HuggingFace
Pristine Models
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that sho...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Scaling Verifiable Environments for Long-horizon Work Agents
Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training envir...
HuggingFace
Who to Trust in Multi-Robot Systems: Joint Robot and Object Hypothesis Trust Inference via Neural-Symbolic Cross-Validation
Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing an...
HuggingFace
Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments
Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often...
HuggingFace
Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decod...
HuggingFace
Model-Based Online Decision Making via Generative Trajectory Planning
Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods re...
arXiv
Self-Evolving Agent Harness
Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable ...
arXiv
Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs
Pre-trained Large Language Model (LLMs) are effective on many tasks in zero-shot and few-shot settings. For machine t...
arXiv
Read the Room Before Your Model Generates
Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their out...
arXiv
RoboSimStudio: An Interactive Toolkit for Rapid Real2Sim of Robot Manipulation Tasks
It is difficult to accurately model the physics of the interaction between a robot and the objects it manipulates, in...
arXiv
Fast Rates for Offline Q-Learning with KL Regularization
This paper investigates offline Q-learning for finite-horizon Markov decision processes with Kullback-Leibler (KL) re...
arXiv
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study ...