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.LGOct 3
Principled Top-$k$ Selection for Language Models with Hybrid Gradients
Xuchen Gong, Junfei Sun, Tian Li
Selecting the best $k$ items out of $m$ candidates is a critical component of modern large language model systems, such as document selection in Retrieval-Augmented Generation (RAG) and expert routing in Mixture-of-Experts (MoEs). However, training these selection modules remains challenging due to weak gradient signals and suboptimal exploration-exploitation tradeoffs. Furthermore, prior works often rely on heuristics, lacking principled objectives and approaches that explicitly model and solve the top-$k$ selection problem. In this work, we propose a principled objective for training selection modules, whose gradient naturally provides richer training signals in a hybrid form---containing a supervised-gradient component and a policy-gradient component. We show that the selection problem becomes harder as $m$ increases, and our algorithm converges at rate $O(1/\sqrt{T})$, with the optimal upper bound achieved by balancing between bias and variance. Practically, we apply our method to a set of tasks involving top-$k$ selection, including synthetic regression problems, RAG, and MoE systems, showing that our method outperforms the baselines in next-token prediction perplexity and…
PDF
arXiv cs.CVOct 3
Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation
Md Mustafizur Rahman, Mylene C. Q. Farias
Radiology report generation models can produce fluent text while still containing finding-level inaccuracies. Diagnosis-driven methods improve generation by conditioning on predicted findings, but these predictions do not directly modify the visual patch features provided to the decoder, and global gating applies the same modulation across spatial locations. We introduce a Position-Aware Gate (PAG) that uses predicted finding representations to modulate visual patches spatially without region supervision. We also propose a Decoder-level Supervised Contrastive Loss (DSCL) that structures decoder representations using shared positive findings rather than instance identity. On MIMIC-CXR, PAG+DSCL improves clinical efficacy (CE) F1 from 0.484 to 0.502 over a matched global-gate reference, while PAG and DSCL individually reach 0.491 and 0.495. Without additional fine-tuning, the combined model achieves 0.226 CE F1 on IU X-Ray, compared with 0.211 reported by PromptMRG.
PDF
arXiv cs.LGOct 3
How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws
Ziheng Cheng, Yixiao Huang, Hanlin Zhu, Somayeh Sojoudi
Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning. Training on mathematics can improve performance in other domains, yet gains in Pass@1 can coincide with lower Pass@$N$ than the base model. This raises a fundamental question: does RL expand an LLM's reasoning boundary, or merely reweight its existing reasoning space? We revisit these phenomena across Qwen and Gemma model families, showing both cross-domain gains and forgetting, while coverage at large sampling budgets increases on some tasks and decreases on others. Detailed analysis of solution traces before and after RL indicates a shift in the reasoning strategies the model employs, motivating a two-stage autoregressive policy model that separates \emph{strategy selection} from problem-specific execution. Within this framework, we prove how RL's implicit bias reshapes strategy preferences, allowing gains on some tasks while suppressing strategies required by others. This mechanism can also broaden or narrow coverage at a given sampling budget even without expanding strategy support. We further provide theoretical justifications for log-sigmoid and…
PDF
arXiv stat.MLOct 3
Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
André Ribeiro, Germano Barcelos, Amauri H. Souza, Diego Mesquita, Ana Luiza Tenório
Graph Neural Networks (GNNs) often struggle to capture long-range dependencies due to over-squashing -- a phenomenon in which the repeated compression of node embeddings into finite-size messages causes representations to collapse. Over-squashing is most often diagnosed as a property of the graph topology, with effective resistance serving as a principled measure of the bottleneck. We provide a complementary view on the matter: building on cellular sheaves, we introduce sheaf effective resistance, a generalization of effective resistance that depends on the sheaf attached to the graph, and we prove that for flat vector bundles, the over-squashing sensitivity in the Jacobian sense is upper bounded by a quantity related to the sheaf effective resistance between the nodes. The bottleneck thus need not lie in the graph itself: it can be relocated, and reduced, by adjusting the sheaf. We instantiate this idea in FlatNSD, a simple message-passing variant of Neural Sheaf Diffusion, and show that it implicitly learns to modulate total sheaf effective resistance, performing well on benchmarks designed to stress over-squashing without altering the original graph topology.
PDF
arXiv cs.CLOct 2
Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents
Mincheol Daniel Song, Joshua Ward, Jake Jung, Guang Cheng
LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high leverage applications such as healthcare, this presents a critical risk where system mistakes can be costly. These reliability failures are also resource failures: an incorrect reasoning trajectory spends computation budget on outputs that must be discarded. We introduce Sentinel, a trajectory-derived, classifier-based confidence layer that analyzes an agent's reasoning, code and database outputs to decide at three points whether to stop: refusing unanswerable questions before the agent runs, halting doomed trajectories mid-run, and withholding untrustworthy answers at delivery. Here, utilizing Chow's rule, we optimize decisions under the EHRSQL shared task's Reliability Score, which penalizes incorrect answers given a utility weighting, and find on the benchmark EHRSQL that Sentinel raises this score from +0.08 to +0.24 when mistakes have a low utility weighting, well above the +0.03 earned by refusing every question, with delivered-answer accuracy rising from 54% to 69% as coverage falls from 84% to 55%. At…
PDF
arXiv eess.SYOct 2
One-Cycle Fault Classification and Faulted-Line Identification on the PROTECT-90 Dataset: An Initial Application Benchmark
Emad Abukhousa, Abdulaziz Qwbaiban, Saman Zonouz, A. P. Sakis Meliopoulos
Open electromagnetic-transient datasets are beginning to make reproducible learning-based protection studies possible, but the practical use of these datasets still requires application-level benchmarks that define timing, sensing, and validation assumptions. This paper presents an initial application benchmark on the recently released PROTECT-90 dataset for two protection-oriented tasks: fault-type classification and discrete faulted-line identification. A compact one-dimensional convolutional neural network (CNN) is evaluated using post-inception windows of 0.25, 0.5, 1, and 2 cycles under strict episode-wise splitting. A non-convolutional multilayer perceptron (MLP) is also trained as an architecture-control baseline. The results show that both tasks are nearly saturated under full observability, with one-cycle test accuracies of 99.84% for fault type and 100.00% for line identification. The main performance variation appears under reduced observability: current-only inputs preserve line identification accuracy at 100.00%, whereas voltage-only inputs reduce line identification accuracy to 53.09% with the CNN and 50.57% with the MLP. This indicates that the limiting factor is…
PDF
arXiv cs.CVOct 2
Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution
Feiran Wang, Bin Duan, Junyi Wu, Gaowen Liu, Yan Yan
Video world models aim to preserve scene structure and predict how dynamic objects evolve beyond visual observations. We present Kepler4D, a framework for future video generation through explicit 4D scene state evolution. Given a monocular video, Kepler4D constructs a shared 3D representation of background geometry, object motion histories, coarse spatial supports, and semantic context. Chain-of-Motion summarizes observed motion and uses a vision-language model to select structured speed and heading decisions and decide whether to bound object-center height from below. A deterministic rollout converts these decisions into future object trajectories for inspection and editing before synthesis. We render the evolving proxies into geometric controls for a pretrained video generator, separating coarse object motion from the synthesis of appearance and articulation. Experiments on real-world videos demonstrate that Kepler4D enables controllable object motion and plausible future rollout while preserving scene consistency.
PDF
arXiv cs.CVOct 2
Watermarks and Fingerprints as Soft Bindings for Content Provenance: An Open-Licence Benchmark for Images, Audio and Video
Seyedmahdi Kazempourradi, Ramtin Mojtahedi, Behrang Mohseni
Content-provenance standards such as C2PA let a platform recover a stripped manifest through a soft binding: an invisible watermark read from the content, or a fingerprint looked up in a registry. We benchmarked both families under one protocol, restricted to openly available models whose licences we audited, on public media, with false-match rates calibrated on held-out negatives and source-level bootstrap intervals for performance estimates. For watermarking we evaluated 25 image, 7 audio and 7 video configurations from 12 methods on perceptual quality, robustness, false positives and cost; for fingerprinting, 35 methods on registries of up to 98,985 images, partial edits and adversarial attacks. PixelSeal gave the best balance for image and video watermarks and AudioSeal for audio, but the error-correcting detector of every TrustMark variant fired on 5.9 to 15.3% of unmarked images, so a verifier should test the expected payload. Among fingerprints, copy detectors trained on non-commercial data detected up to 75.5% of transformed images at a pair-level false-match rate of $10^{-7}$ and DINOv2, the best permissively licensed method, 65.0%; near-copies in a product catalogue…
PDF
arXiv cs.LGComputer visionOct 2
You May Be Running the Wrong Inception Crop
Jason Chuan-Chih Chou
A decade after its inception, Inception crop has become the standard crop-based data augmentation method for training deep vision models. Not only is its practice of uniformly sampling crop scale and aspect ratio widely adopted, but also its lower and upper bounds, with the scale lower bound being the sole exception that is sometimes tuned. It is therefore surprising that the standard implementation in the TensorFlow / JAX ecosystem samples crop scale with probability density function $f(A) \propto \frac{1}{\sqrt{A}}$ unlike the PyTorch counterpart, which follows the original description. Motivated by this discovery, we train 522 ViT-S/16 models on the ImageNet-1k dataset with various training budgets and crop scale distributions. We reach $78.78\pm0.09$ top-1 val. accuracy with 90 epochs of training budget and find that 1. Higher training budget requires stronger augmentation; 2. Lower tail of the distribution of the crop scale determines the augmentation strength of Inception crop; 3. Models trained with higher training budget exhibit sparser saliency, regardless of the crop scale distribution or weight decay. Based on 2. we revisit the performance of Beta crop, whose softer…
AIEvals70PDF
arXiv cs.LGOct 2
Consideration Circuits: Depth Separation and Universality Beyond a Single Softmax
Junjie Xiao, Huiwen Jia
Most feature-based choice models, classical and deep, score items and apply a single softmax. We introduce consideration circuits (CC), feature-based models of multi-stage choice defined by directed acyclic graphs of multinomial logit (MNL) units. Source units assign probabilities to menu items, and internal units combine predecessor distributions using MNL weights computed from their probability-weighted feature summaries. On a three-item compromise task with fixed non-collinear features, menu-independent random-utility models (RUM), including a single MNL unit, suffer an error bounded away from zero. For CC, in contrast, we establish a sharp depth--norm separation: increasing depth from $2$ to $3$ reduces the optimal maximum taste-vector norm for error $ε$ from $Θ(\log(1/ε)/ε)$ to $Θ(\log(1/ε))$. The depth-$2$ lower bound holds for arbitrary width and menu-independent routing biases, while a five-node depth-$3$ circuit with zero routing biases attains the logarithmic rate. More generally, we characterize two geometric conditions that are necessary and sufficient for approximating arbitrary deterministic choice tables on finite menu families. Under these conditions, depth $3$…
PDF
arXiv cs.LGOct 2
Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization
Junjie Xiao, Huiwen Jia
Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initialization affects the subsequent training trajectory. Classical implicit-bias results characterize the direction selected by prolonged training, but this direction alone does not provide information regarding the intermediate behavior. We address this question through a geometric approximation of full-batch logistic gradient descent (GD) trajectories on strictly linearly separable data, with large initialization of scale $R$ motivated by prior training. From any limiting normalized initial position, we use minimum-norm projection rules to construct a unique continuous ideal path consisting of finitely many linear segments. The path has two stages: negative-margin correction followed by minimum-margin growth. We prove that, after an explicit two-stage time reparameterization, the fixed-step GD trajectory divided by $R$ converges uniformly to this path on every fixed parameter interval as $R\to\infty$. Further, our quantitative error bounds account for initialization perturbations and the transition between stages. This approximation provides…
PDF
arXiv cs.LGOct 2
ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training
Omatharv Bharat Vaidya, Ashwin Vinod, Pedram Akbarian, Aditya Sai Ellendula, Connor T. Jerzak +1
Mixture-of-experts (MoE) language models send each token to a few experts, so each expert is trained on a different part of the data, and this part changes during training. With a shared learning rate, Muon applies updates of roughly the same size to expert matrices of the same shape, even when an expert's update is poorly aligned with its current gradient. We here propose ExpertMuon-Compass (Compass), which multiplies the Muon step of each expert by two factors. A family factor compares the cosine between the expert's orthogonalized update and its gradient with the same cosine for the other experts in its layer. A scalar radius aggregates the alignment between corresponding rows of the update and gradient into one step-length multiplier. Compass keeps the update direction and the momentum buffer of Muon. In pretraining on FineWeb-Edu, Compass with Nesterov momentum on all matrices performs as well as or better than Muon, NorMuon, and other optimizers, with weight decay matched to NorMuon in the longer runs. Adding its factors to NorMuon gives the same or a lower loss than NorMuon. Compass is the most effective when the data seen by each expert varies during training, for…
PDF
arXiv cs.CVOct 2
From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models
Feiran Wang, Xiaoqi Wang, Ziwei Li, Wenbin He, Yan Yan +1
Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language models (VLMs) and benchmarks for spatial reasoning primarily focus on observed scenes, leaving predictive spatial reasoning beyond the observed interval underexplored. To this end, we introduce SpatialMind, a metric-scale VLM for spatial reasoning and future prediction. Its metric depth adapter anchors spatial reasoning to real-world scale, while its progressive state chain establishes current spatial states and observed dynamics as the foundation for future prediction. Given a video prefix, SpatialMind predicts distances, motion directions, and spatial relations in both observed and unseen future frames. For training and evaluation, we build a scalable data engine that grounds entity descriptions in metric geometry to generate question-answer pairs and state supervision. Using this engine, we construct the SpatialMind-30K dataset and the SpatialMind-2K benchmark, both covering driving and everyday egocentric scenes. The benchmark spans eight tasks across three levels: current-state understanding, observed-dynamics understanding, and…
PDF
arXiv cs.LGOct 2
Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection
Mohsen Nayebi Kerdabadi, Xinrou Li, Yao Xiao, Zijun Yao, Xin Sun
Account takeover (ATO) fraud is a growing threat to digital banking, requiring effective detection while minimizing friction for legitimate customers. Production systems predominantly rely on tabular models that score sessions in isolation, discarding the relational structure of the underlying interaction network. Although graph-based models exploit relationships among sessions and network entities, they primarily reason over local neighborhoods and therefore capture only part of the problem: fraud risk depends jointly on the local relational structure surrounding a session and the evolving global state of the fraud ecosystem. We present HERMES (HEterogeneous Relational Micro--macro graph transformer Encoder for high-risk Sessions), a dual-scale architecture that jointly models these complementary scales of information. Micro-GT captures local heterogeneous graph structure through structured, relation-aware attention over a temporally safe session neighborhood. Complementing this local representation, Macro-GT models ecosystem-level context using non-anticipative climate tokens that summarize fraud dynamics, platform shifts, and infrastructure reuse, together with adaptive class…
PDF
arXiv cs.LGAgentsOct 2▲ 12
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
Som Sagar, Shasha Li, Hejie Cui, Ransalu Senanayake, Sercan Ö. Arık
Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each design choice is observable only through execution, tailoring a harness to each query has required either executing alternatives at inference time or costly manual design. We introduce SHIFT, which moves execution out of the per-query search loop. A local LLM architect learns a policy over harness-building actions from search, and a value function that predicts, from measured executions, a utility balancing accuracy against execution cost. For each query, Monte Carlo tree search uses these predictions to construct a harness. Across 9,193 tasks in six benchmarks, from math to document and general-assistant tasks, with a Gemini 3.5 Flash executor, SHIFT attains the highest mean accuracy, about 80%, outperforming 17 baselines that span prompting, prompt optimization, and workflow search, and exceeding the strongest baseline by 7.2 percentage points. A cheaper mode of SHIFT also attains a higher mean accuracy than every baseline while using 32% fewer execution tokens than the strongest baseline. We further show…
AI90PDF
arXiv cond-mat.mtrl-sciOct 2
Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
Robert Robinson, Shakti Prasad Padhy, Sushant Sinha, Sk Md Ahnaf Akif Alvi, Juan Florez Coronel +4
The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach for efficiently navigating such spaces, but most workflows rely on fixed exploration-exploitation policies that lack the capacity to adapt to shifting constraints in dynamic campaigns typical of self-driving laboratories. In this work, we develop a multi-objective BO framework for alloy design under resource constraints, benchmarking strategies for adaptive policy tuning at each iteration. Our evaluation covers a septenary refractory high-entropy alloy (RHEA) system focused on maximizing melting temperature and minimizing density, and an Fe-Co-Ni-based soft magnetic alloy system targeting saturation magnetization, coercivity, and hardness. We compare an exploitation-focused strategy, a fixed mixed exploratory/exploitative policy, and two distinct LLM-based adaptive strategies with different approaches to batch allocation and campaign signal interpretation, evaluated…
PDF
arXiv cs.AIOct 2
Auditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation
Ji Young Byun, Anthony Hu, Jesse Rogers, Roujia Wang, Manasa Kesapragada +1
Multi-agent systems built on large language models (LLMs) are increasingly applied to scientific discovery and hypothesis generation. Both the effect of refinement and the diversity of the delivered set are hard to interpret before experimental ground truth exists, and both are typically reported by deciding whether pairs of generated hypotheses describe the same underlying mechanism. We study two evaluation questions that rest on this pairwise equivalence judgment: (1) how much self-critique changes delivered hypotheses beyond run-to-run variability, and (2) how the equivalence rule used to group hypotheses affects measured diversity. Across four proprietary instances, we hold opening hypotheses fixed, rerun the downstream workflow with 0, 1, and 5 critique rounds, and score matched hypothesis pairs with an LLM-as-a-judge. Relative to matched same-depth reruns, moving from 0 to 1 round produces 34.5 percentage points (pp) of additional mechanism-level divergence, whereas 1 to 5 rounds adds 1.3 pp. We then compare three equivalence rules: term frequency--inverse document frequency (TF--IDF) similarity, dense embeddings, and the same LLM-as-a-judge. We construct controlled…
PDF
arXiv cs.CLOct 2
PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
Jingquan Wang, Jun Yin, Xu Han, Yongsheng Mei, Jie Hao +1
Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses. A socially competent agent must infer users' unstated goals, respect their preferences, and adapt as the conversation unfolds. These behaviors are inherently multi-turn and social, making them hard to optimize: real interaction data is scarce, and user preferences are typically latent rather than directly observable. To address these challenges, we build on a persona-driven social simulation environment (consisting of a persona library, LLM-based user simulators, and a user-satisfaction scoring system ranging from [0, 1]), to introduce preference-batched GRPO (PB-GRPO), a post-training algorithm that learns socially adaptive policies from conversation-level feedback. Compared to vanilla GRPO, PB-GRPO computes advantages using a normalization estimated across a bucket of users with similar preferences, stabilizing training across a diverse social population. Empirical evidence shows that PB-GRPO improves models' social behavior over strong reinforcement learning baselines in our simulated…
PDF
arXiv astro-ph.IMOct 2
Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy
Kshitij Duraphe, Aravind Kannappan, Dun Li Chan, Okiki Famutimi, Yaswant Sai Ejjagiri +2
In this paper we investigate whether geometrically aligned astronomical representations are also scientifically interchangeable. We analyze every layer's representation from 36 pretrained models using cross-matched optical images, infrared images, and spectra. All 139 analyzed model-survey comparisons show significant local-neighborhood alignment somewhere in the network after accounting for the search over depth. However, alignment does not generally increase with network depth and can be stronger for the changes between consecutive computational blocks than for the block outputs themselves. We find that geometry-selected stages under-perform label-selected stages in every image-transfer comparison; moreover, every final HSC-COSMOS-Web model pair is aligned while every redshift transfer has negative R^2. Models can therefore recover a similar cross-survey geometry among astronomical objects without recovering a survey-invariant linear encoding of the physical properties tested here.
PDF
arXiv cs.AIOct 2
InvestigationWorlds: An Agentic Environment for Legal Investigation
Albert Yu Sun, Andrew Benard, Sil Hamilton, Anna Teresita A. Marcelo, Yong Jae Kim +6
We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summary judgment motion. This motion relies upon a record composed of real evidence exhibits, and results in a court-adopted hypothesis that is treated as ground truth for the purposes of deciding the motion. Each environment is built from a real U.S. Federal Court case retrieved from Public Access to Court Electronic Records (PACER) and augmented by an attorney-validated generation pipeline that synthesizes role-tagged documents around the original record. The resulting corpus admits multiple coherent factual readings, only one of which matches the court-adopted hypothesis. Evaluating on 100 cases, we find agents often commit to incorrect hypotheses despite retrieving relevant evidence, struggling to distinguish the court-adopted hypothesis from alternative hypotheses.
PDF

Papers

Open problems across fields

Dynamic model and policy routing for general-purpose AI1 paper raises it · 1 addresses it
Balancing performance and computational cost across diverse tasks and modalities is critical for scalable AI systems.
- Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systemsraises · addresses
Cross-repository consistency in coding agents1 paper raises it · 1 addresses it
Real-world software development often requires coordinated changes across interdependent repositories, which current agents struggle to handle.
- CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises · addresses
Efficient long-video generation with consistent quality1 paper raises it · 1 addresses it
Real-time long-video generation demands continuous output without quality degradation or camera drift, which current methods fail to achieve efficiently.
- Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
Local decision-making for reasoning compression1 paper raises it · 1 addresses it
Reducing inference costs without sacrificing accuracy requires models to know when to stop reasoning, not just how to shorten outputs.
- Think Less, Locally: Local Preference Learning for Reasoning Compressionraises · addresses
Unified taxonomy and coordination for agentic systems1 paper raises it · 1 addresses it
Fragmented terminology and rapid growth in agentic systems hinder systematic understanding and coordination across tasks.
- Advances in Agentic Computer Graphicsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Rising research topics

Databases11+175.0%
DevOps & cloud16+128.6%
Speech emotion17+54.5%
Linear bandits117+53.9%
Anomaly detectors29+31.8%
Federated learning42+31.2%
Algorithmic trading26+30.0%
Channel state information18+28.6%

Rising research topics

Ask the research

Sample

Papers

arXiv cs.LGOct 3
Principled Top-$k$ Selection for Language Models with Hybrid Gradients
Xuchen Gong, Junfei Sun, Tian Li
Selecting the best $k$ items out of $m$ candidates is a critical component of modern large language model systems, such as document selection in Retrieval-Augmented Generation (RAG) and expert routing in Mixture-of-Experts (MoEs). However, training these selection modules remains challenging due to weak gradient signals and suboptimal exploration-exploitation tradeoffs. Furthermore, prior works often rely on heuristics, lacking principled objectives and approaches that explicitly model and solve the top-$k$ selection problem. In this work, we propose a principled objective for training selection modules, whose gradient naturally provides richer training signals in a hybrid form---containing a supervised-gradient component and a policy-gradient component. We show that the selection problem becomes harder as $m$ increases, and our algorithm converges at rate $O(1/\sqrt{T})$, with the optimal upper bound achieved by balancing between bias and variance. Practically, we apply our method to a set of tasks involving top-$k$ selection, including synthetic regression problems, RAG, and MoE systems, showing that our method outperforms the baselines in next-token prediction perplexity and…
PDF
arXiv cs.CVOct 3
Diagnosis-Conditioned Spatial Gating and Decoder-Level Supervised Contrastive Learning for Radiology Report Generation
Md Mustafizur Rahman, Mylene C. Q. Farias
Radiology report generation models can produce fluent text while still containing finding-level inaccuracies. Diagnosis-driven methods improve generation by conditioning on predicted findings, but these predictions do not directly modify the visual patch features provided to the decoder, and global gating applies the same modulation across spatial locations. We introduce a Position-Aware Gate (PAG) that uses predicted finding representations to modulate visual patches spatially without region supervision. We also propose a Decoder-level Supervised Contrastive Loss (DSCL) that structures decoder representations using shared positive findings rather than instance identity. On MIMIC-CXR, PAG+DSCL improves clinical efficacy (CE) F1 from 0.484 to 0.502 over a matched global-gate reference, while PAG and DSCL individually reach 0.491 and 0.495. Without additional fine-tuning, the combined model achieves 0.226 CE F1 on IU X-Ray, compared with 0.211 reported by PromptMRG.
PDF
arXiv cs.LGOct 3
How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws
Ziheng Cheng, Yixiao Huang, Hanlin Zhu, Somayeh Sojoudi
Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning. Training on mathematics can improve performance in other domains, yet gains in Pass@1 can coincide with lower Pass@$N$ than the base model. This raises a fundamental question: does RL expand an LLM's reasoning boundary, or merely reweight its existing reasoning space? We revisit these phenomena across Qwen and Gemma model families, showing both cross-domain gains and forgetting, while coverage at large sampling budgets increases on some tasks and decreases on others. Detailed analysis of solution traces before and after RL indicates a shift in the reasoning strategies the model employs, motivating a two-stage autoregressive policy model that separates \emph{strategy selection} from problem-specific execution. Within this framework, we prove how RL's implicit bias reshapes strategy preferences, allowing gains on some tasks while suppressing strategies required by others. This mechanism can also broaden or narrow coverage at a given sampling budget even without expanding strategy support. We further provide theoretical justifications for log-sigmoid and…
PDF
arXiv stat.MLOct 3
Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
André Ribeiro, Germano Barcelos, Amauri H. Souza, Diego Mesquita, Ana Luiza Tenório
Graph Neural Networks (GNNs) often struggle to capture long-range dependencies due to over-squashing -- a phenomenon in which the repeated compression of node embeddings into finite-size messages causes representations to collapse. Over-squashing is most often diagnosed as a property of the graph topology, with effective resistance serving as a principled measure of the bottleneck. We provide a complementary view on the matter: building on cellular sheaves, we introduce sheaf effective resistance, a generalization of effective resistance that depends on the sheaf attached to the graph, and we prove that for flat vector bundles, the over-squashing sensitivity in the Jacobian sense is upper bounded by a quantity related to the sheaf effective resistance between the nodes. The bottleneck thus need not lie in the graph itself: it can be relocated, and reduced, by adjusting the sheaf. We instantiate this idea in FlatNSD, a simple message-passing variant of Neural Sheaf Diffusion, and show that it implicitly learns to modulate total sheaf effective resistance, performing well on benchmarks designed to stress over-squashing without altering the original graph topology.
PDF
arXiv cs.CLOct 2
Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents
Mincheol Daniel Song, Joshua Ward, Jake Jung, Guang Cheng
LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high leverage applications such as healthcare, this presents a critical risk where system mistakes can be costly. These reliability failures are also resource failures: an incorrect reasoning trajectory spends computation budget on outputs that must be discarded. We introduce Sentinel, a trajectory-derived, classifier-based confidence layer that analyzes an agent's reasoning, code and database outputs to decide at three points whether to stop: refusing unanswerable questions before the agent runs, halting doomed trajectories mid-run, and withholding untrustworthy answers at delivery. Here, utilizing Chow's rule, we optimize decisions under the EHRSQL shared task's Reliability Score, which penalizes incorrect answers given a utility weighting, and find on the benchmark EHRSQL that Sentinel raises this score from +0.08 to +0.24 when mistakes have a low utility weighting, well above the +0.03 earned by refusing every question, with delivered-answer accuracy rising from 54% to 69% as coverage falls from 84% to 55%. At…
PDF
arXiv eess.SYOct 2
One-Cycle Fault Classification and Faulted-Line Identification on the PROTECT-90 Dataset: An Initial Application Benchmark
Emad Abukhousa, Abdulaziz Qwbaiban, Saman Zonouz, A. P. Sakis Meliopoulos
Open electromagnetic-transient datasets are beginning to make reproducible learning-based protection studies possible, but the practical use of these datasets still requires application-level benchmarks that define timing, sensing, and validation assumptions. This paper presents an initial application benchmark on the recently released PROTECT-90 dataset for two protection-oriented tasks: fault-type classification and discrete faulted-line identification. A compact one-dimensional convolutional neural network (CNN) is evaluated using post-inception windows of 0.25, 0.5, 1, and 2 cycles under strict episode-wise splitting. A non-convolutional multilayer perceptron (MLP) is also trained as an architecture-control baseline. The results show that both tasks are nearly saturated under full observability, with one-cycle test accuracies of 99.84% for fault type and 100.00% for line identification. The main performance variation appears under reduced observability: current-only inputs preserve line identification accuracy at 100.00%, whereas voltage-only inputs reduce line identification accuracy to 53.09% with the CNN and 50.57% with the MLP. This indicates that the limiting factor is…
PDF
arXiv cs.CVOct 2
Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution
Feiran Wang, Bin Duan, Junyi Wu, Gaowen Liu, Yan Yan
Video world models aim to preserve scene structure and predict how dynamic objects evolve beyond visual observations. We present Kepler4D, a framework for future video generation through explicit 4D scene state evolution. Given a monocular video, Kepler4D constructs a shared 3D representation of background geometry, object motion histories, coarse spatial supports, and semantic context. Chain-of-Motion summarizes observed motion and uses a vision-language model to select structured speed and heading decisions and decide whether to bound object-center height from below. A deterministic rollout converts these decisions into future object trajectories for inspection and editing before synthesis. We render the evolving proxies into geometric controls for a pretrained video generator, separating coarse object motion from the synthesis of appearance and articulation. Experiments on real-world videos demonstrate that Kepler4D enables controllable object motion and plausible future rollout while preserving scene consistency.
PDF
arXiv cs.CVOct 2
Watermarks and Fingerprints as Soft Bindings for Content Provenance: An Open-Licence Benchmark for Images, Audio and Video
Seyedmahdi Kazempourradi, Ramtin Mojtahedi, Behrang Mohseni
Content-provenance standards such as C2PA let a platform recover a stripped manifest through a soft binding: an invisible watermark read from the content, or a fingerprint looked up in a registry. We benchmarked both families under one protocol, restricted to openly available models whose licences we audited, on public media, with false-match rates calibrated on held-out negatives and source-level bootstrap intervals for performance estimates. For watermarking we evaluated 25 image, 7 audio and 7 video configurations from 12 methods on perceptual quality, robustness, false positives and cost; for fingerprinting, 35 methods on registries of up to 98,985 images, partial edits and adversarial attacks. PixelSeal gave the best balance for image and video watermarks and AudioSeal for audio, but the error-correcting detector of every TrustMark variant fired on 5.9 to 15.3% of unmarked images, so a verifier should test the expected payload. Among fingerprints, copy detectors trained on non-commercial data detected up to 75.5% of transformed images at a pair-level false-match rate of $10^{-7}$ and DINOv2, the best permissively licensed method, 65.0%; near-copies in a product catalogue…
PDF
arXiv cs.LGComputer visionOct 2
You May Be Running the Wrong Inception Crop
Jason Chuan-Chih Chou
A decade after its inception, Inception crop has become the standard crop-based data augmentation method for training deep vision models. Not only is its practice of uniformly sampling crop scale and aspect ratio widely adopted, but also its lower and upper bounds, with the scale lower bound being the sole exception that is sometimes tuned. It is therefore surprising that the standard implementation in the TensorFlow / JAX ecosystem samples crop scale with probability density function $f(A) \propto \frac{1}{\sqrt{A}}$ unlike the PyTorch counterpart, which follows the original description. Motivated by this discovery, we train 522 ViT-S/16 models on the ImageNet-1k dataset with various training budgets and crop scale distributions. We reach $78.78\pm0.09$ top-1 val. accuracy with 90 epochs of training budget and find that 1. Higher training budget requires stronger augmentation; 2. Lower tail of the distribution of the crop scale determines the augmentation strength of Inception crop; 3. Models trained with higher training budget exhibit sparser saliency, regardless of the crop scale distribution or weight decay. Based on 2. we revisit the performance of Beta crop, whose softer…
AIEvals70PDF
arXiv cs.LGOct 2
Consideration Circuits: Depth Separation and Universality Beyond a Single Softmax
Junjie Xiao, Huiwen Jia
Most feature-based choice models, classical and deep, score items and apply a single softmax. We introduce consideration circuits (CC), feature-based models of multi-stage choice defined by directed acyclic graphs of multinomial logit (MNL) units. Source units assign probabilities to menu items, and internal units combine predecessor distributions using MNL weights computed from their probability-weighted feature summaries. On a three-item compromise task with fixed non-collinear features, menu-independent random-utility models (RUM), including a single MNL unit, suffer an error bounded away from zero. For CC, in contrast, we establish a sharp depth--norm separation: increasing depth from $2$ to $3$ reduces the optimal maximum taste-vector norm for error $ε$ from $Θ(\log(1/ε)/ε)$ to $Θ(\log(1/ε))$. The depth-$2$ lower bound holds for arbitrary width and menu-independent routing biases, while a five-node depth-$3$ circuit with zero routing biases attains the logarithmic rate. More generally, we characterize two geometric conditions that are necessary and sufficient for approximating arbitrary deterministic choice tables on finite menu families. Under these conditions, depth $3$…
PDF
arXiv cs.LGOct 2
Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization
Junjie Xiao, Huiwen Jia
Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initialization affects the subsequent training trajectory. Classical implicit-bias results characterize the direction selected by prolonged training, but this direction alone does not provide information regarding the intermediate behavior. We address this question through a geometric approximation of full-batch logistic gradient descent (GD) trajectories on strictly linearly separable data, with large initialization of scale $R$ motivated by prior training. From any limiting normalized initial position, we use minimum-norm projection rules to construct a unique continuous ideal path consisting of finitely many linear segments. The path has two stages: negative-margin correction followed by minimum-margin growth. We prove that, after an explicit two-stage time reparameterization, the fixed-step GD trajectory divided by $R$ converges uniformly to this path on every fixed parameter interval as $R\to\infty$. Further, our quantitative error bounds account for initialization perturbations and the transition between stages. This approximation provides…
PDF
arXiv cs.LGOct 2
ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training
Omatharv Bharat Vaidya, Ashwin Vinod, Pedram Akbarian, Aditya Sai Ellendula, Connor T. Jerzak +1
Mixture-of-experts (MoE) language models send each token to a few experts, so each expert is trained on a different part of the data, and this part changes during training. With a shared learning rate, Muon applies updates of roughly the same size to expert matrices of the same shape, even when an expert's update is poorly aligned with its current gradient. We here propose ExpertMuon-Compass (Compass), which multiplies the Muon step of each expert by two factors. A family factor compares the cosine between the expert's orthogonalized update and its gradient with the same cosine for the other experts in its layer. A scalar radius aggregates the alignment between corresponding rows of the update and gradient into one step-length multiplier. Compass keeps the update direction and the momentum buffer of Muon. In pretraining on FineWeb-Edu, Compass with Nesterov momentum on all matrices performs as well as or better than Muon, NorMuon, and other optimizers, with weight decay matched to NorMuon in the longer runs. Adding its factors to NorMuon gives the same or a lower loss than NorMuon. Compass is the most effective when the data seen by each expert varies during training, for…
PDF
arXiv cs.CVOct 2
From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models
Feiran Wang, Xiaoqi Wang, Ziwei Li, Wenbin He, Yan Yan +1
Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language models (VLMs) and benchmarks for spatial reasoning primarily focus on observed scenes, leaving predictive spatial reasoning beyond the observed interval underexplored. To this end, we introduce SpatialMind, a metric-scale VLM for spatial reasoning and future prediction. Its metric depth adapter anchors spatial reasoning to real-world scale, while its progressive state chain establishes current spatial states and observed dynamics as the foundation for future prediction. Given a video prefix, SpatialMind predicts distances, motion directions, and spatial relations in both observed and unseen future frames. For training and evaluation, we build a scalable data engine that grounds entity descriptions in metric geometry to generate question-answer pairs and state supervision. Using this engine, we construct the SpatialMind-30K dataset and the SpatialMind-2K benchmark, both covering driving and everyday egocentric scenes. The benchmark spans eight tasks across three levels: current-state understanding, observed-dynamics understanding, and…
PDF
arXiv cs.LGOct 2
Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection
Mohsen Nayebi Kerdabadi, Xinrou Li, Yao Xiao, Zijun Yao, Xin Sun
Account takeover (ATO) fraud is a growing threat to digital banking, requiring effective detection while minimizing friction for legitimate customers. Production systems predominantly rely on tabular models that score sessions in isolation, discarding the relational structure of the underlying interaction network. Although graph-based models exploit relationships among sessions and network entities, they primarily reason over local neighborhoods and therefore capture only part of the problem: fraud risk depends jointly on the local relational structure surrounding a session and the evolving global state of the fraud ecosystem. We present HERMES (HEterogeneous Relational Micro--macro graph transformer Encoder for high-risk Sessions), a dual-scale architecture that jointly models these complementary scales of information. Micro-GT captures local heterogeneous graph structure through structured, relation-aware attention over a temporally safe session neighborhood. Complementing this local representation, Macro-GT models ecosystem-level context using non-anticipative climate tokens that summarize fraud dynamics, platform shifts, and infrastructure reuse, together with adaptive class…
PDF
arXiv cs.LGAgentsOct 2▲ 12
Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction
Som Sagar, Shasha Li, Hejie Cui, Ransalu Senanayake, Sercan Ö. Arık
Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Because the value of each design choice is observable only through execution, tailoring a harness to each query has required either executing alternatives at inference time or costly manual design. We introduce SHIFT, which moves execution out of the per-query search loop. A local LLM architect learns a policy over harness-building actions from search, and a value function that predicts, from measured executions, a utility balancing accuracy against execution cost. For each query, Monte Carlo tree search uses these predictions to construct a harness. Across 9,193 tasks in six benchmarks, from math to document and general-assistant tasks, with a Gemini 3.5 Flash executor, SHIFT attains the highest mean accuracy, about 80%, outperforming 17 baselines that span prompting, prompt optimization, and workflow search, and exceeding the strongest baseline by 7.2 percentage points. A cheaper mode of SHIFT also attains a higher mean accuracy than every baseline while using 32% fewer execution tokens than the strongest baseline. We further show…
AI90PDF
arXiv cond-mat.mtrl-sciOct 2
Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
Robert Robinson, Shakti Prasad Padhy, Sushant Sinha, Sk Md Ahnaf Akif Alvi, Juan Florez Coronel +4
The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach for efficiently navigating such spaces, but most workflows rely on fixed exploration-exploitation policies that lack the capacity to adapt to shifting constraints in dynamic campaigns typical of self-driving laboratories. In this work, we develop a multi-objective BO framework for alloy design under resource constraints, benchmarking strategies for adaptive policy tuning at each iteration. Our evaluation covers a septenary refractory high-entropy alloy (RHEA) system focused on maximizing melting temperature and minimizing density, and an Fe-Co-Ni-based soft magnetic alloy system targeting saturation magnetization, coercivity, and hardness. We compare an exploitation-focused strategy, a fixed mixed exploratory/exploitative policy, and two distinct LLM-based adaptive strategies with different approaches to batch allocation and campaign signal interpretation, evaluated…
PDF
arXiv cs.AIOct 2
Auditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation
Ji Young Byun, Anthony Hu, Jesse Rogers, Roujia Wang, Manasa Kesapragada +1
Multi-agent systems built on large language models (LLMs) are increasingly applied to scientific discovery and hypothesis generation. Both the effect of refinement and the diversity of the delivered set are hard to interpret before experimental ground truth exists, and both are typically reported by deciding whether pairs of generated hypotheses describe the same underlying mechanism. We study two evaluation questions that rest on this pairwise equivalence judgment: (1) how much self-critique changes delivered hypotheses beyond run-to-run variability, and (2) how the equivalence rule used to group hypotheses affects measured diversity. Across four proprietary instances, we hold opening hypotheses fixed, rerun the downstream workflow with 0, 1, and 5 critique rounds, and score matched hypothesis pairs with an LLM-as-a-judge. Relative to matched same-depth reruns, moving from 0 to 1 round produces 34.5 percentage points (pp) of additional mechanism-level divergence, whereas 1 to 5 rounds adds 1.3 pp. We then compare three equivalence rules: term frequency--inverse document frequency (TF--IDF) similarity, dense embeddings, and the same LLM-as-a-judge. We construct controlled…
PDF
arXiv cs.CLOct 2
PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
Jingquan Wang, Jun Yin, Xu Han, Yongsheng Mei, Jie Hao +1
Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses. A socially competent agent must infer users' unstated goals, respect their preferences, and adapt as the conversation unfolds. These behaviors are inherently multi-turn and social, making them hard to optimize: real interaction data is scarce, and user preferences are typically latent rather than directly observable. To address these challenges, we build on a persona-driven social simulation environment (consisting of a persona library, LLM-based user simulators, and a user-satisfaction scoring system ranging from [0, 1]), to introduce preference-batched GRPO (PB-GRPO), a post-training algorithm that learns socially adaptive policies from conversation-level feedback. Compared to vanilla GRPO, PB-GRPO computes advantages using a normalization estimated across a bucket of users with similar preferences, stabilizing training across a diverse social population. Empirical evidence shows that PB-GRPO improves models' social behavior over strong reinforcement learning baselines in our simulated…
PDF
arXiv astro-ph.IMOct 2
Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy
Kshitij Duraphe, Aravind Kannappan, Dun Li Chan, Okiki Famutimi, Yaswant Sai Ejjagiri +2
In this paper we investigate whether geometrically aligned astronomical representations are also scientifically interchangeable. We analyze every layer's representation from 36 pretrained models using cross-matched optical images, infrared images, and spectra. All 139 analyzed model-survey comparisons show significant local-neighborhood alignment somewhere in the network after accounting for the search over depth. However, alignment does not generally increase with network depth and can be stronger for the changes between consecutive computational blocks than for the block outputs themselves. We find that geometry-selected stages under-perform label-selected stages in every image-transfer comparison; moreover, every final HSC-COSMOS-Web model pair is aligned while every redshift transfer has negative R^2. Models can therefore recover a similar cross-survey geometry among astronomical objects without recovering a survey-invariant linear encoding of the physical properties tested here.
PDF
arXiv cs.AIOct 2
InvestigationWorlds: An Agentic Environment for Legal Investigation
Albert Yu Sun, Andrew Benard, Sil Hamilton, Anna Teresita A. Marcelo, Yong Jae Kim +6
We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summary judgment motion. This motion relies upon a record composed of real evidence exhibits, and results in a court-adopted hypothesis that is treated as ground truth for the purposes of deciding the motion. Each environment is built from a real U.S. Federal Court case retrieved from Public Access to Court Electronic Records (PACER) and augmented by an attorney-validated generation pipeline that synthesizes role-tagged documents around the original record. The resulting corpus admits multiple coherent factual readings, only one of which matches the court-adopted hypothesis. Evaluating on 100 cases, we find agents often commit to incorrect hypotheses despite retrieving relevant evidence, struggling to distinguish the court-adopted hypothesis from alternative hypotheses.
PDF