, failing to convey intended relational information.
- On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
Poor trajectory supervision for tool-use agents1 paper raises it · 1 addresses it
Successful trajectories may lack compositional coverage or decision grounding, limiting agent learning.
- Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
Uneven evaluation of coupled agent-world model systems1 paper raises it · 1 addresses it
Separate evaluation of agents and world models fails to predict their joint performance or sustained learning.
- Dual Exam: Controlled Evaluation of Multimodal Agents and World Modelsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Rising research topics

Anomaly detectors24+71.4%
Channel state information15+36.4%
AI tutors15+36.4%
Character recognition OCR12+20.0%
Multimodal emotion8+14.3%
Physics informed neural130−11.6%
Machine learned interatomic37−14.0%
Supervised & diffusion models89−25.8%

Rising research topics

Ask the research

Sample

Papers

arXiv cs.CLOct 12
PIG: Parallel Inconsistency Guidance for Accelerating Diffusion Language Models
Quentin Fruytier, Anton Xue, Sanjay Shakkottai, Sujay Sanghavi
Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequential counterparts, which are slow and expensive "oracles" that adhere to the joint distribution of language. In this paper, we propose Parallel Inconsistency Guidance (PIG), a new paradigm that uses a trained auxiliary model to directly estimate the inconsistency between parallel and sequential generation from a single model forward pass. During inference, masked positions are traversed by decreasing confidence, and tokens are added to the parallel decode set one-at-a-time until the total estimated inconsistency between the parallel and sequential generation exceeds a threshold. Surprisingly, it suffices to train a lightweight ~2M parameter auxiliary model on a small mixture drawn from OpenCoder, GSM8K-train, MATH-train, and MBPP-train. For LLaDA-8B Instruct and NemotronDiffusion-3B Instruct, PIG extends the accuracy-TPF frontier on GSM8K, MATH500, MBPP, HumanEval, and MMLU, when compared to the industry standard Fast-dLLM and measures favorably on LLaDA-8B Instruct against DAPD,…
PDF
arXiv cs.LGOct 12
HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery
Yingzi Ma, Yulong Cao, Nanxi Li, Fang Wu, Yizhe Zhang +3
Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this search can improve the procedure used to conduct it. We introduce HarnessTTT, a test-time learning framework that trains a harness proposer while keeping the executor frozen. The proposer generates executable harnesses comprising system prompts, reusable skills, tools, middleware, and execution controls. Each harness guides a budgeted discovery rollout, whose outcome provides feedback for updating the proposer. A discovery-oriented policy-gradient objective combines gap-normalized rewards, leave-one-out advantages (RLOO), and max-sharpening to favor high-performing proposals. Generated components are validated before execution, and the search retains the best valid solution and selected harnesses across rounds. Across fourteen discovery tasks in mathematics, systems, GPU kernels, heuristic programming, astrodynamics, and biology, HarnessTTT with a frozen 9B executor improves on OpenEvolve with the same executor on all eleven benchmark tasks (e.g., from 1.17 to 2.64 on circle packing), improves on the discovery-fine-tuned Finch-9B…
PDF
arXiv cs.IROct 12
HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation
Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff +1
Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We introduce an approach showing that explicitly incorporating hierarchical and attribute-level supervision into generative recommendation can simultaneously improve training efficiency and long-tail recommendation performance. Existing approaches typically optimize semantic ID prediction with a standard causal cross-entropy objective, which does not explicitly exploit the hierarchical structure of semantic IDs and can require substantial training to learn effective item representations. Moreover, data-sparse tail items often suffer from poor representations due to limited supervision, resulting in weaker long-tail recommendation performance. We address these challenges with HASTE (Hierarchical and Attribute-aware Supervision for generaTive rEcommendation), a unified training framework that introduces hierarchical and attribute-specific supervision. HASTE's Hierarchical Loss explicitly exploits the multi-level structure of semantic IDs, providing supervision at each level of the item hierarchy and substantially accelerating training…
PDF
arXiv cs.AIOct 12
When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions
Saloni Gupta, Sébastien Krier, Glenn Matlin
As LLM agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an agent maintains shared inference state across these interactions, information associated with one relationship may influence decisions made for another. We test OLMo-3-7B-Instruct in a controlled two-client environment with 20 market scenarios, where each client is assigned an opposing objective. With shared conversational memory, the model deviates from the current client's objective in 22% of eligible decisions. We then investigate how these goals are represented in the KV cache. Linear probes show that client-goal ownership becomes highly recoverable in middle layers and is concentrated in particular attention heads. We use these results to identify where to intervene in the cache and test whether these representations affect the model's decisions. Ablating the competitor's cached goal representations at these locations shifts the model toward the current client. The effect is larger for heads identified by probing than for randomly selected heads, and larger when ablating goal tokens than matched non-goal tokens from the same…
PDF
arXiv cs.CLOct 12
UMCR: Universal Medical Concept Recognition through Guideline Integration and Agentic Linking
Fabrice Lamarche, Amal Zouaq
Medical Concept Recognition is the task of extracting and grounding spans in medical text to entries in a standard ontology. Current methods are generally developed towards a single ontology and source text type (clinical notes, drug labels, etc.) The central challenge is therefore to build methods that adapt to any target ontology without requiring ontology-specific retraining. More recent approaches like REAL and AutoPCR make direct use of Large Language Models and can theoretically adapt to any ontology choice but suffer from a lack of generalization. We propose UMCR, a pipeline that allows extraction and linking to any target ontology using any source text variety, utilizing direct guideline integration and an agentic linking module. We evaluate our method on the recent MedPath benchmark, covering a wide variety of medical text types and vocabularies, and show that our method achieves strong performance across these tasks. This ability unlocks interoperability in the healthcare domain, allowing for extraction and alignment between different medical standards. Our method also reduces dependence on parametric LLM memory, thanks to improved interaction with the target ontology…
PDF
arXiv cs.CLOct 12
claimcheck: Measuring and Improving Specification Faithfulness
Martin Amster, One An, Holly Baker, Fernanda Graciolli, Simon Henniger +1
Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant. As LLMs increasingly write both code and specifications, a gap between the author's natural-language requirement and the specification becomes a live risk. A machine-checked proof of a property narrower than the one requested is worthless but passes every check. Closing this gap is solving the spec formalization problem: given a natural-language requirement, produce a formal artifact whose meaning matches it. To measure the gap, we curate an end-to-end benchmark for spec formalization spanning four formal languages: Dafny contracts and Lean 4, Isabelle and Rocq theorem statements. Each of its 3,234 rows pairs a natural-language requirement with a formal artifact and a label established by execution, by proof, or by the benchmark it is drawn from. A third of the rows are meaning-preserving rewrites of the artifact that keep the faithful label, so a judge cannot score by detecting that a row was edited. We introduce claimcheck, a tool that detects incorrect formalizations: the formal artifact is translated back into plain English by…
PDF
arXiv cs.CVOct 12
Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars
Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia, Maurice Rekrut, Christian Theobalt +1
Driving digital head avatars is classically done by hand-crafted artist design or by image-based facial performance capture. In this work, we ask whether spatio-temporal tracking of the humans's head geometry and appearance can be performed solely from brain signals, i.e., Electroencephalography (EEG). Since prior work mostly focused on activity and emotion recognition, this task is relatively unexplored without even having publicly available high-quality datasets and benchmarks. Thus, we contribute a dataset featuring paired EEG and human head geometry as well as appearance annotations. We synchronize 64-channel EEG with per-frame expression latent codes of a personalized Gaussian head avatar. Second, we introduce a baseline to the task of expression recovery of a head avatar from EEG signals. To this end, we propose a dedicated EEG-to-expression model that takes a temporal sequence of EEG signals as input and regresses the latent expression parameters of the 3D Gaussian head avatar. Lastly, we validate our capture and algorithmic design choices through a benchmark protocol that we introduce to this task. We believe this work paves the way towards better understanding of the…
PDF
arXiv cs.CVOct 12
WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs
Ameen Ali, Tamim Zoabi, Lior Wolf, Chaim Baskin
Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decoder layer during prefill, stored in the key value cache, and attended by every generated token, so a long video raises prefill, memory, and generation cost at once. We present WIRE (Weight Space Implicit Representation Encoding), which reduces this recurring cost by moving part of the video conditioned computation of a frozen video language model from its input activations into a temporary low rank update of its weights. WIRE keeps a short explicit visual context, so the update acts as a correction rather than a replacement of the video. WIRE first compresses the full resolution embeddings of each frame into a small set of carrier tokens using a question conditioned bidirectional selective scan, and physically contracts the decoder input so every decoder layer, cache entry, and decoding step operates on the shorter sequence. Hypernetworks at selected decoder layers read the compressed forward pass together with a readout of the full resolution features removed by contraction and generate LoRA updates to the attention and…
PDF
arXiv cs.CVOct 12
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo, Michela Antonelli, Sebastien Ourselin +1
Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice…
PDF
arXiv cs.CVOct 12
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Yating Wang, Kui Wu, Ran Yi, Zixuan Lu, Tongtong Wang +3
Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer broader hairstyle priors, but their outputs are not directly usable for strand-based rendering and simulation. Existing approaches require costly per-instance optimization to fit hair priors to meshes from foundation models and 2D orientations from specialized predictors trained on limited hair data, restricting efficiency and generalization. We present HairFlow, a multimodal conditioned diffusion framework for efficient and controllable hair strands modeling. HairFlow conditions strand generation on two complementary representations: a coarse mesh that constrains global shape and multi-view sketches that specify local strand flow. HairFlow combines an Orientation VAE with a conditioned diffusion transformer to generate volumetric fields that are traced into explicit strands. To overcome the lack of paired sketch-strand training data, we introduce an automatic synthesis pipeline that generates geometrically aligned multi-view sketches with diverse styles representative of inference-time inputs.…
PDF
arXiv cs.LGOct 12
On the Statistical Mechanics of Attention
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su, Han Liu
We revisit the statistical mechanics of Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter regimes and critical thresholds for robust attention inference. The resulting free-energy landscape incorporates randomness in query states and attention weights. Attention then emerges as the equation of motion of the corresponding statistical-mechanical system (i.e., modern Hopfield model) through the standard free-energy minimization principle. This allows us to identify first-order phase transitions in attention between glassy and robust-inference phases. We further extend to attentions with stochastic queries and keys. Together, our results provide a rigorous statistical-mechanics framework for characterizing phase structure and inference reliability across a family of Transformer attention mechanisms.
PDF
arXiv stat.MLOct 12
Monitoring for Shifts at Unknown Times: Parameter-Free Conditional Conformal Martingales
Tuo Liu, Drew Prinster, Francesco Orabona
Conditional conformal test martingales provide sequential tests for detecting distribution shifts, using a fixed reference dataset to avoid contamination from test-time samples. Prior work used a penalized betting function via online optimization with smoothing, clipping, and other hyperparameters, which can adapt slowly when a shift occurs after a long stationary period. In this work, we introduce an approach that requires no hyperparameters and provably adapts quickly to shifts occurring at unknown times. Our key idea is to frame the penalized betting problem as portfolio selection in a three-asset market. Then, we use a restarting universal portfolio, with a heavy-tailed wealth allocation over time. We establish anytime false-alarm control and derive optimal finite-sample bounds on detection delay under detectable alternatives. We also develop an FFT-based implementation that computes the portfolio sequence over $T$ rounds in $\mathcal{O}(T^2\ln T)$ time, instead of $\mathcal{O}(T^3)$ of the naive implementation. Synthetic and real-world experiments suggest that the proposed approach adapts rapidly after long periods of null samples, with detection delays depending…
PDF
arXiv cs.AIOct 12
Budgeted KV-Cache Repair for Evolving Contexts
Han Yu, Wenhui Zhu, Jincheng Cao, Rui Cai, Yuanda Xu +13
Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) states remain conditioned on the deleted content, while recomputing the entire retained suffix can be costly. We introduce budgeted KV-cache repair: recovering task performance by recomputing a user-chosen fraction of the retained suffix. Comparing repair allocations under identical relevance scores and token budgets, we find that refreshing coherent regions can substantially outperform refreshing isolated tokens. This finding motivates Semantic-Unit Refresh (SUR), which allocates the budget to query-relevant text regions using inexpensive embedding scores, without training or an auxiliary transformer forward. To execute these repairs efficiently, a layer-packed executor processes selected states together at each layer while preserving full causal cache access. Across five models, SUR achieves strong recovery in controlled deletion tasks while recomputing only 2-5% of the suffix. On four natural multi-hop QA datasets, it achieves near-full-recompute exact match at a 5% budget with lower post-edit latency.…
PDF
arXiv stat.MLOct 12
Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Marc Bocquet, Tobias S. Finn, Sibo Cheng
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which…
PDF
arXiv cs.LGOct 12
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Damien Lo, Hong Kyu Lee, Ruixuan Liu, Li Xiong
Vision large language models (VLLMs) are deployed in privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude…
PDF
arXiv cs.AIOct 12
Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean
Tomas Ortega, Simon Park, Ayush Khaitan, Liam Fowl, Alex Kontorovich +1
General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. This makes it difficult to determine which components of theorem-proving agents provide benchmark gains: an improved base model, a specialized harness, a specific tool, or a combination of any of them. We introduce mini-Lean-agent, a deliberately minimal agent for Lean tasks whose only model-visible tool is bash. The model must use bash to inspect and edit the repository, search local libraries, invoke Lean, and manage its own intermediate work, while a separate trusted evaluator verifies the final artifact. We compare mini-Lean-agent against AxProverBase and Numina-Lean-Agent on the Putnam 2025 benchmark. Experiments with Gemini 3.8 Flash as the base model show that mini-Lean-agent solves 7/12 problems at \$2 per problem limit, compared with AxProverBase's 4/12. With Astra as the base model, mini-Lean-agent solves 12/12 problems at an average cost of \$1.28 per problem. This suggests that a generic coding agent with a minimal harness can already achieve strong performance on Lean benchmarks. Our results motivate using…
PDF
arXiv cs.CLOct 12
The Curse of Knowledge in Role-Playing Language Models
Xiao Zhang
Role-playing language models speak as characters in games and agent simulations, where the system records what each character can hear, see and understand. We test whether characters respect these boundaries in 480 scenes, each with a counterfactual twin that changes only the hidden fact, so mentions of the twin's fact measure guessing. Across 11 open-weight models, characters use content from speech they cannot understand or hear at 67 and 72 percentage points (pp) above this baseline, although most models correctly state what the character perceives. This is a curse of knowledge. The leak extends to hidden actions and private messages and changes where characters search. Five of six proprietary models rarely leak, but compliance in strong models depends on input format. Changing only the scene layout or character description raises the rate in two otherwise compliant open-weight models from under 10 to over 60 pp, and combined changes raise two proprietary models from near zero to 13 and 21~pp. Writing the line as the scene's author leaks nearly as much as role-play, and thinking rarely helps. Giving models only what the character observes stops the leak without hiding what it…
PDF
arXiv cs.CLOct 12
Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior
Kibum Moon, Dan R. Johnson, Kostadin Kushlev, Benjamin Lira, Indre Viskontas +4
AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and less effective thinking that AI avoids? We developed Expansion of Divergent Generative Expression (EDGE) to map AI's semantic "blind spots" by assessing how strongly/weakly individual human ideas were represented in a task-matched AI semantic comparison set. Specifically, we compared human-generated vs. AI-generated ideas across three open-ended tasks: college admissions essays, alternative uses for everyday objects, and interpersonal advice. Across all three tasks, human responses extended into semantic regions sparsely covered by AI outputs. These distinctively human responses showed no meaningful deficits in creativity, quality, or effectiveness, were associated with equal-or-better academic performance, and with credibly superior ratings and achievement for some outcomes. These ideas were thus not merely poor-performing variation; they performed as well as or…
PDF
arXiv cs.CVOct 12
SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy
Tunahan Parlayıcı, Erchan Aptoula, Yücel Saygın
Face recognition systems are deployed widely enough that a photograph shared online can be matched without its subject's consent. Generator-based protection methods rely on heavy pretrained backbones, multi-stage inference or visible semantic edits. We introduce SSM-Attack, a black-box face privacy framework built on Selective State Space Models. Rather than synthesizing the perturbation, the state-space model predicts in one linear-time pass a spatial allocation of the perturbation budget, marking which facial locations carry identity evidence; a short projected refinement then sets the values within this per-pixel budget. Against published benchmark results, SSM-Attack attains the highest average black-box attack success rate on all three evaluation sets: 87.10 percent on CelebA-HQ, 86.90 on LADN and 81.15 on FFHQ, the last from a network that never saw that dataset. The allocation network holds 5.73 million parameters, or 16.13 million with the frozen networks used by its quality terms. Under the same cap of 0.10 on the maximum per-pixel change, allocation improves structural similarity by 0.044, peak signal-to-noise ratio by 1.62 decibels and Frechet Inception Distance by…
PDF
arXiv cs.DCOct 12
GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference
Rithik Sharma, Reese Levine, Zheyuan Chen, Ananthajit Srikanth, Yanwen Xu +1
As demand for LLM inference grows and consumer GPUs grow more capable, edge deployment is becoming increasingly attractive. WebGPU is compelling in this setting because it offers cross-platform portability and browser accessibility. However, these same strengths also make high performance difficult to achieve, as an implementation that performs well in one context may not perform well in another. To address this, we present GPU Goldmines, a framework for specifying, executing, and tuning WebGPU kernels. We instantiate GPU Goldmines with kernels for key LLM building blocks: matrix multiplication, matrix-vector multiplication, and flash attention. We characterize performance across diverse devices, shapes, and browsers, and use the resulting database to accelerate subsequent autotuning and configuration selection. On shapes drawn from Llama and Qwen models, our matrix multiplication kernels outperform ONNX Runtime and llama.cpp WebGPU kernels by 7.0x and 1.41x geometric mean, respectively, and deliver end-to-end improvements of 1.48x in the prefill stage of llama.cpp for chat workloads.
PDF