HuggingFace
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demons...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models....
HuggingFace
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supp...
HuggingFace
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specif...
GitHub
[GitHub] Leonxlnx/taste-skill
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop（⭐94247）
HuggingFace
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding...
HuggingFace
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expen...
HuggingFace
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vi...
HuggingFace
Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It...
HuggingFace
Incremental Open-Ended Deep Research with Structured Harness
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for...
HuggingFace
Pumpire: Unified Benchmark for Metric Distance Estimation
We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image...
HuggingFace
Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they ...