新闻与研究

arXiv:2605.08678v2 Announce Type: replace Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find that current agents remain far from reliably surpassing human-designed methods, and that engineering-style tuning is easier for them than genuine method invention. We further study the effects of test-time scaling, adaptive compute allocation, and conte

arXiv:2605.26492v1 Announce Type: cross Abstract: LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five prompts. We find that 11 words occur in 88.3% of generated stories, with little difference between models. These words include names (Elias, Mara, Elara), settings (lighthouses), and professions (clockmaker, librarian). These tokens do not often occur in published literature nor pre-training data, but they are found in preference data that is likely to have been used by all current models. Surprisingly, these "lighthouse" stories are infrequent when compared with the average post-training story, much of which contains references to copyrighted characters or adult content. This result demonstrates the potentially disproportionate impact of small datasets combined with powerful alignment algorithms.

arXiv:2605.26944v1 Announce Type: new Abstract: The problem of object pose and shape estimation has seen key advancements lately. Encoder-decoder (e.g., SAM3D, LRM, CRISP) and diffusion-based models (e.g., InstantMesh, Zero123, SceneComplete) have shown category-agnostic shape encoding capacity and open-set generalizability. In this work, we ask the question: Are the object pose and shape estimation methods mature enough, such that when used with antipodal grasp sampling, can outperform the end-to-end grasp synthesis methods? We explore this question in detail by scoping our study to parallel jaw grippers, 7-DoF grasps, and single-view RGB(-D) image as input. We implement and compare a state-of-the-art, end-to-end grasp synthesis method and three modular methods, which first estimate the object pose and shape for all objects in the scene, and generate grasps using antipodal sampling. We observe that the modular methods outperform the end-to-end method in all our experiments. The modula

arXiv:2505.17163v2 Announce Type: replace-cross Abstract: Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the absence of a dedicated and systematic benchmark. To address this gap, we propose OCR-Reasoning, a novel benchmark designed to systematically assess Multimodal Large Language Models on text-rich image reasoning tasks. Specifically, OCR-Reasoning comprises 1,069 human-annotated examples spanning 6 core reasoning abilities and 18 practical reasoning tasks in text-rich visual scenarios. Unlike existing text-rich image understanding benchmarks that only provide a final answer, this benchmark additionally provides a detailed step-by-step reasoning process. This dual annotation enables the evaluation of both the models' final answers and their reasoning processes, thereby offering a holistic assessment of text

arXiv:2605.27116v1 Announce Type: new Abstract: Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det f

arXiv:2605.26690v1 Announce Type: cross Abstract: Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informative. Existing reinforcement learning and off-policy generative approaches often degrade under surrogate noise, and position-agnostic mutation proposals risk disrupting functionally critical residues. We introduce SILO, a trajectory-level self-improvement imitation framework for oracle-budgeted protein design. SILO uses a hierarchical edit policy that decomposes each mutation into a position choice followed by a residue choice. In each active-learning round, the policy samples candidate trajectories via incremental stochastic beam search without replacement (SBS), and a UCB-based proxy ensemble, combined with an alanine-scan fitness score (AFS), selects candidates with functionally relevant edits for in silico oracle evaluation. The policy is then updated by next-action cross-entropy imitat

arXiv:2512.08371v4 Announce Type: replace Abstract: Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate multivariate Bernoulli distribution parameters and calculates weights for each label combination. This approach ensures the weighted sampling acquires target distribution characteristics while accounting for label dependencies. We applied this approach to a variety of datasets, including a sample of research articles from Web of Science labeled w

arXiv:2605.26717v1 Announce Type: cross Abstract: Adapting large language models (LLMs) for personalized recommendation requires aligning their general-purpose capabilities with user-specific preferences while effectively leveraging both behavioral and semantic signals. Existing approaches typically integrate these signals at either the input level (e.g., injecting behavioral embeddings into the token space) or the output level (e.g., contrastive alignment of separate encoders), suffering from distribution gaps or lack of end-to-end task supervision. In this work, we introduce L2Rec, which unifies behavioral and semantic understanding at the parameter level of LLMs. Our key insight is that the same set of Transformer parameters can serve as a shared medium for both views: by applying view-specific, personalized low-rank perturbations via a Dual-view Personalized Mixture-of-Experts (DPMoE) mechanism, L2Rec enables a single LLM backbone to produce complementary behavioral and semantic ad

arXiv:2506.11253v2 Announce Type: replace Abstract: Machine unlearning removes certain training data points and their influence from AI models (e.g., when a data owner revokes their consent to allow models to learn from the data). In this position paper, we propose to lift data-tracing machine unlearning to knowledge-tracing for foundation models (FMs). We support this position based on practical needs and insights from cognitive studies. Practically, tracing data cannot meet the diverse unlearning requests for FMs, which may be from regulators, enterprise users, product teams, etc., who have no access to FMs' massive training data. Instead, it is convenient for these parties to issue an unlearning request about the knowledge or capability FMs (should not) possess. Cognitively, knowledge-tracing unlearning aligns with how the human brain forgets more closely than tracing individual training data points does. We further discuss the nontrivial challenges in the knowledge-tracing machine

arXiv:2605.26596v1 Announce Type: new Abstract: The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the comp

arXiv:2512.16111v2 Announce Type: replace Abstract: Learning the structure of directed acyclic graphs (DAGs) from observational data is a central problem in causal discovery, statistical signal processing, and machine learning. Under a linear Gaussian structural equation model (SEM) with equal noise variances, the problem is identifiable and we show that the ensemble precision matrix of the observations exhibits a distinctive structure that facilitates DAG recovery. Exploiting this property, we propose BUILD (Bottom-Up Inference of Linear DAGs), a deterministic stepwise algorithm that identifies leaf nodes and their parents, then prunes the leaves by removing incident edges to proceed to the next step, exactly reconstructing the DAG from the true precision matrix. In practice, precision matrices must be estimated from finite data, and ill-conditioning may lead to error accumulation across BUILD steps. As a mitigation strategy, we periodically re-estimate the precision matrix (with less

arXiv:2605.06213v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies at the boundary, where the per-prompt pass probability is near $0.5$ under random-sampling decoding, and propose Dynamic Boundary Evaluation (DBE), which actively locates each model's boundary and places it on a globally comparable difficulty scale. DBE delivers three artifacts: (i) a calibrated item bank covering safety, capability, and truthfulness, with per-item difficulty labels validated across $9$ reference LLMs; (ii) Skill-Guided Boundary Search (SGBS), a search algorithm that finds boundary items for a given target LLM using only API-level query access; and (iii) an evaluation protocol that places a new LLM on a unified ability scale and grows the evaluation set adaptively when the target fa

arXiv:2605.26302v1 Announce Type: new Abstract: Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how long does an agent remain reliable after deployment? Even when model weights are frozen, an agent's effective state keeps changing as it compresses interaction history, retrieves from a growing memory store, revises facts after updates, and undergoes routine maintenance. Reliability therefore becomes a lifespan property of the full agent harness, not only a snapshot property of the base model. We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering: measuring not only whether deployed agents degrade, but what form the degradation takes and where repair should target. AgingBench organizes agent aging into four mechanisms: compression aging, interference aging, revision aging, and maintenance aging. To diagnos

arXiv:2605.27136v1 Announce Type: new Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment. However, most existing methods are adapted from the LLM literature and primarily focus on the language modality, leaving the contribution of visual information to LVLM uncertainty largely underexplored. In this paper, we investigate how LVLMs process visual information and whether this process can be used to improve uncertainty estimation. By analyzing hidden representations after the integration of visual features during the generation process, we observe that high-confidence predictions rely more heavily on visual content than uncertain ones. Building on this insight, we propose Visual-Grounded Token UQ (VIG-TUQ), a training-free framework that explicitly incorporates visual grounding into uncertainty estimation by weighting token-level language uncertainty with visual grounding scores.

arXiv:2605.27304v1 Announce Type: new Abstract: Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To address this gap, we present PlayClass, a pipeline for play-behaviour classification in poultry from top-down pen video. The pipeline leverages long-duration tracking with SAM 3 via YOLO-guided chunk boundaries to minimise identity errors in point-based prompting, and frozen embeddings from image and video foundation models for play action classification. Although handcrafted motion features from tracked masks alone achieved competitive accuracy, V-JEPA 2.1 consistently outperformed all other backbones across model scales, reaching 77.0 macro-averaged F$_1$ when combined with handcrafted features. Despite this result, the dataset remains challenging due to play sub-types sharing similar kinematic profiles with non-play and inter-bird occlusion. Overall, our work provides encouraging evidence t