Research

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

  Models struggle to follow incremental multimodal requests while maintaining state consistency and visual fidelity.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• End-to-end deep search in real-world open Web environments1 paper raises it · 0 address it

  Agents cannot reliably explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises
• Prior-consistent solutions for ambiguous nonlinear inverse problems1 paper raises it · 1 addresses it

  Diffusion-based samplers often favor measurement-consistent but prior-inconsistent solutions in ambiguous cases, masking failures with best-of-k reporting.

  • Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problemsraises · addresses
• Explainable artifact detection in AI-generated videos1 paper raises it · 1 addresses it

  Detectors often fail to identify subtle artifacts or justify their decisions with faithful evidence.

  • Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videosraises · addresses
• Temporal trajectory modeling for clinical risk prediction1 paper raises it · 1 addresses it

  Existing multimodal approaches underutilize irregular, heterogeneous clinical data accumulated over time for accurate inpatient risk prediction.

  • TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Predictionraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 11

  To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse

  Zhiwei Lin, Jiahao Liu, Yan Liu, Chengpeng Wang

  Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Existing methods optimize such reuse for latency and generation quality, but its safety implications remain unclear. In this work, we systematically evaluate this issue across diverse sender-receiver pairs and reuse configurations. We refer to deviations from the receiver's native safety behavior as safety incompatibility. Our study shows that both the direction and magnitude of safety incompatibility depend on the model pair and reuse configuration, with value reuse causing substantially larger deviations than key reuse across all evaluated pairs. Furthermore, we propose VReparo, a technique that learns per-layer and per-KV-head affine maps offline to align reused sender value tensors with their receiver-native counterparts before decoding. Across two model pairs under full KV reuse and the state-of-the-art selective reuse setting, VReparo reduces the average HarmBench attack success rate (ASR) from 57.28% to 39.21% and the average StrongREJECT score from 0.4215 to 0.2163 upon our benchmarks, while retaining an average Time to First…

  PDF

  Summarize this
• arXiv cs.AIOct 11▲ 10

  History Replays Itself: Unleashing Long-Context Capability in Linear Attention

  Li Nanbo, Firas Laakom, Yilan Zhang, Piotr Piękos, Yimeng Chen +8

  Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ongoing computation and preserve information from an ever-growing history. This coupling has reinforced a prevailing view that the state's memory capacity defines the model's long-context capability. We challenge this presumed ceiling: \emph{recurrent computation need not bear the full burden of long-term storage}. We introduce NoteBank, a sparse episodic memory that archives selected text before future queries are known, uses the backbone's native features for writing and addressing, and reads retrieved evidence through its native forward computation via replay. This \emph{training-free, plug-and-play} interface requires no external embedding model, separately trained retriever, or separate neural reader. At one million tokens, it raises Gated DeltaNet's mean accuracy across six RULER retrieval tasks from 1.7% to 70.3%, with no observed significant retrieval degradation from 4K to 1M tokens. This recovery adds $\leqslant$0.025% to analytical FLOPs, with persistent context storage approximately 1/2,600 that of a Transformer's full MHA…

  PDF

  Summarize this
• arXiv cs.AIOct 11

  MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation

  Rui Tang, Hongqiu Wang

  Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centric systems may lose context, misuse tools, fail to verify consequential transitions, or cross authorization boundaries. Existing medical-agent benchmarks primarily emphasize terminal task outcomes, making it difficult to determine whether execution failures arise from the agent model, the runtime harness, or their interaction. We present the Medical Harness Protocol, an outcome-preserving framework that independently evaluates seven healthcare-specific process dimensions: Care Action Fulfillment, Clinical Resource Competence, Patient-Evidence Alignment, Clinical Workflow Continuity, Clinical Auditability, Closed-Loop Verification, and Clinical Conduct Boundaries. A normalized intervention trace further tracks whether runtime support is available, activated, delivered, adopted by the agent, and propagated into subsequent behavior. We instantiate the protocol as MedHarnessBench, comprising 342 executable tasks across FHIR/EHR operations, healthcare-administration interfaces, and multimodal clinical tools. Across…

  PDF

  Summarize this
• arXiv cs.CLOct 11

  TL;QR: Querying Temporal Discursive Patterns in Textual Corpora

  François Hublet, Vladimir Krsmanovic, Jesus Solano, Ahmed Bouhoula, Ana Oliveira da Costa

  Many questions about large textual corpora concern patterns that unfold over time, such as a political group whose stance on a topic drifts from support to criticism over several years of debates. We present TL;QR (Too Long; Query with logical temporal Reasoning), a declarative query language and open-source engine for finding such temporal discursive patterns. In TL;QR, a single query combines natural-language predicates, whose truth is judged by a Large Language Model (LLM), with regular expressions and the operators of a temporal logic. The LLM answers only local questions about individual text passages; a symbolic engine then aggregates these judgments over time and links every match to the recorded passages and predicate decisions behind it. With this division of labor, the temporal and relational reasoning stays exact and auditable even over long time horizons. In addition, when a query includes a regular-expression pre-filter, only a small fraction of the corpus ever reaches the LLM. On a suite of controlled synthetic benchmarks with temporally and semantically complex patterns, TL;QR is substantially more accurate than LLM-only baselines. In a case study on ten years of…

  PDF

  Summarize this
• arXiv cs.LGOct 11

  What DNA Foundation Models Learn Beyond Sequence Composition

  Vincenzo Yuto Civale, Andrew David Bagdanov, Alberto Magi

  Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition? We evaluate frozen representations from five DNA FMs against normalized k-mer frequencies across 57 genomic classification datasets and two exploratory gene-expression regression tasks. Simple k-mer features remain competitive with most models, whereas NTv3 shows a consistent advantage; the ranking is robust to globally fixed and multi-scale k-mer baselines and alternative downstream probes. To test incremental predictive utility directly, we compare global 6-mer features with their concatenation with each FM embedding under a matched Random Forest protocol. NTv3 improves 46 of 57 datasets (mean $Δ$MCC = +0.072), while Caduceus provides smaller gains and the other models do not improve mean MCC. We separately decompose embeddings into a component linearly predictable from 6-mer frequencies and a ridge residual, finding that linear recoverability does not reliably indicate downstream utility. Exact 6-mer-preserving shuffles further reveal task-relevant sequence-order sensitivity, most pronounced for NTv3, although order sensitivity alone does not guarantee predictive improvements.…

  PDF

  Summarize this
• arXiv cs.AIOct 11

  Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate

  Xupeng Chen, Chenqian Le

  Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair as changed or not, so they cannot tell a gate that acts on established change from one that acts on a hint. We write a task contract that separates the two (SUPERSEDED vs. NEEDS-CONFIRMATION vs. COMPATIBLE), label 500 test pairs built from STALE (change pairs plus same-user controls) with three LLM annotators and two human adjudicators (one author and a second annotator; provenance reported), and evaluate Jev, a typed "System One" decision model, under pre-registered hypotheses. Of the 179 test pairs STALE marks as changed, 72 meet the contract's bar for an established change. Jev never retired a claim on 141 same-conversation non-changes. Its failure is premature retirement: the binary gate retires 39.2% of claims whose change is only suggested. A three-way decision cuts this to 15.5% at a 15.3-point detection cost, which misses our pre-registered 10-point budget, and it lands on the binary gate's own threshold frontier; these verdicts hold under three readings of the gold labels. On a held-out vault scored against a second…

  PDF

  Summarize this
• arXiv cs.LGOct 11

  Preserving Updates in Low-Bit Recurrent State Quantization

  Haotian Li, Liran Dong, Kaicheng Xiao, Guoliang Xing

  Linear attention and recurrent models compress past tokens into a fixed-size state that is updated at every step. However, storing these states in high precision incurs substantial memory and bandwidth costs at large batch sizes, motivating low-bit state quantization. Unlike weights and key--value caches, a recurrent state is requantized after every update, so its quantization errors accumulate across steps. Our analysis shows that these errors are highly coherent across steps, so reducing per-step errors alone is insufficient. This coherence arises mainly from small updates that are lost in rounding. To preserve these updates, we intervene both before and at rounding. Before rounding, we propose Low-Rank Bypass (LRB), which accumulates small updates in a compact low-rank buffer and periodically merges its sufficiently large elements into the state. At rounding, we observe that a state element can even move opposite to its update, and such reversals prove particularly harmful. Therefore, we propose Bounded Directional Rounding (BDR), which rounds reversed elements toward their updates without additional storage. Although BDR enlarges the rounding error, it improves the model,…

  PDF

  Summarize this
• arXiv cs.AIOct 11

  SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications

  Yutong Cheng, Haifeng Chen, Peng Gao, Wei Cheng

  Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights. We study recursive self-improvement through behavioral specifications: natural-language code documentation that describes the behavior of program entities and guides agents in generating correct code. We formulate a self-improvement loop in which an agent generates code from its current specifications, evaluates it with execution-verified tests, and refines the specifications based on observed failures. The improved specifications then guide subsequent generation, progressively improving the agent's understanding of the codebase. However, recursive refinement is challenging because program entities are interdependent. Improving the specification of one entity can inadvertently degrade the correctness of others, a phenomenon we call output coupling. This creates a whack-a-mole effect in which local improvements cause regressions elsewhere, preventing consistent progress. We introduce SpecForge, a multi-frontier tree search framework that addresses this challenge with three mechanisms: (i) Pareto-guided state selection preserves…

  PDF

  Summarize this
• arXiv cs.LGOct 11

  Generalizable Model Editing Could Be More Than Direct Generalization

  Xiaotian Ye, Chunyao Yang, Xiaohan Wang, Junkai Chen, Yongqi Duan +2

  A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior as an input-output mapping and expecting a factual update to alter outputs on reasoning tasks. Yet despite substantial empirical effort, the field consensus remains that such generalization is highly challenging and elusive. However, when we deploy the latest models in an in-the-wild chatbot-user setting, we surprisingly find that even classical editing methods exhibit remarkably fluent generalization behavior. This motivates us to revisit the obstacles to generalization and the limitations of the prevailing paradigm. We find that direct generalization is fundamentally constrained both theoretically and practically: theoretically, it suffers from an identifiability issue; and practically, existing approaches attempting to circumvent this are further hindered by the ambiguity of their constructed biases and by vulnerability to being overridden by other factors such as optimization dynamics. We instead identify compositional generalization, empowered by the increasingly strong reasoning and composition…

  PDF

  Summarize this
• arXiv cs.CLOct 11

  bharatSetu: a 1M x 22 bridge for indic translation

  Haq Nawaz Malik, Nahfid Nissar, Faizan Iqbal

  India's Eighth Schedule recognises 22 languages, yet parallel data is uneven across them, and many language pairs, especially among lower-resource languages such as Bodo, Dogri, Santali and Kashmiri, lack direct bitext. We present BharatSetu 22-Indic 1M, a row-aligned table of 984,764 English sentences, each paired with machine translations into all 22 scheduled languages (21,664,808 Indic cells), generated with the sarvamai/sarvam-translate model family. Because every Indic cell in a row translates the same English sentence, any two columns form a translation pair: 462 directed Indic-to-Indic pairs, or 506 including English, without direct bitext. We call these pivot-derived pairs and propose a confidence layer that lets users choose how strictly each pair is connected. The corpus is machine-generated and not human-verified; quality is expected to vary by language, domain and sentence style, and pivot-derived pairs can inherit errors from both sides. We therefore release BharatSetu as a machine layer and propose a human-correction layer keyed to the same row identifiers, so that each corrected column upgrades every pair that uses it, together with an evaluation protocol. We…

  PDF

  Summarize this
• arXiv cs.LGOct 11

  RespFocus: Learning Temporal Evidence for Weakly Supervised Respiratory Sound Classification

  Yi Tian, Xiaohuan Chen, Yufei tang, Xinyu Lin, Hongliang Li +3

  Respiratory auscultation provides a low-cost means of assessing pulmonary function, yet transient crackles and sustained wheezes can be difficult to recognize in noisy clinical recordings. Conventional deep learning classifiers often operate as black boxes, offering limited insight into the temporal acoustic evidence supporting their predictions. We present RespFocus, a weakly supervised framework that uses multiple instance learning (MIL) to learn inspectable temporal evidence from cycle-level labels and integrate it into classification. We also introduce PedResp2026, a multicenter pediatric respiratory sound cohort collected in routine clinical environments with adjudicated cycle-level annotations. In classification experiments, RespFocus achieves four-class Scores of 69.55\% on public ICBHI 2017 and 72.91\% on PedResp2026. Evidence diagnostics and matched temporal interventions support the functional contribution of the learned evidence to model predictions. Together, these findings highlight RespFocus's potential as a tool for automated respiratory sound diagnosis.

  PDF

  Summarize this
• arXiv cs.LGOct 11

  TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks

  Jayoung Kim, Sanghyun Hong, Noseong Park

  Generative modeling for tabular data has advanced to the point where models can synthesize realistic records, recover missing values, and generate samples conditioned on class labels or observed attributes. Despite recent advances, existing approaches either require table-specific training or restrict in-context learning to single-cell prediction. In this work, we formulate these tabular generative tasks as a single problem: modeling the joint conditional distribution of an arbitrary set of target cells given the observed cells of an unseen table. To this end, we turn to diffusion, whose denoising objective is defined jointly over all target cells rather than one cell at a time. Under the pretraining distribution, this objective is minimized by the posterior predictive distribution over the target set. Building on this, we propose TabMosaic, a unified in-context diffusion model for generating mixed-type target cells in unseen, potentially incomplete tables without table-specific training. We further show that its pretraining objective bounds the conditional negative log-likelihood and the divergence from the posterior predictive for arbitrary target sets, extending the Bayesian…

  PDF

  Summarize this
• arXiv cs.LGOct 11

  DRanker: A Transformer-Based Multi-Task Ranking Model for the Disney+ Homepage

  Priya Nirmal Singh Khokher, Daniel Nemirovsky, Benjamin P. Whitesell, Ethan Sukrae Lee, Eric Wulf +2

  We present DRanker (Disney+ Ranker), a transformer-based multitask ranking model serving personalized recommendations on the Disney+ homepage. We describe the encoder-only architecture over enriched engagement-history sequences paired with a lightweight causal debiasing mechanism, and the inference stack that enables transformer-based ranking at scale. Through iterative development, we systematically evaluated more complex alternatives and found that simpler designs consistently outperformed them on offline metrics, qualitative behavioral evaluation, and in production. Deployed globally, DRanker drives over 1% lift in our key engagement metric and 0.5% lift in daily active users across all experiences powered by the ranker. We share practical lessons on data engineering, debiasing, and architectural choices that shaped our ranking system at scale.

  PDF

  Summarize this
• arXiv cs.CLOct 11

  Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop

  Sayantan Adak, Rima Hazra, Koyel Mukherjee, Digbalay Bose, Somnath Banerjee

  Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear. We present a process-centered synthesis of LLM tutoring that follows the path from learner-state infer- ence to pedagogical action, tutor training, eval- uation, and student simulation. This view ex- poses a central gap: implementing a tutoring component does not establish that it works or that its outputs meaningfully affect later stages. A structured study-level audit shows that peda- gogical evaluation is common, while evidence becomes much thinner for learner-conditioned intervention, human learning gains, and espe- cially transfer or delayed retention. Human studies nevertheless provide a conditional posi- tive result: LLM tutors can improve learning, but benefits depend on pedagogical structure, learner engagement, and how learning is mea- sured. We argue that progress requires validat- ing the interfaces between tutoring stages, not only improving individual components.

  PDF

  Summarize this
• arXiv cs.AIOct 11

  FARL: A Fully Automated Pipeline of RL Interface and Solver Design

  Tianyu Jin, Liuyu Xiang, Chaowen Yang, Xingyang Chang, Pei Pei Li +1

  Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies heavily on human expertise to design the learning pipeline: what an agent observes, how it is rewarded, which algorithm it uses, and how training is configured. Automating these choices is challenging because they are tightly coupled. We introduce FARL (Fully Automated Reinforcement Learning), a framework that automates RL design by jointly searching observation and reward programs, learning algorithms, and training settings. FARL uses training statistics and observed behavior to diagnose failures, propose changes, and test whether they improve learning. Its search preserves diverse candidates and the controls needed for these tests, using a staged budget to screen designs before investing in longer training. Experimental memory records each finding together with its conditions, so an unsuccessful component can be reconsidered in a different combination. Across expert-withheld and expert-available settings, FARL outperforms the evaluated automated baselines on challenging navigation, locomotion, and manipulation…

  PDF

  Summarize this
• arXiv stat.MLOct 11

  Notes on Uniform Policy Score Bounds and Lipschitz Continuity for Truncated Gaussian, Product Cauchy, Boltzmann, and Softmax Policies

  Yanjie Dong

  We establish uniform score bounds and Lipschitz continuity for truncated Gaussian, Cauchy, Boltzmann, and softmax policies under explicitly stated parameterizations.

  PDF

  Summarize this
• arXiv stat.MLOct 11

  When do explicit penalties improve flow matching?

  Lea Kunkel, Alberto González-Sanz, Sophie Langer

  Flow matching can learn structure directly from data, raising the question of when additional constraints improve generation. We study penalties that encode such constraints, with physics-informed flow matching as a motivating example. Satisfying a constraint more closely need not make the generated distribution more accurate. We therefore compare penalised and unpenalised generative modelling through their expected squared $2$-Wasserstein error. Our analysis covers both vector-valued and functional data in a Hilbert-space setting. We first derive geometric criteria that account for constraint violations and the distribution of samples after projection onto the constraint set. We then solve the statistical comparison explicitly for specific velocity-field classes and constraints via flow matching. In this model, penalisation improves accuracy exactly when the reduction in estimation variance outweighs the increase in squared bias. The resulting formula shows how this trade-off depends on sample size, the model class, the noise schedule, and the penalty weight.

  PDF

  Summarize this
• arXiv cs.CLOct 11

  Towards Autopilot Labeling for Short Video Content Governance

  Junwen Chen, Hongwei Wang, Zixuan Wang, Jingbing Wang, Gorden Liu +10

  The explosive growth of short videos has presented significant challenges to content governance. Traditional manual labeling is inefficient, slow to iterate, and costly. Therefore, we explore and develop a multi-stage autopilot labeling framework aimed at progressively increasing the level of automation in short video content annotation. To move beyond the heavy reliance on human expert labeling at the initial L0 stage, we first introduce a discriminative MLLM labeler at the L1 stage, which is fine-tuned with supervised data to directly predict labels for short videos. Advancing to the L2 stage, we shift to a domain-adaptive MLLM pretrained on short video data and use it for zero-shot labeling, enabling flexible generalization without task-specific supervision. In the L3 stage, we propose an agentic annotation workflow, and equip the agent with several key tools, which empower the agent to handle complex, unfamiliar, or vaguely defined cases, significantly reducing the need for human intervention. We conduct extensive experiments across various content issues, and results demonstrate that each stage of the autopilot labeling framework progressively improves labeling accuracy, and…

  PDF

  Summarize this
• arXiv cs.AIOct 11

  Radioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision

  Yuejia Li, JunHeng Li, Hao Wu, Ke He, Mang Ye

  Conventional distillation transfers capability through teacher-generated demonstrations. LLM-as-a-Judge knowledge distillation offers a distinct and increasingly practical alternative. In the label-only variant studied here, the student generates every response and improves from scalar scores alone. Prior work shows that this non-demonstrative feedback can improve student capability, but it creates a fundamentally different provenance problem. No teacher-generated answer enters the student's training set, so any evaluator-specific trace must pass through a low-bandwidth reward signal rather than copied text. Existing watermarks and distillation detectors do not cover this score-only channel. We introduce Radioactive Feedback, which encodes a registered pattern of behavioral preferences in the rewards themselves. The evaluator applies bounded pointwise adjustments to quality-qualified responses, allowing repeated optimization to transfer the pattern to a student trained by another party. Experiments on code and mathematics show that the registered preferences transfer through scores alone and across datasets, enabling black-box detection against a fixed reference pool.

  PDF

  Summarize this
• arXiv cs.CVOct 11

  Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning

  Qingwang Zhang, Jiahao Li, Xiangdong Zhou

  Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goals are expressed through incomplete and unstructured modalities (e.g., hand-drawn sketches and textual descriptions). In this work, we rethink the human intent-to-CAD pipeline and propose a unified method that directly maps multi-level human intents to executable codes, without assuming the prior existence of target CAD models. To support our study, we construct HiCAD, the first large-scale dataset aligning hand-drawn sketches, textual descriptions, and parametric CAD codes. Based on this, we introduce HiCAD, a two-stage framework comprising Cooperative Multi-Task Alignment to bridge the representational gap between heterogeneous inputs, and Spatial-Aware Reinforcement Learning to enforce geometric and topological consistency. Extensive experiments demonstrate that our method significantly outperforms existing baselines across multiple tasks, validating its effectiveness and robustness in transforming heterogeneous human intents into high-fidelity parametric CAD models. Our project page: https://zqwlearning.github.io/HiCAD.

  PDF

  Summarize this

• Anomaly detectors21+50.0%
• Deepfake detection41−16.3%
• Optimal power flow9−18.2%
• Electrocardiogram ecg31−26.2%
• AI tutors8−27.3%
• Causal discovery14−30.0%
• Multimodal emotion7−30.0%
• Multimodal493−31.2%