Knowledge catalogue
arXiv:2607.17524v2 Announce Type: replace Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness predicti
arXiv:2508.05880v3 Announce Type: replace-cross Abstract: Understanding human emotions is central to user-facing AI applications, safety alignment, and the simulation of human behavior. As emotional s
arXiv:2610.08205v1 Announce Type: cross Abstract: Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-
arXiv:2610.07004v1 Announce Type: new Abstract: Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for s
arXiv:2610.08540v1 Announce Type: new Abstract: Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if alignment were one property. We treat it as a famil
arXiv:2610.07382v1 Announce Type: new Abstract: Robots are entering human spaces faster than we can establish when they deserve trust. We propose a framework for trustworthy physical AI that integrate
arXiv:2610.07089v1 Announce Type: cross Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request
arXiv:2610.08733v1 Announce Type: new Abstract: Language models provide a plug-and-play interface between humans and robots, but important challenges remain when speech, dialogue, fast interaction, an
arXiv:2610.07802v1 Announce Type: new Abstract: Bird monitoring in natural environments is challenging due to the small size of some species of birds relative to the scene, background clutter, variabi
arXiv:2610.07320v1 Announce Type: new Abstract: Multi-robot missions in infrastructure-denied environments frequently rely on reliable communication links between spatially separated locations. We pro
arXiv:2610.08555v1 Announce Type: new Abstract: Network pruning can reduce parameter redundancy in robotic policies. However, generic pruning criteria are tailored for image recognition tasks and comm
arXiv:2610.07358v1 Announce Type: new Abstract: Post-wildfire debris flows (PFDFs) are destructive sediment-laden hazards triggered when intense rainfall strikes recently burned terrain, destabilizing
arXiv:2610.08630v1 Announce Type: new Abstract: Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, us
arXiv:2610.07778v1 Announce Type: cross Abstract: Attributed graph clustering aims to discover node groups by jointly exploiting node attributes and graph topology, yet its unsupervised nature makes m
arXiv:2610.07640v1 Announce Type: new Abstract: State-of-the-art reinforcement learning agents are capable of outperforming human experts at games like chess, Go and StarCraft II. These agents do not
arXiv:2610.07767v1 Announce Type: cross Abstract: Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generatio
arXiv:2610.07355v1 Announce Type: cross Abstract: Video world models track objects they can see; we ask what they keep of objects they cannot. We hide an object from a frozen V-JEPA 2 predictor and co
arXiv:2610.06858v1 Announce Type: cross Abstract: This demo paper presents the conceptual foundations and the first steps towards implementation of a novel no-code solution for movement data analytics
arXiv:2610.07350v1 Announce Type: new Abstract: Long chain-of-thought reasoning increases sequential decoding cost while creating a growing history of potentially reusable continuations. We investigat
arXiv:2610.07859v1 Announce Type: new Abstract: Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fro
arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exi
arXiv:2603.05670v2 Announce Type: replace Abstract: When humans learn new manipulation skills, they are able to generalize these skills to new contexts and environments. In particular, when learning,
arXiv:2610.06902v1 Announce Type: new Abstract: Retrieval-augmented generation grounds language models in external context, but for long documents flat top-k retrieval can cluster on a single region a
arXiv:2610.07043v1 Announce Type: cross Abstract: Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and samp
arXiv:2610.07755v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges for automated AI evaluation. A common practice is to randomize prompt sequences and avera
arXiv:2610.08230v1 Announce Type: new Abstract: As video capture moves to handheld and edge devices, motion blur from camera shake has become a pervasive degradation that lowers perceptual quality and
arXiv:2610.07823v1 Announce Type: new Abstract: The AI CUP 2025 Precise Analysis of Table Tennis Smart Racket Data Competition introduced smart table tennis rackets that collect extensive player swing
arXiv:2610.07070v1 Announce Type: new Abstract: Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calli
arXiv:2610.08070v1 Announce Type: new Abstract: Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion
arXiv:2610.07503v1 Announce Type: cross Abstract: Two populations of graphs often have to be compared without any correspondence between their vertices, for instance when networks come from different
arXiv:2610.08277v1 Announce Type: cross Abstract: Deciding whether two samples come from the same distribution is a classical problem in statistics, and generative transport offers a new way to approa
arXiv:2610.07572v1 Announce Type: new Abstract: In-context learning (ICL) adapts frozen large multimodal models (LMMs) to new tasks from a few demonstrations (demos), but re-encodes them at every quer
arXiv:2610.07941v1 Announce Type: cross Abstract: Physically-based differentiable rendering enables gradient-based optimization of scene parameters by matching rendered images to measurements, but has
arXiv:2610.07570v1 Announce Type: new Abstract: In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism o
arXiv:2603.23184v2 Announce Type: replace-cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF), existing reward modeling methods largely rely on explicit feedback,
arXiv:2610.06974v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchma
arXiv:2610.08353v1 Announce Type: new Abstract: While graph neural networks (GNNs) have shown substantial promise in connectome-based diagnostic classification, deterministic models inevitably suppres
arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2603.16017v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across re
arXiv:2610.08379v1 Announce Type: new Abstract: Visual counting is commonly formulated as counting a single specified target, with a model receiving an image-specific exemplar, text query, or target c
arXiv:2610.07655v1 Announce Type: cross Abstract: Discrete diffusion models have emerged as a practically successful framework for generative modeling on discrete product spaces, yet their statistical
arXiv:2607.09985v2 Announce Type: replace Abstract: Object pose estimation is a fundamental problem in 3D vision. Although recent state-of-the-art approaches achieve strong performance, generalization
arXiv:2610.06938v1 Announce Type: new Abstract: Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed s
arXiv:2511.20471v3 Announce Type: replace Abstract: Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively und
arXiv:2610.07689v1 Announce Type: new Abstract: Vision-Language Models (VLMs) such as CLIP excel in global semantic alignment but often lack fine-grained perceptual capabilities. This hinders dense pr
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an en
arXiv:2610.07903v1 Announce Type: new Abstract: Adapting vision-language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing
arXiv:2610.08398v1 Announce Type: new Abstract: On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this i
arXiv:2610.08225v1 Announce Type: new Abstract: In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physi
arXiv:2610.08564v1 Announce Type: new Abstract: Tabular foundation models (TFMs) can classify the nodes of a graph without training on it, by reading node and neighborhood features as table rows next
arXiv:2610.07606v1 Announce Type: new Abstract: This paper establishes a theoretical framework for vertical adaptive layer skipping, proving three foundational results: (i) an Expected FLOPs formula (
arXiv:2610.07899v1 Announce Type: cross Abstract: Generative actors are transforming offline reinforcement learning (RL) by enabling expressive policy classes that model complex action distributions.
arXiv:2610.08677v1 Announce Type: new Abstract: Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly
arXiv:2512.13708v2 Announce Type: replace Abstract: Inferring interaction structure from steady-state observations is a central inverse problem when transient trajectories are unavailable. Here we for
arXiv:2610.08043v1 Announce Type: new Abstract: Ensuring safety in autonomous driving requires continuous map maintenance supported by reliable quality indicators. In this context, it is crucial to id
arXiv:2610.06962v1 Announce Type: cross Abstract: In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than re
arXiv:2610.07097v1 Announce Type: new Abstract: Experimental studies of generative AI in education mostly report average effects, yet field evidence shows that AI can narrow attainment gaps or widen t
arXiv:2610.08761v1 Announce Type: new Abstract: Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constr