Knowledge catalogue
arXiv:2609.37500v1 Announce Type: new Abstract: On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its reliance
arXiv:2609.36393v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit o
arXiv:2609.36677v1 Announce Type: new Abstract: Language-guided multi-camera tracking must preserve a target identity across unobserved gaps, where similar candidates and uncertain returns can make ea
arXiv:2609.38164v1 Announce Type: new Abstract: General-purpose physical AI models must combine broad visual and linguistic capabilities with precise control across robot embodiments and efficient ada
arXiv:2609.36561v1 Announce Type: new Abstract: Motion planning on arbitrary Riemannian manifolds is an important and difficult problem that frustrates typical planning methods for Euclidean spaces. I
arXiv:2609.35953v1 Announce Type: new Abstract: Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress. We examine young adults' (ages
arXiv:2609.35874v1 Announce Type: new Abstract: Online POMDP planners optimize the expected cumulative cost, which can mask dangerous states when the belief places significant mass on high-cost states
arXiv:2609.37554v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructio
arXiv:2609.37493v1 Announce Type: cross Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error
arXiv:2609.37065v1 Announce Type: new Abstract: Decision-making under uncertainty often relies on predicted parameters, yet accurate prediction does not necessarily lead to good operational decisions.
arXiv:2609.37633v1 Announce Type: cross Abstract: The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards t
arXiv:2609.37916v1 Announce Type: cross Abstract: Production machine learning (ML) stacks often split graph compilation and kernel execution across different layers and languages, making backend behav
arXiv:2609.36885v1 Announce Type: cross Abstract: RNA design aims to identify sequences that fold into specified secondary structures. Existing methods formulate the task as target-specific search or
arXiv:2602.18319v2 Announce Type: replace-cross Abstract: We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld c
arXiv:2609.36605v1 Announce Type: new Abstract: Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We intro
arXiv:2609.37560v1 Announce Type: new Abstract: Grinding and sanding are fundamental processes in industrial robotic surface finishing. However, physical trials are expensive and consume workpieces, m
arXiv:2609.37583v1 Announce Type: new Abstract: Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interaction
arXiv:2609.37925v1 Announce Type: cross Abstract: Autoregressive (AR) video diffusion enables low-latency, streamable video generation, but prediction errors often accumulate over long rollouts. Train
arXiv:2609.36843v1 Announce Type: new Abstract: Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World mo
arXiv:2609.35954v1 Announce Type: cross Abstract: Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is
arXiv:2609.36724v1 Announce Type: new Abstract: Sparse expert models can distribute traffic evenly while still grouping incompatible training signals within the same experts. We study routing as a gra
arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such
arXiv:2609.36851v1 Announce Type: new Abstract: End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their
arXiv:2609.38072v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires models to resolve small visual evidence within extremely large image
arXiv:2609.37543v1 Announce Type: new Abstract: Cross-lingual zero-shot transfer and multilingual fine-tuning are promising approaches for NLP tasks such as Named Entity Recognition (NER) in low-resou
arXiv:2609.36866v1 Announce Type: new Abstract: Inter-modality MRI translation aims to synthesize missing MRI modalities from available acquisitions, reducing the need for additional scanning while pr
arXiv:2609.37976v1 Announce Type: cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacit
arXiv:2609.36875v1 Announce Type: new Abstract: Accurate instance segmentation in dynamic scenes is important for downstream applications such as robotics and autonomous driving. Existing Segment Anyt
arXiv:2609.36942v1 Announce Type: cross Abstract: Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settin
arXiv:2609.36580v1 Announce Type: new Abstract: LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available on
arXiv:2609.37294v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks, yet their stochastic behavior challenges the validity, reproducibil
arXiv:2609.36862v1 Announce Type: cross Abstract: Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface:
arXiv:2609.36906v1 Announce Type: new Abstract: Reliable embodied decisions under partial observability require informative observations and sufficient supporting evidence. However, semantic scores al
arXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and
arXiv:2609.35790v1 Announce Type: cross Abstract: While neural theorem provers have achieved impressive milestones in formal mathematics, they largely operate on the assumption that faithful Lean 4 fo
arXiv:2609.36601v1 Announce Type: new Abstract: On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teac
arXiv:2609.36031v1 Announce Type: new Abstract: Learning from human videos offers a promising route to acquiring diverse manipulation skills. Extending this capability beyond tabletop settings to long
arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hin
arXiv:2609.36995v1 Announce Type: cross Abstract: Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related
arXiv:2609.37283v1 Announce Type: new Abstract: Medical multimodal large language models (MLLMs) are increasingly expected not only to answer clinical questions, but also to localize the visual eviden
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template
arXiv:2609.36421v1 Announce Type: cross Abstract: Reinforcement learning (RL) is a powerful framework for robotic control, yet its practical application is often hindered by high sample complexity. Th
arXiv:2609.36939v1 Announce Type: new Abstract: GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning imp
arXiv:2609.37509v1 Announce Type: new Abstract: The boundary element method (BEM) provides an efficient numerical framework for solving multiple scattering problems in unbounded homogeneous domains. B
arXiv:2609.36950v1 Announce Type: new Abstract: Simulation-based inference is challenging when many heterogeneous observations must be composed, hierarchical latent structure must be preserved, and th
arXiv:2609.36784v1 Announce Type: new Abstract: When transferring manipulability across systems with different sizes and kinematic structures, matching absolute ellipsoid scale may be unnecessary when
arXiv:2609.37416v1 Announce Type: new Abstract: Post-training quantization (PTQ) methods in the GPTQ family minimize a layer-wise reconstruction error on a uniform grid whose scale must be chosen; the
arXiv:2609.37298v1 Announce Type: cross Abstract: Conformal prediction provides set-valued predictions with distribution-free coverage guarantees, making it attractive for high-stakes image classifica
arXiv:2609.37842v1 Announce Type: cross Abstract: Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influen
arXiv:2609.36599v1 Announce Type: cross Abstract: We study whether scaling video generation enables models to reason about hidden information from the past frames, and at what computational cost. Our
arXiv:2609.37899v1 Announce Type: new Abstract: Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient v
arXiv:2609.36545v1 Announce Type: new Abstract: Equirectangular projection (ERP) is the standard representation for 360^irc imagery, and robust dense feature matching on ERP underpins panoramic stereo
arXiv:2609.37951v1 Announce Type: new Abstract: Replacing a visible advertisement in a broadcast frame is geometrically straightforward but photometrically delicate. A pasted graphic can have the corr
arXiv:2609.36801v1 Announce Type: new Abstract: Interactive simulations of embodied AI or spatial computing applications build on realistic 3D scenes that support daily activities. However, sparse, ir
arXiv:2609.36653v1 Announce Type: new Abstract: Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with shar
arXiv:2609.36527v2 Announce Type: new Abstract: Recovering complete physical fields from sparse observations is challenging because the measurements may not uniquely determine the underlying state. Di
arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under be
arXiv:2609.36107v1 Announce Type: new Abstract: While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these
arXiv:2604.01178v4 Announce Type: replace-cross Abstract: We call query--key relevance absolute when its values lie on a fixed bounded scale, depend on neither competing keys nor sequence length, requ
arXiv:2609.37917v1 Announce Type: new Abstract: Projection pursuit searches for a direction along which the data look least Gaussian. When the observation space contains a large Gaussian complement, t