HuggingFace
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instructi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Grounded Action Model: 3D Grounding as a Foundation for Robotics
Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current ro...
HuggingFace
Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles
Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point toler...
HuggingFace
Harness-Zero: Harness Distillation via Agent-as-Harness
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent per...
HuggingFace
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda...
HuggingFace
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation
Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated tr...
HuggingFace
OmniEdu: Open Foundation Models for Learning and Teaching
Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, an...
HuggingFace
CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies
Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once exec...
HuggingFace
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descript...
HuggingFace
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene
Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent s...
HuggingFace
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document forma...
HuggingFace
Streaming Video Editing with Easy Adaptation
In this paper, we propose SVEET, a framework that requires merely training on a pretrained bidirectional video diffus...