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 fields3475Multimodal545Agents520Frontier LLMs443Inference & serving268Image segmentation180Learning verifiable rewards1633D scene160Graph learning158Evals103Voice AI99Classifier & causal discovery87Forecasting time78Flow matching74Training & fine-tuning63Teacher 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.

Papers

  • arXiv cs.CLOct 18

    LAMB: Latent Multi-Hypothesis Beliefs for Long-Horizon Large Language Agents

    Peien Ding, Hui Li, Yuhan Liu, Jinsong Su

    Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states. Although effective, many belief-state methods encode memory in discrete natural language, where repeated compression can omit evidence or prematurely discard plausible alternatives. We introduce LAMB, a recurrent framework for latent multi-hypothesis beliefs. A Common--Delta factorization combines a shared Common state for interaction evidence with weighted Delta components for competing hypotheses. Relative evidence from action-outcome predictions guides recurrent hypothesis updates without generating textual memory. A context-conditioned readout exposes hypotheses separately to the policy through a fixed-token belief prefix in the default configuration. The belief modules and policy are jointly trained using action imitation and auxiliary state, outcome, and observation-discrimination objectives. Across ALFWorld, BabyAI, ScienceWorld, and Crafter, LAMB matches or outperforms PABU, improving ALFWorld SR@30 and ScienceWorld success by 6.0 and 22.0 percentage points, respectively, and Crafter achievement progress by 26.37 points. On…

    PDF
  • arXiv cs.LGOct 18

    M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21

    Karthik Iyer, Nasser Sabar

    Self-supervised molecular representation learning is increasingly used to improve transfer on small, label-limited property prediction tasks, yet commonly used contrastive objectives can be sensitive to view construction and are often evaluated with protocols that report only discrimination. We adapt Joint Embedding Predictive Architectures (JEPAs) to molecular graphs by masking chemically coherent connected subgraphs and training a context encoder to regress the masked target embedding produced by an exponential-moving-average (EMA) teacher. To evaluate predictive self-supervision under realistic distribution shift, we introduce a leakage-resistant, compute-matched three-phase protocol: (i) an 80-run objective screening on ESOL with fixed compute budgets, (ii) JEPA-only refinement of masking and augmentation choices, and (iii) per-assay Tox21 evaluation under Bemis-Murcko scaffold splits with joint discrimination-reliability analysis and attribution diagnostics. Under matched compute, M-JEPA achieves substantially lower ESOL proxy RMSE than a compute-matched InfoNCE baseline (mean RMSE 2.12 vs 3.75; mean paired dRMSE 1.61; 95% bootstrap CI [1.52, 1.72]; Wilcoxon p=2.4e-4) and…

    PDF
  • arXiv cs.LGOct 18

    Indistinguishable Agents: Training Agent Privacy as Twin-World Indistinguishability

    Jiaming He, Guanyu Hou, Yi Yu, Xudong Jiang

    LLM agents search, shop and send messages for their users, and every action is seen by some party. Existing privacy training rewards agents for not mentioning protected items, yet an observer can infer a private fact from what the agent does. Since an observer learns a fact only if its view changes with the fact, we propose \methodfull (\method), which trains on twin worlds that differ only in the private fact. A frozen distinguisher scores each observer's view by its log-likelihood ratio for the true world, and paired GRPO trains the agent on task success minus this ratio. We prove that this objective controls the Bayes success of every observer on every channel. On shopping and messaging tasks \method removes the leakage that disclosure judges and query-level rewards miss, while the agent still completes its tasks.

    PDF
  • arXiv cs.CLOct 18▲ 1

    Legal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations

    Amirreza Mohseni, Gerasimos Spanakis

    People ask conversational AI models about their legal rights, obligations, procedures, and personal situations that may have legal consequences. To study this behavior, we first need to distinguish requests for legal guidance from other legally themed discussions and unrelated conversations. We contribute a multi-axis taxonomy of legal queries capturing whether legal guidance is sought, how a request is formulated, and which legal domains it concerns; apply it to 2,122 naturally occurring WildChat-1M conversations; and create a human-reviewed gold evaluation set of 200 conversations. All annotations, model checkpoints, and evaluation code are publicly available. In this enriched sample, 71.1% of conversations containing legal content seek personalized or practical guidance. Rights-and-options advice is the most common primary request type among legal-content conversations, and 25.3% of guidance-positive conversations span multiple legal topics. The gold evaluation set supports a two-stage comparison of ModernBERT-base and ModernBERT-large against a TF-IDF cascade. Our framework supports large-scale studies of legal guidance in conversational AI, and the public release of the…

    Code
  • arXiv cs.CLOct 18

    Do LLMs Reproduce the Age Gap in Loneliness? Evaluating Survey Simulation against European Survey Data

    Yuliya Li, Achim Rettinger, Dominik Beyer

    Large language models (LLMs) are often used to simulate survey respondents, but matching survey averages does not establish accurate demographic differences. We test whether LLM outputs reproduce within-country age gaps in loneliness using the 2022 EU Loneliness Survey, comparing adults aged 18-34 and 65 or older in France, Italy, Poland, and Sweden. We evaluate simulation with and without age information and direct distribution estimation against a probability-based sample, with a non-probability sensitivity reference. Both human samples show higher mean loneliness among younger adults. Under age-specified simulation with standard response-option order, Mistral Small 4 and GPT-5.6 Terra reverse this ordering under all three prompt framings in three and two countries, respectively, mainly by overestimating older-adult means. DeepSeek V4 Flash preserves the ordering everywhere but underestimates both group means, with errors largely cancelling in France and Italy. Against the probability-based reference, direct estimation has lower absolute age-gap error than simulation for Mistral and Terra in every country. For DeepSeek, simulation has lower gap error but direct estimation has…

    PDF
  • arXiv cs.CVOct 18

    Deep Auxiliary Learning via Bilevel Feature Optimization for Label-Efficient Medical Image Segmentation

    Fuping Wu, Xi Jia, Le Zhang, Jiahua Li, Rima Mustafa +2

    Auxiliary learning (AL), which can improve the performance of a primary task by leveraging related auxiliary tasks, is commonly regarded as a special case of multi-task learning. Existing AL approaches typically require manually annotated auxiliary labels, increasing annotation costs, particularly in medical imaging where expert labeling is expensive. In this work, we investigate whether segmentation performance can be improved using auxiliary tasks whose labels are automatically derived from existing segmentation annotations, requiring no additional manual labeling. To address this, we propose a novel auxiliary learning framework, formulated as a bilevel optimization problem. Our method enables effective knowledge transfer between tasks via a feature communication module, enhancing the primary segmentation task. We evaluate the method on three medical image segmentation benchmarks under limited-label settings. The results demonstrate consistent improvements over state-of-the-art methods, achieving superior label efficiency. The code is publicly available at https://github.com/FupingWu90/ALBO.

    PDF
  • arXiv cs.CLOct 18

    Morpheus: a fully local, defense-in-depth de-identification engine for Greek clinical text - a benchmark evaluation

    Filippos-Paschalis Rorris, Nikoleta Stanitsa, Tatiana Rorri, Foteini Rorri, Constantine N. Antonopoulos

    Background and Objective: Clinical free text cannot leave the hospital without de-identification, yet no de-identification system or benchmark exists for Greek clinical text. We evaluated Morpheus, a fully local de-identification pipeline for Greek clinical documents, on 500 synthetic discharge summaries. Methods: The notes (300 cardiac surgery, 100 cardiology, 100 nephrology) were generated by a frontier large language model (Gemini 3.1 Pro) constrained to authentic Greek hospital document layouts. Notes were pre-annotated at generation; two clinicians then independently reviewed and corrected every note, blinded to each other, with disagreements arbitrated. Primary outcomes were recall over must-redact identifiers and over-redaction of clinical content, measured over must-survive probes. Secondary outcomes: residual leaks flagged by an independent egress-review layer, processing time and reproducibility. Results: Inter-annotator agreement was F1 = 0.998. The de-identification rate was 96.59% (7,666/7,937 identifier instances; 95% CI 96.16-96.96): 98.49% for direct and 93.42% for quasi-identifiers. No patient's own complete identifier survived in any note; of 271 residual…

    PDF
  • arXiv cs.LGOct 18

    Learning without Overwriting: Structural Knowledge Fusion for Continual Learning

    Kanishk Bakshi, Amitansu Pattanaik, Kathiravan Srinivasan

    Catastrophic forgetting in sequential deep learning arises from a fixed-capacity architectural constraint: parameter updates encoding new tasks perturb weight subspaces supporting prior representations. We introduce the Knowledge Fusion Network (KFN), which mitigates the stability-plasticity trade-off in class-incremental learning through novelty-gated structural expansion rather than parameter negotiation within a shared capacity budget. KFN decouples task acquisition from knowledge consolidation: each incoming task is learned in an isolated lightweight specialist network (2.8M parameters) and integrated into the global model via a Structural Fusion Module that allocates dedicated channel capacity conditioned on a quantitative novelty score. Dual structural isolation--channel-space separation with temporally phased gradient unfreezing--protects consolidated knowledge. On ten-task Split CIFAR-100, KFN achieves 11.94% minimum task accuracy and 71.16% task-10 accuracy, whereas shared-parameter baselines degrade severely: LwF to 9.07% average accuracy (0.00% min), Replay++ to 8.91% (85.08% forgetting), and Replay to 16.21% (73.44% forgetting); KFN's forgetting (57.92%) is 15.5 pp…

    PDF
  • arXiv cs.LGOct 18

    FHKAN: Fractional Hermite Kolmogorov-Arnold Networks for Data-Driven and Physics-Informed Learning

    Arsha Farnoush, Amirhossein Sadr, Aida Pakniyat, Dara Rahmati, Saeid Gorgin +1

    Kolmogorov-Arnold Networks (KANs) replace fixed scalar weights by learnable univariate maps, yet most spectral KANs still rely on Chebyshev polynomials that live on a bounded interval and therefore require a saturating squashing of the pre-activation. We introduce the Fractional Hermite Kolmogorov-Arnold Network (FHKAN), a neural architecture that equips KANs with an adaptive, trainable fractional-order generalized Hermite basis. With a nonnegative shape parameter, the underlying generalized Hermite functions are orthonormal on the entire real line and uniformly bounded under a Gaussian envelope, so they act directly on unbounded pre-activations without any saturating map. We derive closed-form derivatives of the generalized, fractional, and scaled basis away from the origin and determine its order of differentiability at the origin, where the fractional power map creates a singular point. On synthetic regression, FHKAN attains the lowest test error at every network depth among nine fixed activations and the spline-based KAN. On image classification, image denoising, and sentiment analysis, the best-performing fractional Hermite block yields the highest accuracy or reconstruction…

    PDF
  • arXiv cs.CVOct 18

    PLANE: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models

    Jianghao Yin, Lang Yu, Qianxi Yu, Qin Chen, Jie Zhou +2

    Large Vision-Language Models (LVLMs) commonly suffer from hallucinations, which appear as fabricating non-existent objects or outputting incorrect attributes and spatial relationships in images. Previous works empirically indicate that CLIP-style vision encoders tend to focus on primary objects while ignoring image details, which is one of the causes of hallucinations. To address this issue, we propose plug-and-play fine-grained visual experts (PLANE) comprising two components: LoRA visual experts operating on CLIP for multi-aspect image encoding, and an instruction-aware gate network for adaptive image feature fusion. During training, we construct a fine-grained image-caption pairs dataset, where images are described from three aspects: objects, attributes, and relations between objects. Image-caption pairs from different aspects are used to train the three fine-grained LoRA experts respectively. Aiming at comprehensively evaluate our method's capabilities, we manually annotate a fine-grained hallucination evaluation benchmark for LVLMs which is GPT4-independent during evaluation phase (GIFT). We conduct experiments both on popular hallucination evaluation benchmarks and GIFT.…

    PDF
  • arXiv cs.CLOct 18

    A Multi-granularity Interaction Network for Relational Triple Extraction

    Xiaocheng Luo, Yanping Chen, Zaifu Zhan

    Relational triple extraction identifies entity relations from raw sentences without depending on entity type information. The performance of traditional methods is seriously degenerated by ``unseen'' entities, because these methods can't build contextual dependencies relevant ``unseen'' entities. This paper addresses this challenge by proposing a multi-granularity interaction network that leverages word-word, entity-relation, and head-tail interactions to capture deep semantic dependencies. By incorporating multiple iterations, the multi-granularity interaction network is effective to refine the representations corresponding to head and tail entities. It enhances the global semantic features associated with relational triples, aiding in the remediation of triples that may have been overlooked or omitted in earlier steps. Strong and consistent performance is achieved by our method on two rearranged datasets, with a significant improvement in identifying relational triples, including those involving ``unseen'' named entities. For example, our model improves F1-score by 3.1%/20.5% over previous approaches on the NYT-R/WebNLG-R datasets in the Unseen metric. Code:…

    PDF
  • arXiv cs.CVOct 18

    Image Dehazing as In-Context Tabular Inference

    Le-Anh Tran

    Image dehazing is traditionally addressed through handcrafted physical priors or task-specific deep learning models, often requiring carefully designed architectures or extensive model training. Recent advances in tabular foundation models (TFMs), however, offer an alternative learning paradigm in which continuous relationships can be inferred directly from contextual examples without task-specific model training. Motivated by this capability, this paper investigates whether single-image dehazing can be effectively reformulated as an in-context tabular regression problem and introduces DehazeTab, a framework that estimates atmospheric transmission from structured image-patch representations. Specifically, overlapping patches extracted from hazy images are transformed into tabular samples using handcrafted haze-related descriptors, pretrained visual embeddings, or their hybrid combinations, while corresponding transmission patches are summarized as scalar regression targets. A pretrained TFM then performs in-context regression using labeled reference patches to predict transmission values for unseen images without any further fine-tuning. These predictions are spatially aggregated…

    PDF
  • arXiv cs.AIOct 18

    Spectral Adaptive Graph Transformer for Efficient and Scalable Traffic Forecasting

    Amirhossein Ghaffari, Susanna Pirttikangas, Ekaterina Gilman

    Traffic forecasting models based on spectral graph convolution offer an interpretable account of how information is mixed between sensors, but they rely on an eigendecomposition of the graph Laplacian. It costs cubic time, is fixed by the road network, and provides a symmetric operator that cannot represent the directed propagation of traffic congestion. Attention-based spatio-temporal transformers remove these limitations but generate a dense sensor-by-sensor attention map at each layer and time step, so memory, rather than accuracy, becomes the binding constraint on large networks. We introduce the spectral adaptive graph transformer, whose spatial operator is learned rather than derived from the Laplacian, directed rather than symmetric, and conditioned on the current traffic state rather than a static state, at a cost linear in the number of sensors. A sparse road graph diffusion branch provides the strictly local propagation that a low-rank operator cannot express, and a zero-initialized gate learns the balance between the two. Before spatial mixing, a unit-mean-gain frequency-bin attention module reweights each sensor's short-term periodicities according to its identity and…

    PDF
  • arXiv cs.CVOct 18

    Reflection-Guided Dynamics Rectification for Text-to-Image Generation

    Shuo Xu, Hanrui Ying, Debin Liu, Jianjun Li, Zhiyuan Ma

    Fine-grained rectification of existing generations under a limited additional budget remains a key problem in test-time optimization (TTO) for image generation. As for prior approaches, they could identify residual errors, but could not directly ensure that the model acts on the feedback during reasoning. Such errors stem from multiple sources, such as the initial noise or text prompt, and ultimately induce an execution gap of failing to handle potential deviations along the trajectory generating. However, classic models generally cannot remedy this gap. To narrow it, we propose Reflection-Guided Dynamics Rectification (RGDR), which turns reflections on completed outputs into corrective interventions on the process of sampling dynamics at the trajectory level. Specifically, RGDR could impact every sampling step by adapting to instantaneous intervention. Moreover, RGDR generates flexible candidates while adjudicating between them and the reference. As experiments show, rectification from RGDR starts from the existing base trajectory and reflection, and RGDR is substantially more effective than former trajectory exploration. Under matched budgets for additional image generation,…

    PDF
  • arXiv cs.CVOct 18

    HullProbe: Measuring Interventional Part Reliance in Maritime Vessel Classifiers

    Faisal Mohammad, Mohamed Younis

    Recognizing a vessel's type from an image supports maritime surveillance and sanctions monitoring, but a classifier can reach high accuracy by leaning on the generic hull instead of the more distinctive superstructure, and is then fooled when a vessel is re-hulled or occluded. De-biasing methods claim to remove such reliance, yet the field certifies them with worst-group accuracy, a proxy that needs group labels and only infers reliance from accuracy. We measure the reliance directly. HullProbe swaps a registered anatomical part of a vessel for another instance's and reads how much that part drives the decision, using a same-class swap to control for compositing artifacts. Because a surface vessel is a hull and a superstructure arranged along one axis, its parts form a 2x3 grid whose 2^6 = 64 swaps we evaluate exhaustively, and a single Walsh transform returns each part's interventional influence and its interaction spectrum. On planted shortcuts, where the true reliance is known, the measure tracks worst-group accuracy (r = -0.94 over 45 configurations), and replacing its learned segmenter with human annotations changes the hull-share by less than the audit's resolution. On the…

    PDF
  • arXiv cs.CLOct 18

    TIRE: Top-Down Formula Instantiation with Reliable Execution for Physics Problem Synthesis

    Xiaoyu Wu, Zhaoxin Yu, Xinglin Xiao, Nan Xu

    Advancing physics reasoning in large language models requires scalable training data that connect physical laws, concrete problem scenarios, and verifiable numerical answers. Expert-designed problems offer top-down control over physical laws, conditions, and scenarios, but require costly human effort. LLM-based synthesis from texts scales efficiently, but model-generated answers and assessments leave supervision vulnerable to hallucinations. We introduce TIRE, a framework for Top-Down Formula Instantiation with Reliable Execution that brings knowledge-driven problem construction to large-scale data generation. Top-down instantiation uses reusable physical formulas and their applicability conditions to control the physical relations and numerical configurations of generated problems. Reliable execution establishes reference answers before problem generation, providing a common numerical foundation for problem construction and teacher distillation. Together, these mechanisms combine control over problem content with execution-grounded supervision for both supervised fine-tuning and reinforcement learning. Using TIRE, we construct TIRE-19k, spanning nine subfields of physics. Across…

    PDF
  • arXiv cs.CROct 18

    Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use

    Tianhe Lu, Sakuna Harinda Jayasundara, Eric Spero, Ewan Tempero, Robert Biddle +1

    Cryptographic API misuse in large language model-generated code can compromise software security. While many existing approaches improve code security by modifying model parameters or inputs, how representation changes associated with different cryptographic API repairs can support a shared intervention for safer code generation remains underexplored. To investigate this, we construct 48,000 matched program pairs across four programming languages and ten cryptographic API misuse categories. Each pair changes a specified API decision while preserving the programming task. Subtracting the misuse program's internal representation from its secure counterpart's gives a repair vector. Across five models, comparisons of mean repair vectors reveal stronger organization by misuse category than by language. These category-specific patterns also support a shared intervention. We introduce CrypSteer, which extracts a shared direction by normalizing repair differences and selecting a principal component aligned with repairs across misuse categories. With model weights fixed, adding one shared direction per model to its internal activations during generation improves aggregate target security…

    PDF
  • arXiv stat.MLOct 18

    Decision-Target Reversal under Informative Label Missingness

    Farinborz Setoudehtazangi, Geoffrey J. McLachlan

    Informative label missingness can improve classification efficiency because the pattern of label availability may itself contain information about the discriminant structure. We show that this advantage need not persist across deployment objectives: with the data-generating model and statistical experiments held fixed, informative partial classification can be favourable under one loss and unfavourable under another. We call this phenomenon decision-target reversal. For binary Gaussian discrimination, we derive a local cost-sensitive excess-risk expansion and, in one dimension, obtain explicit critical cost ratios at which the first-order risk ordering reverses. We show that the required covariance geometry arises under finite uncertainty-dependent missingness mechanisms with a fixed marginal missing-label proportion. We then extend the analysis to multiclass finite-action problems through loss-specific active-boundary curvature, yielding a general decision-target frontier. Monte Carlo experiments illustrate the predicted reversals, and a descriptive gastrointestinal-lesion application with agreement-defined label availability illustrates sensitivity to deployment costs. The…

    PDF
  • arXiv cs.CLOct 18

    MemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity

    Jiajun Tan, Fei Sun, Xinyu Ma, Shixuan Zhang, Du Su +4

    Memory serves as the core component of LLM-based agents, enabling personalized responses via extracting and using user preferences from past interactions. However, its use may reduce response diversity, thereby narrowing the range of information available to users. Existing evaluations rely largely on synthetic interactions and cover few memory systems, leaving the effects of memory on response diversity insufficiently evaluated in real-world scenarios. We introduce MemBubble, a benchmark of 1000 instances built on preferences extracted from real user-assistant conversations. To measure the extent to which memory concentrates response distributions, we construct test queries in scenarios distinct from user preferences while preserving topical relevance through shared preference categories. Across multiple LLMs and memory mechanisms, entropy decreases by 34.7% on average compared with directly providing the full interaction history, highlighting the important role of memory processing in diversity loss. We also explore simple user-side interventions and changes in information availability but find that these do not effectively close the diversity gap. Our findings highlight the…

    PDF
  • arXiv cs.LGOct 18

    Trackable Skill Library Lifecycle Management for Agentic Reinforcement Learning

    Xi Zhu, Yuanlin Duan, Changyi Yang, Kai Mei, Riyang Bao +2

    Skill-augmented agentic RL has emerged as an effective approach to improving LLM agents on long-horizon tasks. Despite this progress, individual skills may follow distinct trajectories as the policy evolves, with some becoming redundant after the model internalizes their capabilities, others remaining valuable as external scaffolding, and still others turning harmful. However, existing skill library systems fail to identify each skill's true contribution due to free-riding among co-retrieved skills, difficulty confounding across tasks, and the absence of skill-specific counterfactual evidence, which prevents reliable skill lifecycle management. We propose TrackRL, an agentic RL framework where skill tracking drives skill library full lifecycle management. Specifically, within each GRPO group, we turn grouped sampling into online randomized controlled experiments. Independent random injection and within-group contrasts on the same task isolate each skill's true contribution, and reliability-weighted aggregation accumulates evidence across groups. As evidence accumulates, we continuously track skill utility, which measures the skill's causal contribution as external scaffolding,…

    PDF
Load more
PDF

Rising research topics

Coming with more sources: more tagged papers
  • Training & fine-tuning63+6200.0%
  • Code models23+2200.0%
  • AI safety45+2150.0%
  • Evals103+1960.0%
  • Robotics30+1400.0%
  • Image & video generation36+1100.0%
  • Computer vision47+1075.0%
  • Small LLMs11+1000.0%