HuggingFace
Training the Whole Agent, Not Just the Model
Training coding agents typically updates the policy while keeping the harness fixed. During training, trajectories re...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks
Bimanual manipulation with dexterous hands has attracted growing attention in research on robotic action models. Howe...
HuggingFace
Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
A fine-tuned Vision-Language-Action (VLA) policy can easily place the alphabet soup in the basket on command, just as...
HuggingFace
What Makes a Good Symbol for Hybrid Discrete-Continuous Planning?
The physical world has continuous state and action spaces, yet robot planning often benefits from hybrid discrete-con...
HuggingFace
ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed samplin...
HuggingFace
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as ...
arXiv
Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning
Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) o...
arXiv
SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images
Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult....
arXiv
Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation
Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every toke...
arXiv
What Do RTL Repair Benchmarks Actually Measure?
RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we constr...
arXiv
Evolving Agent Interfaces
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when...
arXiv
Turning TS2Vec into a Foundation Model for Time Series Classification
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is desi...