Knowledge catalogue
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:2610.05677v1 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: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:2610.05882v1 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:2610.05872v1 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: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
Really nice paper on harness-aware distillation for small language model agents. (bookmark it) It's a super interesting distillation framework for small language model agents that are deployed with a
arXiv:2610.06010v1 Announce Type: new Abstract: Ultrasound visual servoing is essential for autonomous robotic ultrasound, yet 6-DoF probe control from 2D B-mode images remains challenging due to limi
arXiv:2610.05151v1 Announce Type: new Abstract: Visuomotor policies can execute familiar tasks yet lack the corrective behavior needed after their own mistakes. We present a framework for recursive se
arXiv:2610.05768v1 Announce Type: cross Abstract: We ask: given a retrieved source audio S and a separate reference audio R, can we synthesize novel audio Y out of this pair (S,R) such that Y remains
arXiv:2610.06041v1 Announce Type: new Abstract: Deep learning has advanced chest X-ray (CXR) diagnosis, yet demographic biases in learned representations may contribute to performance disparities acro
arXiv:2610.06648v1 Announce Type: cross Abstract: We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference
arXiv:2610.05833v1 Announce Type: cross Abstract: Long-running agents repeatedly call an LLM while retaining most of their document window, evicting old documents, and appending new ones. These rollin
arXiv:2610.04882v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model on self-generated trajectories, but transmitting dense teacher distributions across long reasoning t
AWS invests in tools that help customers align with international standards for responsible AI governance. In this post, we explore the AI system impact assessment: what it is, how it improves enterpr
arXiv:2610.04272v1 Announce Type: new Abstract: Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-mode
arXiv:2610.05063v1 Announce Type: new Abstract: Multi-step revealing can make off-policy evaluation tractable under memoryless logging. With history-dependent logging, state decodability and target-re
arXiv:2610.04054v1 Announce Type: new Abstract: Recent advances in robot learning have enabled generalist control policies capable of completing a wide range of tasks. However, their performance degra
arXiv:2509.25604v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have shown strong reasoning capabilities, yet further improving them typically requires costly post-tr
arXiv:2610.04681v1 Announce Type: new Abstract: Vision-language-action (VLA) and world-action models (WAMs) often degrade under out-of-distribution task variations despite retaining partial task capab