Knowledge catalogue
arXiv:2610.01399v1 Announce Type: new Abstract: Among on-policy deep reinforcement learning methods, Proximal Policy Optimization (PPO) has become the de facto standard, due to its consistently strong
arXiv:2610.01249v1 Announce Type: new Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffect
arXiv:2610.00729v1 Announce Type: new Abstract: This paper explores a reward-based policy to achieve zero-shot transfer between source and target environments with completely different observation spa
arXiv:2610.00715v1 Announce Type: new Abstract: Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are unce
arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from
arXiv:2610.00524v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often struggle to generalize to skill combinations absent from their fine-tuning demonstrations, even when every c
arXiv:2610.00797v1 Announce Type: new Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool cal
arXiv:2610.00758v1 Announce Type: new Abstract: By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluation of agents under modified environments. Such tra
arXiv:2610.02092v1 Announce Type: cross Abstract: Data selection is critical for training large language models on massive and heterogeneous corpora. Meta-learning for Training-data Selection offers a
arXiv:2610.00686v1 Announce Type: new Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene
arXiv:2610.00903v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using supervision derived from their own samples. This makes t
arXiv:2610.00838v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error c
arXiv:2610.00262v1 Announce Type: cross Abstract: Selective intent routing allows an assistant to act on reliable predictions while deferring uncertain requests. Standard confidence scores primarily r
arXiv:2502.04892v2 Announce Type: replace Abstract: Learning robust representations from functional magnetic resonance imaging (fMRI) is fundamentally challenged by the temporal irregularity and noise
arXiv:2610.00157v1 Announce Type: cross Abstract: Symmetry reduces the capacity of a quantum learning model, but the imposed group must match both the measured information and the label transformation
arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, r
Terence Tao on today's AI: 'you look at how it's done and it doesn't feel like intelligence, like its some trick, you just cobble together these neural networks and we ran some algorithm and we were l
arXiv:2610.00132v1 Announce Type: cross Abstract: Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar successor states can accompany differently authoriz
arXiv:2610.00332v1 Announce Type: cross Abstract: Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current a
arXiv:2610.00899v1 Announce Type: cross Abstract: Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with sta
arXiv:2610.01826v1 Announce Type: cross Abstract: Collaborative embodied artificial intelligence (CEAI) enables multiple physical agents to perceive, reason, and act cooperatively in dynamic environme
arXiv:2610.00575v1 Announce Type: new Abstract: A common approach to world-model simulation for vision-language-action (VLA) systems is to predict future RGB observations and then re-encode them into
arXiv:2610.01005v1 Announce Type: cross Abstract: As artificial intelligence is increasingly deployed, algorithmic unfairness has raised growing concerns and intensified demands for transparent fairne
arXiv:2610.00438v1 Announce Type: new Abstract: Humanoid whole-body manipulation has advanced rapidly, enabling policies to coordinate locomotion, posture, bimanual interaction, and dexterous hand mov
arXiv:2610.00590v1 Announce Type: cross Abstract: An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability t
arXiv:2610.01566v1 Announce Type: new Abstract: Practical Reinforcement Learning (RL) algorithms learn to solve Markov Decision Processes (MDPs) through iterative policy improvement in the presence of
arXiv:2610.01531v1 Announce Type: new Abstract: Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-m
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference object
arXiv:2610.01282v1 Announce Type: new Abstract: The rapid evolution of Intelligent Transportation Systems and Logistics (ITS&L) has become a cornerstone of the modern social economy, relying heavily o
arXiv:2610.01890v1 Announce Type: cross Abstract: Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. Howe
arXiv:2510.23576v2 Announce Type: replace-cross Abstract: Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following lo
Michael Shepard / Bloomberg: US authorities arrest a California man suspected of smuggling $300M+ worth of restricted Nvidia AI chips to China via Malaysia and Singapore from 2023 to 2024 — By continu
arXiv:2610.01718v1 Announce Type: new Abstract: Quantum federated learning (QFL) has emerged as a promising approach for collaboratively training compact quantum neural networks (QNNs) over distribute
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics
arXiv:2601.12758v2 Announce Type: replace-cross Abstract: As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preferenc
arXiv:2610.00202v1 Announce Type: cross Abstract: Several recent pipelines build RLVR training data by masking a span of real corpus text and asking a language model to invent plausible wrong answers
arXiv:2610.00372v1 Announce Type: new Abstract: Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Y
arXiv:2610.01149v1 Announce Type: cross Abstract: Given a fixed set of pending deletion requests, retraining from scratch after each request is prohibitive, so a prescribed request-wise policy process
arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen
arXiv:2610.00404v1 Announce Type: new Abstract: Aerial grasp-and-lift tasks require whole-body coordination across approach, acquisition, and lifting under partial target observations. Early approach
arXiv:2601.23135v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is t
arXiv:2610.01742v1 Announce Type: cross Abstract: Equipping artificial agents with spatial intelligence requires a comprehensive generative prior over the dynamic 3D world. We propose World Motion Mod
arXiv:2602.14929v2 Announce Type: replace Abstract: Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challeng
arXiv:2610.01097v1 Announce Type: new Abstract: End-to-end research agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is struct
arXiv:2606.14597v2 Announce Type: replace Abstract: Transformer-based neural operators have shown remarkable performance for approximating solution operators of partial differential equations on compl
arXiv:2609.39322v1 Announce Type: new Abstract: Robot policies are usually trained for one task, one body and one visual environment, and generalize poorly beyond these conditions. Whether a nervous s
arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of hu
Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can
arXiv:2609.39025v1 Announce Type: new Abstract: Fairness assessment in algorithmic decisions that affect individuals, such as credit scoring, often relies on parity measures calculated at the aggregat
arXiv:2609.38421v1 Announce Type: new Abstract: Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensu
arXiv:2606.13739v2 Announce Type: replace-cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. Howev
arXiv:2609.40111v1 Announce Type: new Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and th
arXiv:2609.38755v1 Announce Type: new Abstract: A wide range of approaches have been developed for camera pose estimation, including correspondence-based methods, end-to-end pose regression, and recen
arXiv:2609.38379v1 Announce Type: new Abstract: Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for prev
arXiv:2609.38645v1 Announce Type: cross Abstract: Models are usually aligned based on their observed outputs, using demonstrations, preference data, or reward signals. These objectives reward response
arXiv:2609.38902v1 Announce Type: new Abstract: Augmenting small concurrent studies with external or historical cohorts is attractive in drug development, where enrollment is slow, follow-up is expens
arXiv:2609.38504v1 Announce Type: cross Abstract: Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components in
arXiv:2503.10118v3 Announce Type: replace-cross Abstract: The sim-to-real gap remains a critical challenge in robotics, hindering the deployment of algorithms trained in simulation to real-world syste