Knowledge catalogue
arXiv:2610.09496v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision
arXiv:2610.09124v1 Announce Type: new Abstract: Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant t
arXiv:2610.10246v1 Announce Type: new Abstract: Constant-step stochastic approximation generally has a nonzero stationary mean error that persists under time averaging. This paper studies that error f
arXiv:2610.09230v1 Announce Type: new Abstract: Partial identification (PI) entails estimating bounds on causal effects by encoding different assumptions on data generation as a constrained optimizati
arXiv:2610.08812v1 Announce Type: new Abstract: We present Go2-DrivoR, a goal-conditioned adaptation of the end-to-end autonomous driving trajectory planning framework DrivoR for urban navigation with
arXiv:2610.09074v1 Announce Type: new Abstract: Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic t
arXiv:2610.09566v1 Announce Type: new Abstract: Imitation learning policies that integrate multiple sensory modalities are prone to overreliance on a dominant modality, such as vision, during training
arXiv:2610.09451v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are effective at understanding what task to perform, but provide limited control over how it should be executed, suc
arXiv:2610.09509v1 Announce Type: new Abstract: Latent actions supervise robot policies with action-like codes inferred from visual transitions, and their usefulness hinges on two questions: what a co
arXiv:2610.09120v1 Announce Type: new Abstract: Randomized exploration is central to bandit learning, multi-agent reinforcement learning, and zeroth-order policy search, yet its independence and priva
arXiv:2610.09255v1 Announce Type: new Abstract: Neural PDE surrogates are trained on numerical solver outputs that contain both physical evolution and solver-specific discretization errors. Because su
arXiv:2610.09408v1 Announce Type: new Abstract: Audio-visual multi-segment grounding (AV-MSG) in untrimmed videos, reasoning over audio-visual evidence and predicting multiple segments for a query, is
arXiv:2610.09462v1 Announce Type: new Abstract: Backdoored vision-language-action (VLA) policies can preserve benign task performance while producing malicious actions when a trigger appears. Detectin
arXiv:2610.10288v1 Announce Type: new Abstract: Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the
arXiv:2610.08933v1 Announce Type: new Abstract: Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating ev
🧬 Training and evaluating AI scientists on drug target discovery is hard. We introduce DrugTargetWorld: Synthetic Biomedical Worlds for Training and Benchmarking AI Scientists The environment turns en
arXiv:2610.10054v1 Announce Type: cross Abstract: Sampling transitions between metastable states is a central problem in dynamical systems theory and molecular dynamics in particular. A key challenge
arXiv:2610.10483v1 Announce Type: new Abstract: Sampling from a softmax distribution is a fundamental operation in machine learning, but its linear complexity in the number of items makes exact sampli
arXiv:2610.09703v1 Announce Type: cross Abstract: Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work,
arXiv:2610.09530v1 Announce Type: cross Abstract: Canonical Correlation Analysis (CCA) is a fundamental method for multiview shared space learning. However, its strict reliance on paired data poses a
arXiv:2610.10261v1 Announce Type: cross Abstract: Context: Once defined a taxonomy of stages structuring Machine Learning (ML) pipelines (e.g. Data Preprocessing, Modeling...), extracting these stages
arXiv:2610.10506v1 Announce Type: cross Abstract: Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should cho
We have a choice in front of us. In my latest op-ed for Transformer, I invite employees of frontier AI companies to ask themselves if their work is truly leading us toward a safer future. Reflecting o
arXiv:2610.09117v1 Announce Type: cross Abstract: Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation
arXiv:2610.08782v1 Announce Type: cross Abstract: Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize in
arXiv:2512.01917v2 Announce Type: replace Abstract: Eddy-covariance (EC) flux towers provide in situ measurements of CO_2 flux and serve as the ground-truth data for predictive `upscaling' models deri
arXiv:2610.07084v1 Announce Type: cross Abstract: An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert a
arXiv:2610.04898v2 Announce Type: replace-cross Abstract: This study analyzes the predictive power of LM-derived, token-level surprisal on Mandarin Chinese reading times. We first propose the Shortest
arXiv:2610.07168v1 Announce Type: cross Abstract: Representations of translated sentences are similar in the inner layers of multilingual language models -- an observation connected to the platonic re
arXiv:2610.07426v1 Announce Type: new Abstract: Accent classifiers are typically trained with a fixed label inventory and cannot accommodate new accent categories as new data becomes available. Moreov
arXiv:2610.06965v1 Announce Type: new Abstract: World action models jointly learn visual predictionand robot actions, providing a way to use observations ofscene evolution for policy learning. Their v
arXiv:2610.07452v1 Announce Type: cross Abstract: Accurate forecasting of pathological outcomes is a central problem in psychology. To do so, psychologists often collect intensive longitudinal data. H
arXiv:2610.07946v1 Announce Type: cross Abstract: Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruptio
arXiv:2610.07804v1 Announce Type: new Abstract: Prior Fitted Networks (PFNs) such as TabPFN now rival established statistical procedures across prediction and estimation tasks. A natural explanation i
arXiv:2610.07615v1 Announce Type: new Abstract: Active Feature Acquisition (AFA) is a classification problem in which an agent decides which costly features to acquire before predicting each sample's
arXiv:2610.07128v1 Announce Type: cross Abstract: Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI):
arXiv:2610.07902v1 Announce Type: new Abstract: Cantonese lyric writing requires close alignment between lexical tones and melodic pitch. Existing melody-guided lyric generation methods typically rely
arXiv:2510.22954v2 Announce Type: replace Abstract: Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human
arXiv:2610.07785v1 Announce Type: new Abstract: A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Yet existing visual goal-conditio
arXiv:2610.07459v1 Announce Type: new Abstract: Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe t
arXiv:2604.01064v2 Announce Type: replace Abstract: Despite advances in reinforcement and imitation learning, achieving both precise control and dynamic whole-body behaviors in long-horizon tasks rema
arXiv:2610.08450v1 Announce Type: new Abstract: Autonomous vehicles (AVs) have significantly advanced in real-world deployment in recent years, yet safety continues to be a critical barrier to widespr
arXiv:2610.08533v1 Announce Type: new Abstract: Geometric alignment scores based on Gram determinants provide a compact way to model higher-order consistency among modalities, yet how such scores resp
arXiv:2610.07023v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs. Exi
arXiv:2610.07891v1 Announce Type: new Abstract: Humanoid whole-body teleoperation translates human motion into stable robot behavior in real time. Existing systems typically rely on online motion reta
arXiv:2610.07601v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides a natural framework for adapting pretrained models to video temporal grounding, where gen
arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain diffi
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can diffe
arXiv:2610.07249v1 Announce Type: new Abstract: How can an AI agent determine what rules to follow? One rule permits an action. Another imposes a condition, exception, or conflicting obligation. Deter
Common Sense Media, a nonprofit that offers reviews of apps, services, and entertainment with a focus on youth safety, today said that OpenAI's ChatGPT for Teens is an 'unacceptable risk.' ChatGPT for
arXiv:2610.07739v1 Announce Type: new Abstract: Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to dow
arXiv:2610.08717v1 Announce Type: new Abstract: We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity
arXiv:2610.07949v1 Announce Type: new Abstract: Action-chunking policies predict multi-step control sequences, but a fundamental question remains: how much of a predicted action chunk should be commit
arXiv:2610.07218v1 Announce Type: new Abstract: Recent advances in representation learning have highlighted the utility of constant-curvature models, such as hyperbolic and spherical spaces, for model
arXiv:2610.08115v1 Announce Type: cross Abstract: Hamilton-Jacobi reachability constructs safety certificates for specified dynamics and safety constraints, tying each certificate to the deployment co
arXiv:2610.07578v1 Announce Type: new Abstract: In cooperative Multi-Agent Reinforcement Learning (MARL), agents are often trained under concurrent participation, while in many tasks some agents act e
arXiv:2610.07752v1 Announce Type: new Abstract: Collaborative manipulation requires robots to perform complementary actions as interactions unfold. We study single-policy decentralized collaboration:
arXiv:2601.16390v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant lan
arXiv:2610.08777v1 Announce Type: new Abstract: Interactive video world models need to generate each video chunk efficiently while responding faithfully to user controls. Many systems use chunk-wise a
arXiv:2610.07868v1 Announce Type: new Abstract: Large language model agents have been used to search over symbolic structures such as programs and equations. We propose CueRator, an agentic framework