Knowledge catalogue
arXiv:2610.04950v1 Announce Type: new Abstract: On-policy distillation (OPD) improves the reasoning capabilities of small language models through token-level teacher supervision on student-generated t
arXiv:2610.04366v1 Announce Type: new Abstract: Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare
arXiv:2610.04238v1 Announce Type: cross Abstract: Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This
arXiv:2610.06129v1 Announce Type: new Abstract: Behavioral foundation models (BFMs) have recently shown that a single humanoid policy can support diverse whole-body control, but extending such general
arXiv:2610.03983v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial convex losses and constraints (mathsf{COCO}). At each round (tin[T]), a learner selects
arXiv:2610.05922v1 Announce Type: cross Abstract: Evaluating the causal effect of new features is a central goal for online platforms. While recent literature addresses limited testing traffic via cen
arXiv:2610.06306v1 Announce Type: new Abstract: General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodi
arXiv:2610.06850v1 Announce Type: cross Abstract: Captured human-object interactions provide rich supervision for humanoid loco-manipulation, but they are sparse, heterogeneous, and not directly execu
Investors pattern matching on old movies is going to lead to a recession. There is no network effect here and no reason to think that large language models will be anything other than a brutal commodi
arXiv:2610.05608v1 Announce Type: new Abstract: We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video
arXiv:2610.04297v1 Announce Type: cross Abstract: Latent safety filters certify safety on a learned low-dimensional representation of the state, enabling constraints that resist analytic description.
arXiv:2610.05677v1 Announce Type: new Abstract: Multi-robot imitation learning, particularly in settings where visuomotor policies are deployed in a communication-free, onboard decentralised style, re
arXiv:2610.06397v1 Announce Type: new Abstract: We propose MOSEL (Multi-Objective Stackelberg Efficient Learning), a framework for a posteriori multi-objective optimization (MOO) in deep neural networ
arXiv:2610.06844v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the
arXiv:2610.06671v1 Announce Type: new Abstract: Small language models are often post-trained as students on reasoning traces from stronger teacher models to efficiently learn new skills. However, toke
arXiv:2610.05200v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) of large language models (LLMs) has demonstrated the ability to improve reasoning capabilities while preserving previ
arXiv:2510.18643v3 Announce Type: replace Abstract: Control Barrier Functions (CBFs) can provide provable safety guarantees for dynamic systems. However, finding a valid CBF for a system of interest i
arXiv:2610.06226v1 Announce Type: cross Abstract: Prior audio-visual self-supervised learning methods rely on mechanisms such as EMA target encoders, prediction heads, reconstruction decoders, and con
arXiv:2610.04744v1 Announce Type: new Abstract: When a team of robots delegates planning and mutual trust to LLM agents, a single compromised robot can corrupt the shared outcome. We study this threat
arXiv:2610.06052v1 Announce Type: new Abstract: Three-dimensional (3D) left ventricular (LV) reconstruction from sparse cardiac magnetic resonance (CMR) imaging remains challenging due to inter-slice
arXiv:2610.05195v1 Announce Type: new Abstract: The next generation of multimodal research agents must reason over long-lived research histories rather than short model completions. During a single ta
arXiv:2610.06195v1 Announce Type: cross Abstract: Learned feature representations in neural networks often contain structure beyond that directly used by the final task output. We study this structure
arXiv:2610.04036v1 Announce Type: new Abstract: Vision Transformers (ViTs) have shown strong performance in volumetric segmentation, but their effectiveness on clinical CT is limited by an isotropic E
arXiv:2602.06017v2 Announce Type: replace Abstract: Video fusion aims to integrate complementary information from multiple source videos while preserving temporal consistency. Effective modeling of te
arXiv:2610.06510v1 Announce Type: new Abstract: When searching for an object, people choose their next move by considering both likely target locations and places already explored. The current view ca
arXiv:2610.03830v1 Announce Type: new Abstract: In partially observable Markov decision processes, the optimal policy generally depends on the history of observations and past actions. Asymmetric acto
arXiv:2610.06830v1 Announce Type: cross Abstract: Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent me
arXiv:2610.06342v1 Announce Type: new Abstract: While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited token-lev
arXiv:2610.05252v1 Announce Type: new Abstract: Diffusion-based dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven diffusion models prioritize density approxima
arXiv:2502.02607v2 Announce Type: replace Abstract: The inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties. While traditiona
arXiv:2610.06120v1 Announce Type: new Abstract: Large learning rates can qualitatively change the trajectory of neural network training, often pushing optimization into regimes far from classical grad
arXiv:2508.15374v3 Announce Type: replace Abstract: Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of
arXiv:2610.06210v1 Announce Type: new Abstract: Autoregressive generation is natural for language, where predicted tokens can be directly reused as the next prediction state, but trajectory forecastin
arXiv:2610.04914v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current
arXiv:2610.05882v1 Announce Type: cross Abstract: Learning from human demonstrations is a reliable way to teach robots new tasks, but the gains from each additional demonstration shrink as the policy
arXiv:2610.05542v1 Announce Type: new Abstract: Control barrier functions are an effective model-based tool to formally certify the safety of a system. However, transferring their theoretical guarante
arXiv:2502.06359v3 Announce Type: replace Abstract: Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This
arXiv:2610.05872v1 Announce Type: new Abstract: A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data oft
arXiv:2610.04067v1 Announce Type: new Abstract: In this paper, we unravel the effect of different decoder architectures on the interpretability of the latent space of the Physically Recurrent Neural N
arXiv:2610.05338v1 Announce Type: new Abstract: Hierarchical reinforcement learning uses temporally extended subtasks for exploration, yet committing to their execution can restrict both deployment an
arXiv:2610.06096v1 Announce Type: new Abstract: In self-supervised learning, a third modality should improve, or at least preserve, performance. Across nine image-text-tabular datasets, we show that i
arXiv:2610.04249v1 Announce Type: new Abstract: Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or prec
arXiv:2610.04937v1 Announce Type: cross Abstract: Level-K reasoning generates a hierarchy of policies specialized to opponents with different reasoning levels. When an opponent's level is unknown, a c
arXiv:2610.05070v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiab
arXiv:2610.04765v1 Announce Type: new Abstract: In this paper, we develop a method that enables bimanual dexterous hands to manipulate articulated objects with a high success rate without suffering fr
arXiv:2610.05122v1 Announce Type: new Abstract: In recent years, Unmanned Aerial Vehicles (UAVs) or drones have been increasingly adopted in urban environments for applications such as parcel delivery
arXiv:2603.13663v2 Announce Type: replace Abstract: The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-atten
arXiv:2610.04659v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies commonly learn action chunks through a fixed left-to-right (LTR) factorization, although the same expert traject
arXiv:2610.04616v1 Announce Type: cross Abstract: A vision--language--action (VLA) policy can complete complex tasks while ignoring the evidence that should determine its actions. An object held near
arXiv:2610.04997v1 Announce Type: new Abstract: We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions
arXiv:2610.05959v1 Announce Type: new Abstract: Recent neural power-flow solvers, including emerging foundation models, achieve accurate voltage predictions, yet such accuracy does not necessarily imp
arXiv:2610.04850v1 Announce Type: new Abstract: Protein binding prediction is central to target identification, therapeutic binder design, and large scale screening, yet remains challenging because bi
arXiv:2604.01142v2 Announce Type: replace-cross Abstract: Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test condi
arXiv:2601.22891v3 Announce Type: replace Abstract: Linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks in multi-task reinforcement lea
arXiv:2610.04638v1 Announce Type: new Abstract: Actor-critic methods reuse past experience to improve sample efficiency. However, historical data are typically regarded as off-policy samples for the c
arXiv:2610.04162v1 Announce Type: new Abstract: Selecting the best k items out of m candidates is a critical component of modern large language model systems, such as document selection in Retrieval-A
arXiv:2610.04928v1 Announce Type: new Abstract: This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to wh
arXiv:2610.04920v1 Announce Type: new Abstract: Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This require
arXiv:2610.04913v1 Announce Type: new Abstract: World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually p
arXiv:2610.06266v1 Announce Type: new Abstract: Freeway on-ramp merges are major sources of congestion, causing significant economic and environmental costs. While Deep Reinforcement Learning (DRL) of