Search: “safety”

arXiv:2610.12710v1 Announce Type: new Abstract: Long-horizon manipulation requires robots to retain task-relevant history while revising conclusions no longer supported by physical evidence. Retaining

arXiv:2610.12781v1 Announce Type: new Abstract: Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only N s

arXiv:2610.13516v1 Announce Type: cross Abstract: Runtime failure monitors for robot policies are typically evaluated by how accurately they distinguish failed from successful executions. Yet an accur

arXiv:2610.13205v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on t

arXiv:2610.12822v1 Announce Type: new Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with

arXiv:2610.13438v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and to

arXiv:2602.00183v2 Announce Type: replace-cross Abstract: Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the perva

arXiv:2610.13912v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model

arXiv:2610.13207v1 Announce Type: new Abstract: Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive pattern

arXiv:2610.13157v1 Announce Type: new Abstract: Reinforcement learning (RL) for search agents often suffers from evidence fabrication, a failure mode where agents bypass external information (E_{ext})

arXiv:2610.13945v1 Announce Type: new Abstract: A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables.

arXiv:2610.13238v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while ex

arXiv:2610.12734v1 Announce Type: cross Abstract: Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models. Ho

Sure does look like @GavinSBaker is “suggesting that public companies are materially inflating their remaining performance obligations”. yet another way the Ai industry is trying to con retail investo

arXiv:2610.12939v1 Announce Type: cross Abstract: Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. However, existing speculative deco

arXiv:2610.12877v1 Announce Type: new Abstract: Agile and reliable navigation is a core capability for embodied robots navigating complex spatial constraints and dynamic interactions. However, a singl

arXiv:2610.13237v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn by predicting teacher representations of masked regions from visible context. Point prediction

arXiv:2610.13711v1 Announce Type: new Abstract: Generative Flow Networks (GFlowNets) learn policies that sample discrete objects in proportion to a positive reward. They are trained by minimizing bala

arXiv:2610.12851v1 Announce Type: cross Abstract: This work studies an entropy-based estimator of Kullback-Leibler (KL) divergence constructed from normalized importance weights. We prove a universal

arXiv:2610.13692v1 Announce Type: cross Abstract: Standard Policy Gradient (PG) algorithms suffer from high estimation variance because they rely on Monte Carlo updates. While off-policy variance redu

arXiv:2610.13252v1 Announce Type: cross Abstract: Can a vision model learn what words mean from pixels alone? We show that the two largest DINOv3 vision transformers organize words rendered in images

arXiv:2610.12733v1 Announce Type: new Abstract: Indoor navigation to task-relevant targets remains difficult when the target is small, occluded, or visually indistinct. Meanwhile, smart appliances, mo

arXiv:2610.12832v1 Announce Type: new Abstract: Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key cha

We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those

arXiv:2610.13247v1 Announce Type: cross Abstract: Open audio-language models are used as judges of generated music: given a clip and its text prompt, the model rates the clip, and the judge is validat

arXiv:2610.12995v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introdu

arXiv:2610.13404v1 Announce Type: new Abstract: Linear models can predict well in complex domains even when underlying mechanisms are nonlinear. We argue that this can occur because the complexity of

arXiv:2610.13687v1 Announce Type: cross Abstract: Audio-visual dataset distillation aims to synthesize a small dataset from a large paired audio-visual dataset, while nearly preserving the training ut

arXiv:2610.13786v1 Announce Type: cross Abstract: Discrete graph diffusion models (GDMs) corrupt the graph structure by adding noise independently to nodes and edges under a Markovian noise model. In

Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format rewards, and other GRPO tips & tricks. 00:00 Introduction an

arXiv:2610.12465v1 Announce Type: cross Abstract: General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (R

arXiv:2610.12113v1 Announce Type: cross Abstract: Off-policy actor--critic methods control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, reg

arXiv:2610.11140v1 Announce Type: cross Abstract: Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagn

arXiv:2610.11354v1 Announce Type: new Abstract: Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence. Written rules can leave gaps in d

arXiv:2610.11724v1 Announce Type: new Abstract: Multimodal meme understanding is increasingly used to analyze socially sensitive content, yet existing models often exhibit biased behavior when interpr

arXiv:2610.11060v1 Announce Type: cross Abstract: World-action models have recently improved autonomous driving by jointly learning future scene prediction and trajectory generation. Most existing app

arXiv:2603.08706v2 Announce Type: replace Abstract: Imitation learning (IL) teaches language-model agents to reproduce expert actions but not to distinguish them from plausible mistakes. Self-reflecti

Automated evals can score every agent session, but they do not automatically reflect what your team considers a good outcome. That takes human judgment. The post Alignment is a human-AI workflow: how

arXiv:2610.11213v1 Announce Type: new Abstract: Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasing

arXiv:2610.12083v1 Announce Type: cross Abstract: LLM-as-a-Judge is the standard paradigm for NLP evaluation, yet its systemic reliability remains poorly understood despite being widely treated as a d

Emily Forlini / Fortune: Anthropic is setting up a “presidential engagement” program for the 2028 US elections that will offer AI policy education to candidates in both parties — Anthropic is setting

arXiv:2610.12386v1 Announce Type: cross Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.

Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su

arXiv:2610.11792v1 Announce Type: cross Abstract: We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and pr

arXiv:2610.11128v1 Announce Type: new Abstract: A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model

arXiv:2607.10169v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip ar