arXiv
QuoteBench: How Matched Scores Can Hide Command-Path Failures
LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with wh...
arXiv
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows,...
arXiv
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a ...
HuggingFace
Full-bandwidth transformer
Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through mode...
HuggingFace
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Video world models simulate future states conditioned on current observations and user actions. Recent systems have d...
HuggingFace
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory sys...
HuggingFace
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a ...
HuggingFace
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two arch...
HuggingFace
DarwinX: Evolving Agent Harnesses Through Natural Selection
An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control f...
HuggingFace
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To im...
HuggingFace
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
We present DreamX-Phi 1.0, an action-conditioned video world model for robotic manipulation that, given an observed f...