Research

• Reliable request execution in streaming video generation1 paper raises it · 0 address it

  Models often fail to follow incremental user requests while maintaining state consistency in real-time video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• End-to-end deep search in real-world web environments1 paper raises it · 1 addresses it

  Agents struggle to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Evidence-grounded evaluation for audio-visual reasoning1 paper raises it · 1 addresses it

  Existing benchmarks often allow models to exploit textual or unimodal shortcuts, failing to test true multi-modal reasoning.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 13

  Revisiting Error Feedback for Model Quantization

  Wai-Yiu Keung, Chi Cui, Wing-Kin Ma, Jesús Cid-Sueiro, Hei Victor Cheng

  We study causal error-feedback coefficients as design variables for model quantization. Modeling instantaneous quantization errors as independent, zero-mean variables with a common fixed variance, we formulated a metric-dependent trace problem for designing feedback coefficients. The formulation resembles fixed-order GPTQ/LDLQ feedback and supports Jacobian-aware designs that account for downstream error propagation. For a positive-definite metric $\boldsymbol{H}$, we prove that the joint rotation-feedback trace minimum is $n\det(\boldsymbol{H})^{1/n}$ and present an attaining pair using the geometric mean decomposition. Experiments on synthetic networks, trained MLPs, and language models show benefits from downstream-sensitive feedback, but also reveal that trace optimality need not improve finite-level performance. Small QAT experiments further illustrate direct loss-driven feedback tuning with fixed or trainable network weights.

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Human-Inspired Asymmetric Collaboration for Dual-Student Semi-Supervised Medical Image Segmentation

  Huiyi Ren, Ziming Fang, Jiaming Cai, Rui Xu, Haojie Li

  Dual-student learning enriches predictive diversity in SSMIS by introducing a strongly augmented view alongside a weakly augmented view. Insufficient strong augmentation may homogenize the students, whereas excessive augmentation can corrupt anatomical evidence and destabilize collaboration. This challenge echoes feedback-regulated human instruction, where learners receive differentiated tasks and the task difficulty is continually adjusted according to their evolving responses. Inspired by these, we propose Human-Inspired Asymmetric Collaboration (HAC), a closed-loop dual-student framework that maintains weak--strong learning through adaptive difficulty calibration and geometry preservation. Specifically, Reinforcement-guided Difficulty Calibration (RDC) formulates strong-augmentation control as a window-level reinforcement learning process, using augmentation history, realized perturbations, and training responses to dynamically adjust the augmentation magnitude, operation number, and magnitude range. Meanwhile, the Gramian Geometry Preservation Constraint (G2PC) preserves the early-stage three-branch geometry through global volume and pairwise area constraints, preventing…

  PDF

  Summarize this
• arXiv quant-phOct 13

  Distance Prediction for Quantum Codes

  Nadav Schneider, Eliya Nachmani

  The distance of a quantum code is a fundamental metric that dictates its error-correction capability. While quantum low-density parity-check (qLDPC) families such as Bivariate Bicycle (BB) codes offer a promising pathway to low-overhead fault-tolerant quantum computing, computing their distance is challenging. Current exact solvers and even search heuristics that provide a distance upper bound suffer from severe computational bottlenecks, restricting the discovery of optimal codes. In this paper, we construct a dataset of BB codes with corresponding distance upper bounds obtained through high-budget heuristic searches. We introduce BB-Net, an attention-based neural network architecture for predicting the distance of BB codes. It achieves 96.39% accuracy on the reference distances in the test set, compared with 94.86% for state-of-the-art heuristics with a budget of up to $10^{4}$ times more computational runtime. On a subset with certified exact distances, BB-Net achieves 98.94%. By relieving the distance-calculation bottleneck, BB-Net enables faster screening of large code spaces, particularly in ML-driven search pipelines, and thereby can accelerate the discovery of novel…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Monitoring latent reasoning in looped language models

  Pawel Olszowiec, Paulina Tomaszewska, Maciej Żelaszczyk, Michal Byra, Neo Christopher Chung

  Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost. Despite their rising popularity, the analysis of looped LMs is still in its infancy: little is known about whether the iterative transformations actually improve their capabilities, or whether these models remain stable under prompt perturbation. We construct an inspection protocol rooted in Mechanistic Interpretability comprising five diverse lenses. We apply it to examine eight looped LMs from four families. Models differ in many aspects but the key one is whether the prompt is transmitted only within the looped state (carry loops: Ouro, LoopUS) or re-supplied at every iteration (re-read loops: Parcae, and Rec-OLMo & Huginn from the Raven family). The results of our study provide valuable insights concerning safety and efficient use of looped language models.

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made

  Ayoub Merimi, Souhail Bakkali, Abdeljalil Sakat

  Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp theory of decision validity and a decision ledger that realises it. Six timestamps define a decision; a freshness ceiling bounds what up-to-date evidence guarantees at action time, placing the remaining risk in information published afterwards. Accuracy then factorises into two capabilities: routing, which delivers that information to affected decisions before their revision deadlines, and temporal judgment, which reads it for the time of action. The ledger is persistent state holding each decision's times, evidence and background knowledge, indexed by watch conditions written at decision time. Controlled decision streams with exact labels confirm four predictions across five LLMs, from 8B to frontier scale: freshness alone yields exactly the accuracy the ceiling predicts; models act on decisive news once it arrives, so accuracy follows routing; the ledger's index sets what routing reaches, and watch conditions reach indirect dependencies at low exposure; and the remaining errors concern when a change takes…

  PDF

  Summarize this
• arXiv cs.CVOct 13▲ 3

  H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression

  Or Ronai, Vladimir Kulikov, Tomer Michaeli

  Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining them as task-specific codecs. Recent codebook-based approaches such as Turbo-DDCM achieve strong perceptual quality at ultra-low bitrates, but their reliance on dense Gaussian codebooks remains costly in both memory and computation, and scales poorly with the large latent dimensions of modern image and video generators. Their combinatorial bitstream encoding further becomes computationally heavy at this scale. We introduce H-DDCM, a scalable generative compression framework that replaces Gaussian codebooks with implicit randomized Hadamard dictionaries. The fast Walsh-Hadamard transform allows for implicitly synthesizing full-dimensional dictionaries with $O(d \log d)$ compute for projection and reconstruction and $O(d)$ memory, without materializing the full-dimensional dictionary. We further introduce an efficient table-free lexicographic coding scheme that makes combinatorial encoding practical at larger dimensions. Beyond images, we adapt the framework to an autoregressive video flow model and develop a streaming compression…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Cheap, Consistent, Calibrated, but Biased? Typed Decision Models as Judges

  Fabian Lukassen, Christoph Weisser, Alexander Silbersdorff

  Typed decision models (TDMs) return a probability for each allowed answer instead of generating text, which makes them candidates for cheaply replacing LLM judges that compare two answers. Whether they share the biases of LLM judges is untested. We run the CALM benchmark's bias tests on eight TDMs and seven LLM judges of 2024 and 2026. Every TDM is biased, in three to eight of twelve tests. Emotional tone affects them most, and rewriting the better answer in such a tone lowers the accuracy of a typical TDM from 99% to 42%. TDMs are more biased than 2026 LLM judges. All eight change verdicts when the answers swap places, which the 2026 LLM judges hardly do, and several side with an answer that most people allegedly prefer or that a famous model allegedly wrote. Yet both kinds of judge are tripped up by the same prompts. The TDMs' probabilities show that most tests mainly flip verdicts the TDM was unsure of, and that good calibration does not protect against bias. As TDMs are more consistent and 37 times cheaper than 2026 LLM judges, our results suggest they can be attractive judges if their biases are tested for the task.

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering

  Donghoon Jung, Min Kim, Seojin Choi, Songeun Chae, Seohyon Jung

  Do language models carry information about narrative events before writing them, and how far ahead? We examine narrative lookahead through salient, state-changing events rather than tokens or response-level attributes. We extract 23,355 LLM-annotated events from 2,000 stories generated by four open-weight LLMs, labeling them along three nonexclusive dimensions of change: within agents, between agents, and in the story world, with human validation on a subset. Event segmentation and plot-independent labels enable comparisons across stories at horizons measured in events rather than in tokens. At event ends, we probe hidden states for upcoming event types and compare predictions with text-only predictors using matched prefixes. Across four models, future event types are decodable above prevalence baselines for at least four subsequent events, but probes significantly outperform both primary text-only predictors only for the next event. In exploratory steering with OLMo-3.1-32B, a probe-derived direction shifts the proportion of the target event type in both intended directions at higher strengths. Our event-level approach links the prediction of future narrative developments to…

  PDF

  Summarize this
• arXiv cs.LOOct 13

  Certifying Almost-Sure Reachability in Unknown MDPs

  S Akshay, Suguman Bansal, Gaurav Mahla

  {\em Specification-Guided Reinforcement Learning (RL)} has largely concerned itself with \emph{learning} an optimal policy against a formal specification in an unknown {\em Markov Decision Process (MDP)}. We take up the dual question. Given a policy already in hand, can one \emph{verify} that it is correct against a formal specification in an unknown MDP, using sampling access alone? Such a question arises naturally in safety-critical systems. We investigate it for the {\em almost-sure reachability property}, whose correctness is witnessed by a {\em ranking supermartingale (RSM)} certificate. Our first finding is negative. In the absence of any further information about the MDP, one can neither learn such a certificate nor verify a candidate one with probabilistic guarantees. On the positive side, we show that, under a mild restriction, a known lower bound $p_{\min}$ on nonzero transition probabilities, a correct certificate \emph{can} be learned with PAC-style guarantees. To the best of our knowledge, this is the first study of learning and verifying certificates for almost-sure reachability in unknown MDPs from sampling access alone. Finally, our experiments show that the…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features

  Enrico Chialà, Francesco Ferrini, Antonio Longa, Bruno Lepri, Filippo Maria Bianchi +2

  Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications. By leveraging the dependence between node features and graph structure, existing graph-specific methods handle missingness by propagating observed feature values along graph edges. However, these methods have mainly been evaluated in overly optimistic settings, where feature entries are removed independently and uniformly across the graph. This overlooks realistic scenarios in which missingness propagates among connected nodes, as can occur during localized sensing failures in sensor networks. We formalize this complementary notion as graph-structured mask dependence, where the joint distribution of missingness indicators is shaped by the graph, and introduce a controlled mechanism that instantiates this setting. We study propagation-based methods theoretically and empirically in this setting, showing that their effectiveness changes substantially compared with the uniformly random regime. Motivated by this limitation, we propose PEMix, designed to remain effective under challenging graph-structured missingness. Rather than…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  SYNPRED: A Synergistic Approach to Multimodal Learning for Clinical Prediction

  Ivana Janíčková, Yen Y. Tan, Thomas H. Helbich, Philipp Seeböck, Julieta Di Marco +4

  Multimodal medical data captures complementary aspects of disease. It provides a comprehensive basis for diagnosis and the identification of biological associations linked to progression or treatment response. Established contrastive learning approaches exploit shared information across modalities, but fall short in exploiting complementary, modality-specific signals relevant for a task. Here, we propose a synergistic multimodal variational autoencoder (VAE) framework that separates task-relevant unimodal and multimodal information from instance-specific variation task-irrelevant, allowing complementary signals across modalities to be leveraged for prediction. The method yields benefits even if modalities are missing at test time. We evaluate the method on a treatment response prediction task using medical imaging and RNA data. Empirical comparison with alignment-based and multimodal VAE state-of-the-art approaches demonstrates improved multimodal prediction performance, and consistent benefits for prediction from a single modality after multimodal training. The full code can be found here: https://github.com/cirmuw/SYNPRED.

  PDF

  Summarize this
• arXiv cs.LGOct 13

  A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge

  Cesare Barbera, Luca Stradiotti, Lorenzo Cascioli, Lorenzo Perini, Niek Tax +4

  Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too costly. Unfortunately, LLM judgments can exhibit systematic biases. Prior work has documented position, verbosity or model family of the candidate answers influencing the judge decision rather than their quality, while additional biases may remain undocumented. $\textit{Multicalibration}$ provides a natural framework to address this problem: each bias corresponds to miscalibration on an identifiable group, $\textit{e.g.}$, family bias manifests as overconfidence in answers generated by models belonging to the same family of the judge. The challenge is to fix miscalibration simultaneously across many, potentially unknown groups. To this end, we introduce $\mathrm{CaLLM}$, a post hoc framework that multicalibrates an LLM judge, thereby bounding all such biases simultaneously. We prove that $\mathrm{CaLLM}$ bounds the bias of every group whose error structure is captured by an available representation, and that augmenting it with explicit bias groups further reduces the residual bias. We…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Chain of Thought Monitoring Can Fail Even When CoT Is Necessary

  Lennart Bürger, Piotr Komorowski, Moritz Weckbecker, Evgenii Kortukov, Aakriti Jain +2

  Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the lack of a successful organizing principle that leads to generalizable conclusions about monitoring reliability in different regimes. Recent work attributes monitoring failures to the CoT not being necessary for the answer, and argues that CoT becomes monitorable when it is necessary. We show that this binary necessary/not-necessary organizing principle is too coarse by demonstrating that monitoring failures persist even if the CoT is necessary for the answer. In response, we introduce a more fine-grained organizing principle based on a hierarchy of four CoT necessity levels. Building on this hierarchy, we develop a framework for measuring CoT monitorability at the three lowest levels via intervention experiments. We demonstrate monitoring failures at all three of these levels on realistic, hard prediction tasks. On a difficult medical-diagnosis task, patient sex and a clinical attribute influence the answer in at least 19% and 24% of correct responses with a necessary CoT, respectively, yet their influence is…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  The Effect of Layer Ordering in Hybrid Architectures

  John Cooper, Mingchen Ma, Jiaqi Mo, Shengqi Qiu, Nathaniel Bastian +2

  Hybrid attention is rapidly becoming the dominant architectural choice for frontier models. Despite their successes, such architectures complicate model design by introducing additional choices, including the types and locations of layers. This combinatorially large design space has been studied empirically, but given the vast expense of training and evaluating models with different configurations, a principled understanding of the effects of layer selection and ordering is needed. We provide the first such analysis, showing that the dominant hybrid architecture is highly task-specific. Concretely, for any layer configuration, we prove that there exists a task where we can construct a model with this configuration that provably outperforms any other model of any different configuration under fixed resource constraints. Empirically, we observe that for standard training, learned hybrid architectures exhibit separations between layer orderings that match our theoretical findings. For instance, under the same memory budget, the optimal architecture predicted by our theory for a segmented retrieval task consistently achieves perfect accuracy, whereas the next strongest plateaus below…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits

  Ibne Farabi Shihab, Joyanta Jyoti Mondal

  Deleting singular components offers a precise way to remove a capability from a language model, yet the first-order spectral saliency used to rank components predicts only a local loss change, whereas deletion is a finite intervention. In this paper, we study how prediction error affects selective editing, where selective editing requires degradation of a target task while preserving others. We decompose the error into derivative transfer across item splits and nonlinear response along the deletion path. We establish that outer interval screening retains every feasible candidate when every candidate's intervals contain its finite validation loss changes on every task. We evaluate these effects using one answer-only negative log-likelihood objective for search, validation, and test, with disjoint calibration and evaluation masks. The primary configuration targets arithmetic in Mistral-7B-Instruct-v0.3 while preserving code and question answering; extensions cover Llama-3.1-8B-Instruct and reversed target roles. In the primary study, which deletes 1024 coordinates from a support of 7168, calibrated intervals cover 968 of 1024 evaluation masks. Outer screening reaches the…

  PDF

  Summarize this
• arXiv cs.CVOct 13▲ 21

  APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

  Sirui Zhang, Fangyun Wei, Dong Chen, Jinjing Zhao, Yitong Wang +3

  Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profile. APT coordinates three agents to construct evaluation sets from user requirements, diagnose model-specific strengths and failure modes, and generate reinforcement learning data with an adaptive prompt distribution that emphasizes underperforming capabilities. By repeatedly evaluating, diagnosing, and updating the generator, APT lets the current model's behavior shape its next training tasks, forming a feedback loop inspired by recursive self-improvement. For general-purpose settings without user-specified evaluation scenarios, we further develop an evaluation harness that enables broad and diverse evaluation set generation. Experiments across multiple base models, benchmarks, and generation architectures demonstrate that APT is model-agnostic, benchmark-agnostic, architecture-agnostic, and fully automated.

  Code
• arXiv cs.AIOct 13

  CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions

  Xinyang Liao, Lingyu Li, Kaicheng Shen, Yang Yao, Na Lu +2

  AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely targets general harms or specific companion platforms and risk categories, while relying on manually collected conversations, limiting scalable and user-grounded evaluation and mitigation. To address this, we introduce CompanionSafe, a unified evaluation-to-mitigation framework for AI companion safety. Its evaluation component, CompanionEval, provides scalable multi-turn evaluation by constructing 1,300 relationally grounded settings from diverse personas, matched companion characters, and dialogue scenarios across four turn tiers. Its mitigation component, CompanionGuard, converts benchmark-exposed failures into turn-localized supervision for companion-specific risk detection. Our results show that even strong LLMs and existing guard models remain vulnerable to companion-specific relational harms, while both closed- and open-source models exhibit increasing safety risks as interactions become longer. Together, CompanionEval and CompanionGuard form a practical evaluation-to-mitigation loop for AI…

  PDF

  Summarize this
• arXiv cs.AIOct 13▲ 20

  LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity

  Yibo Wang, Senjie Jin, Yansong Ning, Xinbing Liang, Haotian Luo +4

  Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, existing benchmarks primarily focus on academic research or synthetic tasks, leaving DR agents' capabilities in real-world life and professional productivity settings insufficiently evaluated. To bridge this gap, we introduce LifeSearch, a challenging benchmark comprising 203 Chinese and English tasks derived from real-user query seeds across 7 concrete life and productivity domains. With more than 4,500 hours of human annotation, we construct over 4,000 expert-written, fine-grained rubrics, covering both report-content criteria for coverage and accuracy and concrete criteria specifying values, units, dates, and URLs. We conduct extensive experiments on 12 advanced DR agents under a unified evaluation harness, systematically analyzing their performance patterns and failure modes. We find that even the best-performing frontier agent, GPT-5.6 Sol, achieves a score of only 63.4%, leaving substantial room for improvement on realistic life and professional DR tasks. We select the grading configuration by comparing candidate LLM judges…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses

  Kaiyu Huang, Yiting Li, Angyang Gu, Pinjia He, Minchen Yu +1

  Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these information gaps remain poorly characterized across models and execution harnesses. We present AM-Bench, a benchmark built from 48 tasks adapted from Terminal-Bench 2.0 and Harness-Bench. Each task includes a fully specified reference and six variants spanning ambiguous or missing goals, context, and constraints. We evaluate every pairing of five models and four harnesses over 20,160 runs. Our results reveal distinct execution deficits: goal gaps hinder completion, context gaps increase token use, and constraint gaps weaken compliance without necessarily preventing completion. Missingness lowers success more than ambiguity in all three domains. These effects also reshape system comparisons: advantages under complete information need not persist, and rankings depend on model $\times$ harness pairings and the evaluation criterion -- completion, success, or repeat consistency. Estimates based on observed clarification requests and matched fully specified runs further suggest that clarification could recover unfinished work while leaving…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  One-Sided Verification Under Limited Expert Review

  Fan Nie, Haotian Ye, Shurui Liu, Zihao Wang, Stefano Ermon +1

  AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a fundamental challenge as candidate generation scales beyond available review capacity. This paper studies verification under limited human effort, where rare valid solutions need to be prioritized while invalid candidates should be filtered out to reduce human workload. We adopt the one-sided verification objective that maximizes the rejection rate of invalid solutions (TNR) under a constraint on the false-rejection rate of valid ones (FNR), making human review cost an explicit term to minimize. Drawing on the intuition that verifying a specific error can be easier than discovering one, we introduce OSVerify, an algorithmic framework that decouples error proposal from error validation. The error proposer searches for errors in solutions across different granularities by hierarchical decomposition, while the validator distinguishes substantial errors from minor or hallucinated ones. Experiments on competition- and research-level benchmarks show that OSVerify reduces the number of human reviews of invalid solutions…

  PDF

  Summarize this

• Adversarial training42−16.0%
• Anomaly detectors29−17.1%
• Forecasting time63−18.2%
• Federated learning37−19.6%
• CAD models12−25.0%
• Inference & serving213−26.0%
• Frontier LLMs372−27.3%
• Teacher policy distillation46−28.1%