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
NewsResearchStacksAPI
Fields · this week
All fields3393Multimodal539Agents509Frontier LLMs435Inference & serving263Image segmentation178Learning verifiable rewards1593D scene158Graph learning153Voice AI98Evals94Classifier & causal discovery86Forecasting time78Flow matching72Training & fine-tuning56Teacher policy distillation51All 32 fields

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in embodied control loops1 paper raises it · 0 address it

    High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

    Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

    Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

    • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

Coming with more sources: more tagged papers
  • Small LLMs11+1000.0%
  • AI safety42+740.0%
  • Training & fine-tuning56+600.0%
  • Robotics28+600.0%
  • Image & video generation34+580.0%
  • Evals93+520.0%
  • Computer vision43+437.5%
  • Code models20+400.0%

Papers

  • arXiv cs.CLOct 17

    Compositional Activation Steering Across Languages and Behaviors with Contextual Gates

    Daniil Gurgurov, Akansh Maurya, Josef van Genabith, Simon Ostermann, Hitomi Yanaka

    Activation steering has emerged as an effective and precise way to influence the behaviours of language models. However, composing multiple steering directions to control several behaviours simultaneously remains challenging, particularly in multilingual settings and with training-free steering vectors. We address this challenge with contextual steering, jointly training gates that adapt the strength of fixed steering directions to the current hidden state and interactions between interventions. Across a broad range of languages, behavioural attributes, and models, our approach outperforms constant-strength steering and four strong baselines, including prompting. It also better preserves general knowledge and keeps the model's internal computation closer to that of the prompted model. Our analysis further shows how jointly trained gates adapt their contributions during composition, explaining the mechanisms underlying effective compositional steering.

    PDF
  • arXiv cs.HCOct 17

    Leveraging Mental Models for Human-Centered Explanations: A Systematic Design Approach Illustrated by Explainable Fake Review Identification

    Sidra Naveed, Md Shajalal, Gunnar Stevens, Alexander Boden

    Explainable AI (XAI) often prioritizes model fidelity over user intelligibility, yielding explanations that satisfy technical transparency yet fail to support human sense-making. We propose a human-centered approach, MIND-X (Mental-model INtegrated Design for eXplainability), which aligns explanations with users' mental models, commonsense concepts, and judgment heuristics. Using fake review detection as a case study, we contribute: (1) a qualitative study (n=10) that elicits how people assess review credibility and produces an actionable, design-guiding taxonomy of perceptual cues; (2) a set of design principles that link those cues to explanation strategies and prompt LLMs to generate adaptive, language-based explanations; and (3) a quantitative evaluation (n=166) showing that these explanations offer distinct advantages over token-level transparency methods widely used in explainable text classification in terms of understandability, satisfaction, perceived trust, persuasiveness, and decision-making support. Rather than claiming general superiority, our evaluation illustrates how grounding explanations in users' everyday reasoning practices can produce more intelligible and…

    PDF
  • arXiv cs.SEOct 17

    RXSynth: A Seed-Grounded Corpus for Studying Java Runtime-Exception Bugs

    Parnian Eslamloo, Banani Roy

    Existing Java bug benchmarks offer limited method-level data for studying runtime-exception detection. Filtering Defects4J, Bugs.jar, Bears, and BugSwarm yields only 170 real buggy/fixed method pairs across seven unchecked exception types. We introduce RXSynth, a corpus of 4,275 synthetic Java method pairs generated from real bug/fix exemplars. We select the generator using structural alignment with real seeds and validate pairs using a two-stage patch-anchored procedure that identifies the labelled exception risk and checks whether the repair removes it. Independent JVM execution confirms patch-local validity for 84.2% of a stratified sample of 500 pairs. Provenance records enable evaluation without overlap between generation exemplars and test bugs. Structural analyses show good alignment within the represented size range, but compression of larger methods. We use RXSynth to compare isolated-method detection with pair discrimination when the repair is visible. Under provenance-controlled evaluation, supervised isolated-method ROC-AUC is about 0.55-0.64. Stronger zero-shot models reach about 69% accuracy but identify only 41.2% of repaired methods correctly. In contrast,…

    PDF
  • arXiv cs.AIOct 17▲ 5

    HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents

    Soyoung Yoon, Peiran Xu, Han Wang, Ruofan Wu, Xiaodong Yu +6

    While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables or unstructured data, real-world analytical questions frequently span heterogeneous sources. For example, answering one enterprise question may require both a result computed over an internal database and evidence found on the web. Recent evaluations on benchmarks like HybridDeepResearch show that even frontier agents struggle when evidence must cross this boundary. While these benchmarks have exposed the limitation, methodologies to explicitly teach cross-source reasoning remain absent. To address this, we introduce HybridResearcher, a 4B agent trained to bridge evidence across the structured and unstructured boundary. To build it, we synthesize cross-source bridge trajectories by starting with validated single-source tasks-such as existing text-to-SQL or web search queries-and fabricating the missing source around a bridge entity drawn from the seed's own output. We retain a sample only when strict construction gates confirm that neither side alone suffices, ensuring the data requires true cross-source interdependence. Finally, we train on…

    PDF
  • arXiv cs.CVOct 17

    Predicting Individual Differences in Lipreading From Eye-Tracking and Pupillometry During Silent Visual Speech

    Puneet Kumar, Satyarth Malik, Gao Zheng, Guoying Zhao, Xiaobai Li

    Lipreading ability varies widely, including among people who are hard of hearing. Although mouth-directed attention is linked to speechreading outcomes, it remains unclear how much lipreading skill can be inferred from viewing behavior and which signals carry this information. We examine whether individual differences in lipreading ability are reflected in viewing behavior during silent speech and quantify the contributions of gaze dynamics, pupil-linked signals, and spatial viewing allocation. We introduce the Lipreading Perception Study (LiPS) dataset and a tracker-independent preprocessing pipeline that synchronizes SR Research EyeLink gaze and pupil recordings with the stimuli. Twenty-four adults (age 32 $\pm$ 10 years) completed a four-alternative forced-choice silent lipreading task. An extreme-groups protocol yielded 18 participants labeled as stronger or weaker lipreaders. Each participant-trial included four aligned views: lip-region images, frame-level gaze, pupil summaries, and spatial viewing proportions. A four-branch neural network with cross-modal attention predicted labels using participant-disjoint splits and systematic ablations. The full model reached accuracy…

    PDF
  • arXiv cs.LGOct 17

    Distribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models

    Romeo Passaro, Jeongjae Lee, Jong Chul Ye, Michael M. Bronstein, Yoshua Bengio +2

    Reward fine-tuning is an effective way to adapt pretrained diffusion and flow-matching models to downstream objectives, but aggressive optimization often leads to mode collapse and distributional drift. Existing methods attempt to control this drift with reverse-KL regularization, implemented as an $\ell_2$ penalty on the velocity field; however, this functions by indirectly constraining sampling dynamics rather than directly acting on the generated distribution. To address this, we propose DFR (Distributional Functional Rewards), which augments the task reward with a distribution-dependent, per-sample reward that acts explicitly on the generated distribution. Formally, we generalize the KL-regularized objective from expected rewards, which are linear in the model's distribution, to convex functionals of it. The first variation of this objective defines an effective, distribution-dependent reward that directly penalizes deviation from the pretrained distribution. This formulation yields additive per-sample rewards for the Fréchet distance (FD), maximum mean discrepancy (MMD), and DreamSim diversity, recovering several recently proposed rewards as special cases. Across various…

    PDF
  • arXiv cs.CROct 17

    Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security

    Khushbu Pahwa, Yubin Ge, Daniele Bonadiman, Xiaofei Ma, Yi Zhang

    LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacker and defender instead, and let execution decide every reward: an attacker (Red) edits a real repository and earns nothing unless its patch applies, builds, passes the tests, completes its development task and reproduces a real exploit in an isolated container, whose path also labels the entry point, the critical operation and the trace between them. Peer-Relative Policy Optimization (PRPO) makes both sides populations of LoRA adapters over one frozen base and credits each against same-role peers that faced an identical condition, placing the population inside the policy-gradient baseline rather than the opponent pool, with a tournament preserving diversity. Matching cancels the condition's difficulty: at equal coverage it is worth 2.3 points of balanced accuracy over a baseline computed on other conditions, and it matches a within-policy control at half the verifier spend. PRPO's 7B diff reviewer reaches 64.8% balanced accuracy on four unseen applications in three untrained languages, 5.5 points above supervised…

    PDF
  • arXiv cs.CLOct 17

    LastWords: Boring Problems Revisited

    Huayang Li, Richard Sproat

    In 2022, the second author published a Last Words piece in Computational Linguistics in which he pointed out that, despite the advances in AI up to that point, there were still some problems in natural language processing that on the one hand seemed trivial and perhaps boring, but on the other were hard to solve using purely neural methods. One such problem discussed in that context was text normalization, and a particular subproblem of that, namely number name reading. The piece came out just a few months before the first release of ChatGPT, and needless to say, a lot has happened since then. Indeed, as we document here, the problem (of number name reading) has practically been solved, at least by one of the latest frontier models. However, we believe that there are still open issues for such limited domain, constrained and limited resource problems, and that in some future machine learning approach, the massive resources of the latest frontier models would not be needed to solve them.

    PDF
  • arXiv cs.CVOct 17

    Multi-Speed Field Evaluation of a Semi-Autonomous Precision Sprayer for Weed Control in Vegetable Crops

    Md Khairul Islam, Boyang Deng, Yuzhen Lu, Daniel Brainard, Ajit Srivastava

    Machine vision-guided precision spraying is promising for sustainable vegetable production by enabling site-specific weed targeting, reducing herbicide application while protecting crop yield and quality. However, the effects of operating speed of sprayer systems on the integrated detection-tracking-actuation pipeline remain insufficiently characterized under field conditions. This study evaluated a semi-autonomous, tractor-based spraying system for targeted weed control in radish and quantified performance across three operating speeds. A five-season dataset comprising 10,599 images and 84,311 annotated instances across seven classes was curated for model development. A YOLOv11-medium model was integrated with ByteTrack tracking and a customized 12-nozzle sprayer on a semi-autonomous electric tractor. Field trials were conducted at 0.13, 0.27, and 0.45 m/s (i.e., 0.3, 0.6, and 1.0 mph) to characterize speed-dependent changes in weed detection, targeting, actuation, and crop damage. At the lowest speed of 0.13 m/s, the system achieved 94.6% mAP@50 and 93.2% recall for weed and crop detection. However, increasing platform speed substantially reduced system performance, with weed…

    PDF
  • arXiv stat.MLOct 17

    Scalable and Adaptive Distribution Regression via Random Features

    Yinsong Wang, Xiao Liu, Yu Ding

    Distribution regression seeks to learn mappings from probability distributions to response variables and has emerged as a unifying framework for kernel methods, multi-instance learning, and set-valued learning. Despite its success, kernel-based distribution regression remains computationally expensive and sensitive to kernel choice, motivating scalable and adaptive representations. Building on random feature approximations, we develop a finite-sample analysis of Random Feature Distribution Regression (RaDR) under two-stage sampling. Our perturbation analysis separates the effects of distribution-level sampling, finite within-bag sampling, and random feature approximation. We establish sufficient feature-budget conditions under which RaDR preserves the order of our excess-risk upper bound for exact two-stage kernel distribution regression while maintaining computational efficiency. We further propose Adaptive Random Feature Distribution Regression (A-RaDR), a unified score-guided framework that adaptively allocates random features according to downstream learning objectives. Experiments on synthetic benchmarks and 41 real-world datasets demonstrate that RaDR delivers substantial…

    PDF
  • arXiv cs.ITOct 17

    Query-Dependent Reading for Quantized Inner-Product Estimation: A Minimax Separation

    Krishnakumar Balasubramanian, Siddharth Bhandari, Shiva Prasad Kasiviswanathan

    We study quantization for inner-product estimation when storage and reading have separate budgets. In the static bit-probe model [Yao, 1981], an encoder stores $w$ bits about $x$ before seeing a query $y$, and a reader probes at most $r<w$ bits to estimate $x^\top y$. Both vectors lie in the $d$-dimensional Euclidean unit ball. Protocols may be randomized, and computation is unrestricted. Performance is measured by $d$ times the worst-case mean-squared error over $x,y$, averaged over protocol randomness. First, we show that query-independent reading cannot benefit from extra storage. Any such reader is equivalent to fully reading an $r$-bit message, even when later reads depend on previously returned bits. At fixed positive rates $W=w/d$ and $R=r/d$, the normalized minimax error converges to $1/(4^R-1)$, independent of $W$. The upper bound was already known [Ordentlich and Polyanskiy, 2025]. We prove the matching lower bound for arbitrary scalar decoders, extending the result for unbiased compressors [Safaryan et al., 2020]. Then, we show that query-dependent reading makes extra storage useful. We construct a two-batch protocol using Gaussian projections and random thresholds,…

    PDF
  • arXiv cs.CLOct 17

    Measuring Data Diversity with Embeddings: A Taxonomy and Benchmark for Diversity Measures

    Cantao Su, Anna Wegmann, Esther Ploeger, Dong Nguyen

    Diversity is a critical property of text corpora, with direct implications for training data curation, test set design, and model generalization. However, its measurement remains fragmented and poorly understood. Existing embedding-based diversity measures vary widely in how they are computed and can yield substantially different diversity scores on the same data, yet no systematic comparison of their empirical behaviour exists. We make two contributions toward addressing this gap. First, we present a taxonomy of 21 embedding-based diversity measures, organizing them into four families based on their underlying computations. Second, we introduce EmbDivBench, a benchmark that evaluates these measures along three conceptually distinct components (variety, balance and disparity) on both simulated and natural text data. Although Mean Pairwise Distance is the most commonly used measure, our experiments show that it is outperformed by several alternatives on the three diversity components, with Graph Entropy being the best choice overall. Lastly, we distil these findings into practical recommendations for diversity measure selection.

    PDF
  • arXiv cs.CLOct 17

    Do We Need the Largest LLMs for Every Clinical Decision?

    Ali H. Lazem, William Teahan

    Large clinical language models often require multi-GPU infrastructure, limiting local deployment. We introduce CERTA, a decision-level statistical certificate that determines when a quantized model may substitute for its native BF16 reference and escalates decisions that cannot be certified to it. Across eleven instruction-tuned models, both general-purpose and domain-adapted, from three families (7-72B), we evaluated 2,500 clinical-verification decisions from de-identified patient contexts (2,484 patients), with patient-disjoint calibration and testing. In the higher-power operational analysis, round-to-nearest 8-bit quantization at BF16 storage served 99.8-100% of held-out decisions across all eleven models; formal finite-sample guarantees were assessed separately using the exact split-sample procedure. In the same operational analysis, the class-conditional 4-bit frontier reduced the amortized, BF16-equivalent deployment cost to 25.8% and 27.3% of the BF16 reference for Qwen2.5-72B and HuatuoGPT-o1-72B, respectively, with measured peak memory of 43.0 and 42.7 GB, below the nominal capacity of a single 48 GB accelerator. Deployment on that specific hardware was not directly…

    PDF
  • arXiv cs.CVOct 17

    Goal Images Are Control Targets: Spatially-Grounded Goal-Image Synthesis for Robotic Manipulation

    Riddhi Chatterjee, Ritish Shrirao, Kushagra Mehrotra, Viswanath Gopalakrishnan

    Goal-conditioned manipulation policies are steered by a goal image, a picture of the desired post-manipulation scene synthesized from the current observation and a language instruction. The prevailing assumption is that better image-editing quality yields better goals, so goal generators are built and compared using general image-editing metrics. We show this assumption is false. Across two independent goal-conditioned policies on CALVIN, the image editors that top aggregate editing-quality leaderboards (Gemini 3 Pro Image and GPT Image 1.5) produce worse control targets than our proposed far smaller finetuned open models, and the gap widens sharply for the multi-step (long-horizon) tasks robots actually face. A per-dimension analysis explains why. Downstream policy success is governed almost entirely by manipulation adherence (selecting the right object and the right final state; Spearman $ρ\approx 0.9$ with success), while photorealism and aesthetic fidelity, precisely where large proprietary editors excel, are uncorrelated with success ($ρ\approx 0$). This dissociation holds on both CALVIN and the real-world-aligned SIMPLER-Bridge benchmark. We then present SGE-Goal, a…

    PDF
  • arXiv cs.SEOct 17

    When Does UML Software Modeling Pay Off? A Contingency Model of Industrial Modeling Value

    Kleinner Silva Farias de Oliveira

    With the emergence of specification-driven development (SDD), software modeling has regained strategic importance as a way to translate human intentions, requirements, and design decisions into precise specifications that can guide both developers and AI-assisted development tools. Despite the renewed relevance of modeling in SDD, empirical evidence remains limited on when its benefits outweigh the socio-technical effort required to create, communicate, synchronize, and maintain software models in industrial practice. This study investigates when software modeling generates value in industrial practice. We analyzed 405 survey responses collected from software practitioners. The questionnaire combined closed items concerning UML use, benefits, barriers, and improvement mechanisms with open-ended questions about current use, difficulties, and worthwhile contexts. Most respondents associated modeling with integration discussions (90 percent) and shared understanding (82 percent), but also reported time pressure (85 percent) and the effort required to create and maintain models (80 percent). Selective modeling, model-code synchronization, and collaborative support emerged as…

    PDF
  • arXiv cs.LGOct 17

    Sample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics

    Ankur Naskar, Vaneet Aggarwal

    Reinforcement learning with general utilities optimizes nonlinear functionals of policy-induced occupancy measures. We develop a natural actor-critic method for concave RLGU objectives admitting an exact variational dual representation, with explicit constructions for a broad class of separable occupancy utilities. Rather than estimating the occupancy measure and then forming the policy-gradient pseudo-reward, our method learns this pseudo-reward directly as a function of the state-action pair using a neural critic. The critic is trained by projected stochastic updates, while multilevel Monte Carlo combines outputs across training horizons to control its bias at logarithmic expected cost. Our analysis separates conditional actor bias from estimator second moments and accounts explicitly for dual optimization, critic approximation, and neural linearization errors. Under policy-transfer, dual-stability, and local critic-regularity conditions, the method achieves $\widetilde{O}(T^{-1/2})$ global convergence above policy, critic-class, and finite-width approximation errors using $\widetilde{O}(T)$ expected environment transitions and reference samples. For a fixed critic…

    PDF
  • arXiv cs.LGOct 17

    RAFT: Redundancy-Aware Input Filtering for Temporal Graph Neural Network Training

    Yue Dai, Sarah Zhou, Youtao Zhang

    Temporal graph neural networks (TGNNs) have shown strong performance on dynamic graph learning tasks by continuously updating node memories from evolving interactions (i.e., events) and leveraging these memories for downstream predictions. As graphs grow rapidly in modern applications, training requires processing an increasing number of events; meanwhile, each event can update node memories used by later events, creating dependencies that constrain parallel execution and limit the benefits of additional computing resources. These costs motivate an upstream question: Are all events, and the dependencies they introduce, necessary for learning? We investigate this question through two roles of temporal events: prediction targets and historical events sampled as inputs. We observe that targets involving stable node memories tend to exhibit lower prediction loss, while filtering historical events associated with stable memories can retain similar training-loss trajectories in several evaluated settings. Together, these observations suggest an opportunity to identify input redundancy through changes in node memories. Building on this opportunity, we propose RAFT, a redundancy-aware…

    PDF
  • arXiv cs.CROct 17

    How Intervention History Changes AI Agent Sabotage on Subsequent Tasks

    Daniel Saeedi, Amirali Aghazadeh

    AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack was caught changes an agent's ability to evade defer-to-trusted (DtT), a protocol that replaces suspicious work with a trusted model's solution. Herein, we study cross-episode adaptation: whether intervention history changes attack behavior on a subsequent task with different objectives and a fresh environment. We evaluate this using ControlArena's Infrastructure-as-Code (IaC) and SHADE-Arena as testbeds, where agents must complete a main task while covertly pursuing a harmful side objective. For each successor task, we pair a history-conditioned attempt with the model's no-history attempt. The retained history either states that the previous submission was replaced or additionally includes the trusted model's replacement. For Claude Opus 4.8 on IaC, intervention history reduces successful sabotage. Completion of both the main and side objectives falls from 77% to 12% when the agent is told about the replacement and to 38% when it is also shown the trusted model's replacement, while main task success…

    PDF
  • arXiv cs.AIOct 17

    The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents

    Jinwei Hu, Youcheng Sun, Yi Dong, Xiaowei Huang

    Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion? In this paper, we introduce the one-relation attack (ORA), a novel cognitive attack on this inferential relation. ORA localizes a critical implicit warrant and performs a one-relation intervention using a single source-grounded sentence that qualifies this warrant and steers the agent toward an incorrect belief. Across eighteen models on biomedical inference and vulnerability detection, best-of-$10 attacks overturn initially correct answers at mean rates of 54.9% for proprietary and 80.0% for open-weight models. Attacks also transfer without victim feedback, and paired controls support the roles of targeting and qualification. Moreover, successful sentences can pass source-support checks and evade identification, and multi-agent debate raises team error from 50.0% to 59.5% in our balanced stress test. These findings establish implicit warrants as a cognitive attack surface for manipulating agents' beliefs.

    PDF
  • arXiv cs.CROct 17

    The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check

    Ruqiya Bin Safi

    Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as a property of the target model. We hold the target model, the prompts and the responses fixed and change only the grader. Three dense graders of 8B and 9B parameters, from three model families, move compliant responses to the neighbouring class, evasion, instead of scattering them across classes. One of them assigns the compliance label zero times in 900 responses. This class collapse also appears on new harmful requests, on a target model from a third family, and in a held-out 7B grader from a fourth family. Per-class label counts expose it at no cost and without human labels. The collapse decides how the rate behaves under a change of grader. On two corpora of 900 responses and eight graders, the compliance rate differs by a factor of 22 to 25, while the non-refusal rate differs by 18 to 23 percentage points. Without the three collapsing graders, compliance differs by a factor of 1.7 to 2.8 on all four corpora, and non-refusal still differs by 10 to 22 points. These results do not change when every grader is called once. We propose a reporting minimum that…

    PDF
Load more