Knowledge catalogue
arXiv:2610.18690v1 Announce Type: new Abstract: Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a cohe
arXiv:2610.17397v1 Announce Type: new Abstract: On-policy distillation (OPD) is a post-training approach for large language models (LLMs) that enables a student model to learn a teacher model's distri
arXiv:2610.18457v1 Announce Type: cross Abstract: Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an a
arXiv:2610.16502v1 Announce Type: new Abstract: Discovering and disambiguating entities from multimodal and heterogeneous data is a key challenge in discovery science, where relevant knowledge is ofte
arXiv:2610.14810v1 Announce Type: cross Abstract: Enterprise AI agents can execute altered versions of approved actions, concurrently reuse the same permission, or retry operations whose responses wer
arXiv:2512.19605v2 Announce Type: replace-cross Abstract: Breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations
arXiv:2610.15756v1 Announce Type: new Abstract: Yoshikawa's Manipulability Index is generally used as a classical measure to define an optimal morphology of a manipulator. However, any such optimizati
arXiv:2610.16940v1 Announce Type: new Abstract: Nearest neighbor search algorithms are widely used and have a long history, but we find that key implementation details are seldom reviewed in articles
arXiv:2610.17440v1 Announce Type: new Abstract: Dual-encoder vision-language models systematically fail at negation, scoring ''a cat without a dog'' nearly identically to ''a cat with a dog.'' We show
arXiv:2610.16547v1 Announce Type: cross Abstract: Sentence representation learning is still an open challenge in Natural Language Processing. In this work, we propose a new self-supervised framework f
arXiv:2610.18684v1 Announce Type: cross Abstract: Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing w
arXiv:2610.18669v1 Announce Type: cross Abstract: Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrar
arXiv:2607.18760v2 Announce Type: replace Abstract: In legged locomotion, divergent components of motion (DCMs) have emerged as characteristic states for balance control. They isolate the unstable mod
arXiv:2610.14448v1 Announce Type: new Abstract: Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail gen
arXiv:2610.18654v1 Announce Type: new Abstract: Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants in
arXiv:2610.14020v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution. Ideally, AI-generate
arXiv:2610.16398v1 Announce Type: new Abstract: Robot learning has undergone significant advancements in the domain of compliant control and robotic assembly. The development of novel methodologies ha
arXiv:2610.13959v1 Announce Type: new Abstract: In e-commerce advertising, ad platforms typically fail to model the externalities among advertisers when making optimization decisions: an advertiser's
arXiv:2610.18053v1 Announce Type: cross Abstract: General-purpose robot manipulation policies learn short-horizon skills effectively, but degrade rapidly on long-horizon tasks. Existing benchmarks can
arXiv:2610.17870v1 Announce Type: new Abstract: Robust proprioceptive state estimation is crucial for legged robots, particularly in challenging environments where exteroceptive sensors are unreliable
arXiv:2610.16634v1 Announce Type: cross Abstract: Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing close
arXiv:2610.13858v2 Announce Type: replace Abstract: Modern vision and language models process ever longer token sequences, and reducing them is the main lever on downstream cost. Token compression, ho
arXiv:2610.18555v1 Announce Type: new Abstract: In this paper, we study the last-iterate convergence of clipped stochastic gradient descent under heavy-tailed noise. We assume that the stochastic grad
arXiv:2610.15571v1 Announce Type: cross Abstract: In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning. A key feature
arXiv:2610.15836v1 Announce Type: cross Abstract: When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category
arXiv:2610.14228v1 Announce Type: new Abstract: Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local
arXiv:2610.14290v1 Announce Type: new Abstract: The inner workings of deep neural networks are still not well understood. The information bottleneck framework, which characterizes deep networks by the
arXiv:2610.18763v1 Announce Type: new Abstract: Online learning platforms are increasingly deploying AI assistants to provide personalized, on-demand tutoring. These can leverage infographics to commu
arXiv:2610.17697v1 Announce Type: new Abstract: AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck. A learned verifier could
arXiv:2610.16720v1 Announce Type: new Abstract: Existing benchmarks for GUI agents primarily focus on increasing task difficulty by extending task horizons. Besides, enabling agents to explore unfamil
arXiv:2610.14537v1 Announce Type: cross Abstract: Particle-in-cell (PIC) simulation is indispensable for modeling beam dynamics in particle accelerators, but its computational cost limits many-query w
arXiv:2610.14219v1 Announce Type: new Abstract: Softmax attention in Transformers suffers from quadratic complexity in sequence length, making it impractical for long-context applications. Linear atte
arXiv:2610.18154v1 Announce Type: new Abstract: We study learning an unknown element g of a group acting with finite orbits on a countable set, from examples (x,gx). After a sample on A, the consisten
arXiv:2610.16535v1 Announce Type: cross Abstract: The idea that learning is closely tied to compression has long served as both a powerful principle and, at times, an informal analogy across machine l
arXiv:2610.16644v1 Announce Type: new Abstract: Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-station
arXiv:2610.17956v1 Announce Type: cross Abstract: We study parameter estimation when each sample from a continuous parametric distribution is accompanied by a binary quality label governed by the same
arXiv:2610.14848v1 Announce Type: new Abstract: Synthesizing believable 4D hand-object grasping sequences is important for character animation, extended reality, and embodied agents. Grasping requires
arXiv:2604.03392v2 Announce Type: replace-cross Abstract: This paper investigates whether it is more effective to condition reinforcement learning policies across changing dynamics using standard inpu
arXiv:2610.17804v1 Announce Type: cross Abstract: How can language models learn to optimize physical designs through experience? We introduce FracLearn, an experience-abstraction-generalization framew
arXiv:2610.16537v1 Announce Type: new Abstract: In a variety of multi-agent and physical environments, an element's update depends strongly on a few other elements and weakly on many, and both the ide
arXiv:2610.16645v1 Announce Type: new Abstract: Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations,
arXiv:2610.15891v1 Announce Type: new Abstract: Predictive video representations do not by themselves specify how a multimodal system should handle missing sensors. We transfer frozen V-JEPA2 features
arXiv:2610.14246v1 Announce Type: new Abstract: Variance-based methods recover a Gaussian linear structural equation model (SEM) with equal or suitably constrained error variances, either by recursive
arXiv:2610.16419v1 Announce Type: cross Abstract: Classifier-Free Guidance (CFG) with guidance scale gamma is commonly motivated by the omega-powered conditional distribution obtained by setting omega
arXiv:2610.16884v1 Announce Type: new Abstract: Continuous symmetry discovery is typically formulated as a separate estimation problem for each function or dataset. We instead investigate whether the
arXiv:2610.18456v1 Announce Type: new Abstract: AI-based cellular perturbation prediction is essential to accelerate drug discovery and therapeutic identification. However, perturbation-specific signa
arXiv:2610.16522v1 Announce Type: cross Abstract: Safe robot navigation in unknown, dynamic environments requires more than geometric collision checking: a robot still far from an obstacle may be unab
arXiv:2610.17750v1 Announce Type: new Abstract: Robotic assistance for human mobility could benefit care recipients and reduce caregiver burden during physically demanding tasks such as Sit-to-Stand (
arXiv:2510.27114v2 Announce Type: replace-cross Abstract: Generative BC policies model expert action distributions well, but they do not explicitly reason about what scene a candidate action would pro
arXiv:2610.15486v1 Announce Type: new Abstract: Robotic systems for lunar surface operations must act autonomously and preserve their own integrity in an environment where failures are unrecoverable a
arXiv:2603.01786v2 Announce Type: replace Abstract: In this paper, we present a novel learning framework for finding shortest paths in graphs utilizing Generative Flow Networks (GFlowNets). First, we
arXiv:2610.18725v1 Announce Type: new Abstract: A transformer trained on sequences whose source parameters are drawn afresh each time can learn only what the sequences share: the source family and its
arXiv:2610.16299v1 Announce Type: new Abstract: Video anomaly understanding (VAU) aims to generate language-level interpretations of anomalous events in long videos, requiring visual evidence that sup
arXiv:2606.12475v2 Announce Type: replace Abstract: Human-robot collaboration (HRC) combines the complementary strengths of humans and robots to improve task efficiency. However, many existing collabo
arXiv:2610.16948v1 Announce Type: new Abstract: Convex relaxations make nonconvex optimization tractable by replacing hard nonconvex problems with convex surrogates that give valid bounds. Yet their d
arXiv:2610.16966v1 Announce Type: new Abstract: Symbolic regression (SR) seeks explicit equations that explain observed data, and recent methods increasingly employ large language models (LLMs) and ag
arXiv:2610.17399v1 Announce Type: new Abstract: Continuous monitoring of generative AI systems requires detecting distribution shifts in the unstructured data they ingest and generate. Existing monito
arXiv:2610.14456v1 Announce Type: new Abstract: Looped transformers reuse a single block across iterations, raising a natural question: how far can a block trained at one depth be safely extrapolated
arXiv:2610.14302v1 Announce Type: new Abstract: Humans and animals do not learn vision from a fixed set of data: they move, interact, and learn from the visual consequences of their actions. Motivated