TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

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

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksFor AI agentsAPI
Fields · this week
All fields1983Multimodal333Frontier LLMs256Recursive self improvement213Inference & serving163Agents & indirect prompt injection159Neural operators137Robotics135Clinical reasoning124Forecasting time94Linear bandits69Voice AI59AI safety36Molecular property prediction33Character recognition OCR33Federated learning27All 23 fields

Rising research topics

  • Diffusion priors20−4.8%
  • Voice AI59−14.5%
  • Character recognition OCR33−17.5%
  • Spiking neural networks6−25.0%
  • Quantum machine learning23−25.8%
  • Channel state information14−30.0%
  • Forecasting time94−35.6%
  • Algorithmic fairness7−36.4%

Open problems across fields

Open problems for this view are being prepared; they appear within a day.

Papers

  • arXiv cs.CVSep 29

    How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective

    Janet Wang, Yunbei Zhang, Xiao Wang, Jihun Hamm

    Medical Vision-Language Models (VLMs) show significant promise for clinical image understanding, offering accurate diagnosis with interpretable reasoning. However, a critical performance gap exists between their strong vision encoders and the full multimodal model: in dermatology, the MedSigLIP encoder outperforms MedGemma by an average of 10.26 percentage points even when both use zero target-task labels; few-shot linear probing provides further evidence of strong visual representations. This gap motivates an investigation of how visual information is used in end-to-end diagnosis and why plausible-sounding predictions can lack grounding in image evidence. Using dermatology as our primary testbed, we systematically investigate three hypotheses for this phenomenon. We further provide a mechanistic analysis of the model's internal attention patterns, showing that a simple describe-then-decide prompting strategy increases vision attention by 30-40% during generation. Task-specific fine-tuning improves dermatology classification but reduces cross-domain medical question-answering performance in our evaluation. To address these challenges, we combine label-free prompting with…

    PDF
  • arXiv cs.AISep 29

    MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems

    Lei Ma, Dennis Hofmann, Haowen Xu, Joshua DeOliveira, Peter VanNostrand +2

    Recent studies report that LLM-based multi-agent systems (MAS) fail at rates of 41%-87%, yet to our knowledge, no benchmark to date supports systematic anomaly detection (AD) for them. Building MAS AD benchmarks is hard because they must remain fresh as LLM systems evolve: tasks may leak into training data and thus be memorized by LLMs, traces and anomaly patterns expire as backbones evolve, and labels must be provided reliably for each refresh. To address these challenges, we present MAADBench (MA: multi-agent; AD: anomaly detection), the first refreshable MAS AD benchmark designed for diverse, evolving LLM backbones underlying the agents. MAADBench combines (1) sampled-and-coupled generative tasks over an approximately 10^37-task space to mitigate task leakage, (2) refreshable trace generation under configurable LLM backbones, and (3) automated provision of cost-free, deterministic step-level labels for fine-grained AD evaluation. Beyond offering the paradigm itself, we run MAADBench with five state-of-the-art LLM backbones and release the MAADBench-Full dataset with 5,200 step-labeled traces. Benchmarking 25 AD methods on the MAADBench dataset reveals substantial limitations…

    PDF
  • arXiv cs.LGSep 29

    SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning

    Zihao Chen, Fanxiang Xiong, Hongran Ren, Xuefeng Bai, Zhongxiang Dai +4

    Maximum Likelihood Reinforcement Learning (MaxRL) targets prompt-wise log-success and has shown strong performance on reasoning tasks. Under finite rollout budgets, however, the estimator used by MaxRL attenuates each prompt's likelihood gradient by a factor that depends on its success probability and rollout count. Under uniform rollout allocation, the common rollout count fails to compensate for success-dependent attenuation, leaving low-success prompts more strongly attenuated and distorting their relative contributions to the expected aggregate gradient. We introduce SERA (Scale-Equalized Rollout Allocation), which redistributes a fixed rollout budget to approximately equalize these finite-rollout scaling factors. Building on our theoretical analysis of how finite rollouts distort prompt-wise likelihood gradients, we formulate the allocation as a fixed-budget max--min problem, derive a waterline solution to its continuous relaxation, and introduce a multiplicity correction to remove the additional prompt weighting induced by heterogeneous rollout counts. Experiments show stronger alignment with exact likelihood gradients in a controlled ImageNet setting and improved…

    PDF
  • arXiv cs.CLSep 29

    Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment

    Josepha Michiko Leo, Hyun-seok Min, Yehoon Jang, Irvan Zidny, Jin-Woo Chung +1

    Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely tested where "correct" has a definable meaning. Patent claim amendment supplies that signal: the examiner names the attacked limitation and cites prior art, providing per-case ground truth. We release three artifacts: (i) a corpus of 7,385 USPTO prosecution cases with XML-aligned pre/post claims, rejection, and cited prior art; (ii) a seven-probe battery comparing random and structural-match retrieval as two policies under a fixed prompt scaffold; (iii) a deterministic five-channel metric (C1-C3 and C5 in main, C4 supplementary) requiring no LLM evaluation. Across 9,600 pre-registered calls on four frontier LLMs (Claude Sonnet 4, Claude Haiku 4.5, GPT-5.4, GPT-4o-mini), no tested model exhibits detectable classical prior-injection behavior; retrieval effects are small and direction-inconsistent between random and structural retrieval, and the null is unchanged under a dense (semantic) retriever, across retrieval depths k in {1,3,5,10}, and under a paraphrase-sensitive grounding metric. Revision locality reveals a model-specific…

    PDF
  • arXiv cs.LGSep 29

    Interactive-Policy Distillation with Bidirectional Propose-and-Verify

    Shutong Wu, Xiwen Chen, Brendan Rappazzo, Daiheng Zhang, Anderson Schneider +2

    On-policy distillation (OPD) trains a student model on its self-generated trajectories with dense token-level teacher feedback. However, naive OPD may suffer from teacher unanchoring, where the student's reasoning trajectory drifts far from the teacher, causing the teacher to be queried on states it would hardly visit and thus provide unreliable supervision. We propose Interactive-Policy Distillation (IPD), which applies adaptive teacher intervention to the student rollout. Under a bidirectional propose-and-verify state machine, the student and teacher alternately exchange their roles as proposer and verifier, and collaboratively generate mixed-source trajectories. Then different supervisions are applied according to the source of each token. This bidirectional propose-and-verify mechanism and the source-split loss make IPD not only a more performant distillation method, but also a unified bridge between on-policy and off-policy paradigms. To make the interleaved dual-model rollouts more efficient, we also design a dedicated fused inference engine that co-hosts both models in one serving instance with separate KV caches and instantiates the state machine model to distribute,…

    PDF
  • arXiv cs.CVSep 29

    SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence

    Gyeonggwan Lee, Eunsoo Im, Seunghwan Hong, Junghun Suh

    Dense feature matching between 360$^\circ$ panoramas underpins omnidirectional pose estimation, 3D reconstruction, and SLAM. Such panoramas are stored in the equirectangular projection (ERP), which unrolls the viewing sphere onto a flat chart and thereby introduces three distinct distortions -- a longitudinal seam (topology), latitude-dependent stretch (metric), and non-uniform pixel area (area) -- that the coarse stage of perspective-trained dense matchers does not model, so these matchers degrade systematically on ERP. We show that correcting the three distortions at the coarse-stage interfaces where they arise -- pairwise distortions in attention, per-pixel distortion in covisibility gating -- improves PCK@1$^\circ$ from 0.230 to 0.275 on Matterport3D under a fixed coarse scaffold, with the refiner architecture unchanged -- our central result. Concretely, SCCM (Spherically Consistent Coarse Matching) augments a chart-naive cross-attention/dual-softmax coarse matcher with two sphere-derived priors: Spherical Positional Attention (SPA) pairs a yaw-periodic RoPE (topology) with a tangent-plane bias (metric), and Area-Aware Covisibility (AAC) applies a pre-sigmoid log-area…

    PDF
  • arXiv cs.CLSep 29

    DraftTrace: A Multi-View Analytics Environment for AI-Integrated Writing

    Divyansh Chandarana, Sandipan De, Vivek Gupta

    Generative AI has changed how students produce writing assignments. The final artifact is no longer sufficient to understand the process through which it was produced. We introduce DraftTrace, a writing environment that jointly captures three complementary views of writing: the final product, the writing process and interactions with an integrated AI-assistant. DraftTrace reconstructs how a document develops over time and organizes these signals into submission, longitudinal, and class-level analytics for instructors. We deployed DraftTrace in a graduate NLP course with 81 students and compared their sessions with LLM-generated responses entered by automated tools and with copy-typed responses. While product measures distinguish differences in text formulation, process measures distinguish differences in how text is entered. Considering both views together helps characterize cases such as copy-typing. Interaction traces show that students use the assistant differently across stages of writing: to clarify the question at an early stage and to verify answers at a later stage. A preliminary instructor survey highlights the importance of multi-view writing analytics and their…

    PDF
  • arXiv cs.ROSep 29

    Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment

    Moritz Zoellner, Reece O'Mahoney, Ioannis Havoutis, Rohan Paleja

    Generalist robot policies such as vision-language-action models (VLAs) have achieved remarkable generalization, but their inference delays can conflict with the demands of real-time control. Asynchronous execution avoids pauses between action chunks by predicting the next sequence of actions while the robot carries out the previous one. In this paper, we study whether asynchronous execution produces the same action distribution as the original VLA. We find that, for non-Markovian demonstrations, asynchronous execution can produce a fundamentally different action distribution, which can limit the policy's reactivity. In our method, we seek to restore this reactivity by aligning the asynchronously produced action distribution with that of the original VLA through two complementary mechanisms. First, Recursive Flow-Field Distillation trains the asynchronous policy using the VLA's action-generation flow. We characterize the learned distribution theoretically and show experimentally that our asynchronous policy can generate nearly the full range of actions the original VLA would produce, while existing asynchronous methods recover only a fraction of that range. Second, Propose-Resolve…

    PDF
  • arXiv cs.CLSep 29

    When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain

    Chenxu Wang, Chaozhuo Li, Xinze Shi, Songyang Liu, Kyrie You Wu +4

    Self-evolution lets large language models (LLMs) improve iteratively using their own generated data, but often suffers from self-evolution degeneration: performance improves, plateaus, then declines. Existing methods address this issue at the component level, targeting either the Questioner or the Solver, and overlook that self-evolution is a tightly coupled system. We propose a holistic framework based on learnable information gain, which measures how much novel, parameterizable information a round provides relative to the previous round. Theoretically, this gain equals the Kullback-Leibler divergence between the two rounds' data distributions plus their entropy change. Practically, it is estimated by fitting a small language model to the previous round and scoring new data via negative log-likelihood. Based on this diagnostic, we propose ATRI (Adaptive Training Regulation via Information-gain), which reweights samples within a round and halts training across rounds when information gain remains low. Experiments on popular datasets demonstrate the superiority of our proposal.

    PDF
  • arXiv cs.CLSep 29

    Retrieval Sensitivity to Identity Signals in Queries

    Andrew Tang, Nicholas Deas, Kathleen McKeown, Vishal Misra

    Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries. We ask whether the identity signals that real users express in their queries---political ideology and dialect---bias what a retriever returns. We design evaluations in two domains, political news and consumer-health questions, each pairing a controlled synthetic set that varies only the identity signal with naturalistic queries. Across five dense retrievers and a sparse baseline, every retriever (i) retrieves articles that align with the query's own political lean and (ii) performs worse for questions written in African American Language (AAL) than in White Mainstream English (WME). Two analyses tie these gaps to queries' identity signals beyond surface vocabulary: partialling out an aggregate lexical-asymmetry score leaves the synthetic gaps largely intact, and linear probes recover lean and dialect from the retrievers' query embeddings beyond token-level features. Left unaddressed, such retrieval biases risk contributing to polarization and reinforcing the health disparities already faced by AAL speakers. Code is available at…

    PDF
  • arXiv stat.MLSep 29

    Hierarchical Utility Calibration for Structured Multiclass Decisions

    Futoshi Futami, Jerry Huang, Ichiro Takeuchi

    In multiclass probabilistic prediction, Utility Calibration (UC), which focuses auditing on specified utilities, has recently received attention as a way to guarantee downstream decisions while controlling computational and sample requirements. At the same time, some multiclass problems have meaningful label hierarchies that play important roles in medicine and image classification, yet how UC evaluates utility within a hierarchy remains insufficiently understood. We show that the difference between realized utility and predicted mean utility admits an exact decomposition into a sum of contributions from the internal nodes of the label tree. This decomposition shows that positive and negative contributions from different nodes can cancel, and that even when UC is small, the utility errors remaining in parts of the hierarchy need not be small. To address this problem, we propose Hierarchical Utility Calibration (HUC), which evaluates each node contribution before summation while retaining the same target utility, subgroup, and predicted-utility interval. We further provide finite-sample evaluation over all predicted-utility intervals and propose HUC-Boost, which updates only…

    PDF
  • arXiv cs.CVSep 29

    Foresight at the Event Boundary: Evaluating Physical Prediction in Video World Models

    Estela Monserrat Arriaga Santana, Julian Rosas Scull, Ehécatl Sacamch'en Núñez Rico, Hugo Jair Escalante

    Video world models are largely regarded as predictive models of the physical world and are therefore expected to anticipate the consequences of observed events. However, evaluation has mainly focused on reference similarity, physical-law consistency, or judgment plausibility, estimating anticipation only indirectly. We address this directly: when a release or impact has just occurred but its consequence is withheld, can a world model anticipate what should happen next? We introduce an event-anchored evaluation based on 62 controlled real-world free-fall recordings and 124 clips spanning three object types, with fine-grained release and impact annotations and ground-truth trajectories. The protocol separates consequence production, temporal placement, and physical realization. Across six contemporary video generation and world models, Runway and Veo produce release and subsequent impact events at rates above 93% but often initiate them substantially late, whereas Cosmos-Predict-2.5 and MAGI-1 frequently preserve the pre-event state and produce little or no measurable consequence. Among measurable falls, plausible timing does not necessarily imply physically consistent motion. We…

    PDF
  • arXiv cs.LGFrontier LLMsSep 29▲ 39

    Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling

    Oliver Sieberling, Bharat Runwal, David Jin, Ryan Chin, Rameswar Panda +1

    Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference. The memory state size is a crucial factor in their performance, as exemplified by the strong performance and resurgence of linear attention, which extends the vector-valued hidden states of ordinary RNNs to matrix-valued hidden states. Crucially, linear attention does so in a parameter-efficient way, in particular by using an outer product of the key and value vectors to write to the matrix-valued hidden state. We generalize this construction and propose triadic linear attention, which writes the triadic outer product of a key, a second key, and a value, into a third-order (i.e., 3D) tensor state, and reads from it by contracting both key axes with two queries. An $E$-dimensional second key thus yields an $E$-fold increase in state size while adding only two projections. Triadic linear attention is compatible with data-dependent forgetting, the delta rule, and chunkwise-parallel training. Applied to Gated DeltaNet and scalar-gated linear attention, triadic linear attention substantially improves long-context language modeling and recall,…

    AIInference & serving70
  • arXiv cs.LGSep 29

    SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference

    Ruichen Xu, Siyao Wang, Fang Wan, Jiacheng Qiu, Wenhan Gao +6

    Recovering complete physical fields from sparse observations is challenging because the measurements may not uniquely determine the underlying state. Diffusion-based PDE solvers address this problem through iterative sampling whereas neural operators provide deterministic one-pass predictions. We propose SCOPE (Sparse-Context Observability-aware Predictive Embeddings) to recover complete PDE fields from sparse observations by coupling full-field latent prediction with physical reconstruction. A shared decoder reconstructs fields from both predicted and complete-view representations so that representation learning is guided by both physical recovery and latent matching. We derive a quadratic risk decomposition at fixed teacher-decoder pairs showing why optimal latent prediction need not yield optimal field reconstruction. We also establish sufficient conditions for decoder improvements on complete inputs to transfer to recovery from partial observations. Experiments across five PDE settings show that SCOPE outperforms mask-aware neural operators on all ten forward and inverse tasks and achieves lower errors than those reported for diffusion-based solvers including DiffusionPDE and…

    PDF
  • arXiv cs.LGSep 29

    Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations

    Guanghui Min, Liang Wu, Mingjia Shi, Yinhan He, Mayank Darbari +2

    Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing prompt-adaptation methods infer compression errors by comparing full-context and compressed trajectories. Such comparisons cannot isolate individual compressions and are confounded by agent stochasticity. We first find that compression degrades reliability before solvability. Using matched counterfactual continuations that compare execution from the same agent state with versus without compression, we further show that severe degradation concentrates at isolated compression events. Motivated by this finding, we propose PAIR (Prompt Adaptation using Interventional Rollouts) for adapting structured compression prompts. PAIR identifies individual compressions that degrade subsequent execution, diagnoses their effects, and revises the relevant sections of a fixed compression template. PAIR achieves the strongest cross-run reliability among compressed methods in every main benchmark-scope combination, consistently exceeding the competing prompt-adaptation baseline. Without modifying the downstream agent, PAIR…

    PDF
  • arXiv eess.IVSep 29

    Reliability Testing of Medical Model Performance under Distributed Deployment

    Yifei Wang, Xiaohan Zhang, Youtao Ding, Tianlin Li, Xiaoyu Zhang +2

    Distributed inference has become an indispensable part of deploying medical models under practical latency, memory, and throughput constraints. Although modern frameworks improve serving efficiency through tensor parallelism, mixed precision, kernel fusion, and multi-device communication, they are generally assumed to preserve the behavior observed during centralized HuggingFace evaluation. This assumption creates an evaluation-deployment mismatch: a model may pass offline evaluation but produce a different output after the execution stack changes. To address this mismatch, we propose a testing framework and an improved, distributed-execution-sensitive medical-model benchmark that evaluates the same checkpoint and input under a centralized HuggingFace reference and matched distributed deployments. Extensive experiments across language, vision, and multimodal medical models show that execution changes can produce measurable output disagreements. Across supported visual settings, the test success rate ranges from 0.21 to 0.43 for single-modality models and from 0.32 to 0.98 for multimodal models. The benchmark is aimed at extending medical-model evaluation from capability and…

    PDF
  • arXiv cs.LGSep 29

    PDE-OBS: Controlled Evaluation Across Observation Patterns

    Ruichen Xu, Siyao Wang, Fang Wan, Jiacheng Qiu, Wenhan Gao +5

    Physical-field reconstruction and forecasting depend on both measurement density and spatial layout, yet evaluation under a single observation pattern does not characterize performance when that pattern changes. We introduce PDE-OBS, an integrated benchmarking platform spanning numerical data generation, model training, and inference and evaluation under varying observation conditions. It combines 560,000 fields and trajectories from seven partial differential equation families with configurable observation operators and seven adapted baseline methods for stationary reconstruction and short-horizon forecasting. Separating observation construction from physical records allows users to specify parameterized patterns and deterministic mixtures for training and testing while preserving prediction targets and data splits. The evaluation protocol uses references trained for each test pattern to compare models on identical test observations and targets, alongside equal-count groups for spatial-layout comparisons. On a 14,000-record subset, we evaluate 441 trained models under nine test patterns, yielding 3,969 evaluations. Mean cross-pattern error exceeds mean matched-pattern error in…

    PDF
  • arXiv cs.ROSep 29

    Distilling Privileged Control Barrier Functions into RGB-Only Safety Filters for Dynamic Visual Navigation

    Seungyeon Yoo, Gawon Lee, Seungwoo Jung, Inkyu Jang, H. Jin Kim

    RGB-only end-to-end visual navigation policies remain vulnerable to collisions in real-world dynamic environments, motivating a dedicated safety layer. Existing visual Control Barrier Function (CBF) approaches seek to provide safety from RGB observations, but often rely on real-time rendering or explicit scene reconstruction and are primarily designed for static scenes, limiting their practicality for onboard deployment. We propose a teacher-student visual distillation framework that transfers the safety behavior of a privileged CBF teacher to an RGB-only student filter for dynamic environments. The student maps a short RGB history, robot velocity, and a nominal control action directly to a safe action, while the teacher uses ground-truth robot and obstacle states in a real-to-sim dynamic Gaussian Splatting environment. To reduce the teacher-student information gap, the teacher constructs safety constraints only from obstacles observable within the student's RGB history. It also accounts for obstacle-velocity uncertainty to improve robustness to motion variations, while action augmentation exposes the student to diverse safe and unsafe nominal actions to better capture the safety…

    PDF
  • arXiv cs.ROSep 29

    LIBERO-MAX: Do Robot Policies Adapt When the World Changes?

    Yunbei Zhang, Zijian Jin, Yuanzhe Liu, Janet Wang, Xilun Zhang +12

    Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previous scene. Many simulation robustness benchmarks fix external conditions at reset, leaving this temporal challenge underexamined. We introduce LIBERO-MAX, a benchmark of 8,000 paired cases spanning eight types of changes to geometry, observations, appearance, clutter, and paths. Each pair compares task execution with and without a mid-task event, holding the task, initial state, policy seed, and pre-event action sequence fixed. This controlled comparison distinguishes event-associated regressions from failures already present without the change. Across fourteen current VLA, hybrid, and world-action policies, events reduce success by 11.0-25.7 percentage points. Event profiles reveal shared vulnerabilities to geometry and observation changes, while policy-family rankings interleave. Camera controls show that robustness reflects both competence under the changed conditions and the trajectory from which they are encountered; varying query cadence does not eliminate the gap. Together, the paired protocol…

    Code
  • arXiv cs.CLSep 29

    Large-scale factor analysis shows machine intelligence is only partially interpretable

    Faiz Ghifari Haznitrama, Afrizal Hasbi Azizy, Faeyza Rishad Ardi

    A common assumption in language model development is that cognitive abilities are organized around a general, domain-free intelligence factor, like fluid intelligence in humans. This assumption is rarely tested directly, and prior attempts have done so only at a much smaller scale. We take a latent variable approach to intelligence in language models, similar to how psychometricians study psychological constructs. Performance in every specific problem set is influenced by a domain-specific and a domain-agnostic latent factor. Using factor analysis as a dimension-reduction technique, we analyzed 13,251 published evaluation scores covering 1,618 language models across 456 different text-only benchmarks. Due to the super-sparse nature of the dataset, we triangulate our analysis across different data densifiers and imputation methods. A robust pattern across different modes of bias is that 1. A general intelligence factor accounts for 70.8% of variance in model performance at our most generous estimate, and far less than that in most of our solutions, 2. Content-similar benchmarks do not necessarily cluster together, and 3. The $g$ factor is not dominated by any common theme, and…

    PDF
Load more
Code
PDF
PDF