Knowledge catalogue
arXiv:2610.03185v1 Announce Type: new Abstract: On-policy distillation (OPD) has become an important approach to language model post-training. However, despite its performance gains, OPD can also coll
arXiv:2610.02697v1 Announce Type: cross Abstract: Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructi
arXiv:2610.02952v1 Announce Type: cross Abstract: Test-driven development gives AI coding agents executable requirements for implementing software. Because these agents can adapt their implementations
arXiv:2610.03055v1 Announce Type: new Abstract: A coding agent can earn a passing grade by fixing its code, or by deleting the test that exposes the bug. Detecting such reward hacking requires recogni
arXiv:2610.02858v1 Announce Type: new Abstract: Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is di
arXiv:2610.02920v1 Announce Type: new Abstract: Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace ma
arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation do
arXiv:2610.02594v1 Announce Type: cross Abstract: Numerical measurements capture how a system behaves, but often leave the meanings of its variables unspecified. Some variables are measured but never
arXiv:2610.02224v1 Announce Type: new Abstract: Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical R
arXiv:2610.02496v1 Announce Type: new Abstract: In the UK, public healthcare staff report turning to machine translation (MT) - predominantly Google Translate (GT) - to communicate with patients acros
arXiv:2610.03641v1 Announce Type: new Abstract: Masked discrete diffusion models offer a promising alternative to autoregressive generation, but iterative sampling can be costly, and intractable seque
arXiv:2610.02626v1 Announce Type: new Abstract: Vision-language-action (VLA) models increasingly incorporate intermediate reasoning to improve robotic manipulation, yet existing approaches primarily r
arXiv:2610.02520v1 Announce Type: cross Abstract: We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constrain
arXiv:2610.02302v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) can be vulnerable to jailbreak attacks in which harmful intent is obscured through composition
arXiv:2610.02897v1 Announce Type: new Abstract: A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral: what is kept is chosen against some notion of
arXiv:2610.03414v1 Announce Type: cross Abstract: Consistency models (CMs) have become a leading approach for generating high-quality samples in few steps. However, adding steps can improve or degrade
arXiv:2610.02300v1 Announce Type: new Abstract: Training-free safeguards for text-to-image generation often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, appl
arXiv:2610.03388v1 Announce Type: new Abstract: Video is an abundant, inexpensive source of human motion data that is rich in extreme athletic behaviors. Making it usable for humanoid robots, however,
arXiv:2610.02586v1 Announce Type: new Abstract: A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carrie
arXiv:2610.02774v1 Announce Type: new Abstract: Long-form generators for music, motion and video produce sequences chunk by chunk, with each chunk generated by iterative denoising while rewards are de
arXiv:2610.02700v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal
arXiv:2610.02811v1 Announce Type: new Abstract: During contact-rich manipulation, interactions between a robot and its environment carry information about local geometry: a surface prevents penetratio
arXiv:2610.02437v1 Announce Type: cross Abstract: Why does supervised fine-tuning (SFT) lead to more forgetting than reinforcement fine-tuning (RFT), even when all teacher demonstrations are semantica
arXiv:2610.02703v1 Announce Type: new Abstract: On-policy distillation (OPD) improves large language model reasoning by training students on their own rollouts with dense token-wise supervision from t
arXiv:2610.03065v1 Announce Type: new Abstract: Learning control from action-free recordings is challenging because intervention effects are unobserved and policies may exploit errors in reconstructed
arXiv:2610.02525v1 Announce Type: new Abstract: Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because suc
arXiv:2610.02359v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-qual
arXiv:2610.03315v1 Announce Type: new Abstract: Trajectory evaluation is essential for improving the reliability of LLM-based agents, but production use makes it expensive to run repeatedly. Modern ag
arXiv:2610.03599v1 Announce Type: new Abstract: High-fidelity 3D head avatars have reached near-photorealistic quality. While recent methods enable text-driven manipulation, they struggle to provide f
arXiv:2610.03454v1 Announce Type: cross Abstract: Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test ti
arXiv:2606.13176v2 Announce Type: replace Abstract: Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical fo
arXiv:2610.02824v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requiremen
arXiv:2610.03480v1 Announce Type: new Abstract: Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive.
arXiv:2610.02662v1 Announce Type: new Abstract: Language-enabled robot systems increasingly combine semantic-graph planning with temporal-logic safety monitors. We investigate a trace-completeness ass
arXiv:2610.02418v1 Announce Type: cross Abstract: Modern large language models (LLMs) are trained on massive, largely unfiltered datasets, including content scraped from nearly every accessible websit
arXiv:2610.02898v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have achieved remarkable advances in robotic manipulation, yet their zero-shot generalization under out-of-distribut
arXiv:2610.03476v1 Announce Type: cross Abstract: Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and
arXiv:2512.21439v2 Announce Type: replace-cross Abstract: A key question in current AI alignment research is how to make AI algorithms learn moral values. Because human morality is highly context-depe
arXiv:2606.18717v2 Announce Type: replace-cross Abstract: Turkish is agglutinative: meaning is carried by morphemes, yet the subword tokenizers that drive modern language models split words by corpus
arXiv:2610.02505v1 Announce Type: cross Abstract: Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient e
My dice are conscious!! Shut down every casino now, for slave-trading!! Either that or read what Congressman Lieu is trying to tell you. [There are actually multiple sources of randomness in LLMs, inc
arXiv:2610.03391v1 Announce Type: new Abstract: World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotate
arXiv:2610.02339v1 Announce Type: cross Abstract: Robot demonstrations may contain useful behavior even when individual episodes are inefficient or unsuccessful. Trajectory stitching offers a way to c
arXiv:2610.02370v1 Announce Type: cross Abstract: Massively parallel GPU simulators train multi-robot policies in thousands of environments, and many fleets use private Fifth-Generation (5G) networks,
arXiv:2610.03190v1 Announce Type: cross Abstract: Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is e
arXiv:2610.02985v1 Announce Type: new Abstract: Embodied agents interacting with the same physical process may maintain heterogeneous, asynchronous, and observer-relative representations. Rather than
arXiv:2610.03642v1 Announce Type: new Abstract: Success conditioning is a strategy for improving decision-making policies in stochastic environments; it updates a policy by increasing the probability
arXiv:2610.02632v1 Announce Type: new Abstract: As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintai
arXiv:2610.02781v1 Announce Type: cross Abstract: Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by s
arXiv:2512.01352v2 Announce Type: replace Abstract: Unsupervised and open-vocabulary 3D object detection have recently gained attention, particularly in autonomous driving, where reducing annotation c
arXiv:2610.03378v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) typically exhibit spectral bias, where some frequencies of the target function converge more slowly than others
arXiv:2610.03423v1 Announce Type: new Abstract: Reinforcement learning (RL) for Text-to-3D (T23D) generation requires optimization across multiple quality dimensions such as semantic alignment and tex
arXiv:2610.03047v1 Announce Type: new Abstract: Despite never being supervised on explicit 3D motion, large-scale text-to-video diffusion models synthesize realistic human motion in their generated vi
arXiv:2610.03667v1 Announce Type: new Abstract: Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploratio
arXiv:2610.03650v1 Announce Type: cross Abstract: Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to partici
arXiv:2610.02925v1 Announce Type: new Abstract: Safety monitors help safeguard language-model agents interacting with external tools and environments, but conservative monitoring can generate many fal
arXiv:2610.02303v1 Announce Type: new Abstract: Language models increasingly assist people with power-related requests, so systematic differences in whom they help could shift the distribution of powe
Powerful testimony from ex Google DeepMind researcher @Turn_Trout at NYC Hearing on AI, about how he tried to get Google to commit to AI safety, and how Google, sadly including Demis Hassabis, ultimat
arXiv:2610.03664v1 Announce Type: new Abstract: Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive para
arXiv:2610.02740v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental