HuggingFace
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank corr...
HuggingFace
Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark tas...
HuggingFace
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but exi...
HuggingFace
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optim...
HuggingFace
TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision
We present TAPe+ML v3, a compact computer vision system based on TAPe (Theory of Active Perception), a structured rep...
HuggingFace
A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
Large language models can hold knowledge they do not report. A model may sandbag on a capability evaluation, or answe...
HuggingFace
UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing
High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view...
HuggingFace
Realtime-Venus: A full-duplex interaction system with asynchronous delegation
Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken ...
HuggingFace
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
Standard subword tokenizers either treat every orthographic variation of a word (such as hello, Hello, HELLO, and Hél...
HuggingFace
SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness
Autonomous agent systems increasingly depend on reusable skill abstractions for consolidating experiential knowledge ...
HuggingFace
ACLArena: Agent Continue Learning in Multi-stage Post-training
Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically ...