HuggingFace
World Action Modeling with Progressive Visual Planning
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visu...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration
Natural-language service requests can require a language-model decision before execution starts, consuming part of th...
HuggingFace
LOCI: Spatial Linear Memory for Streaming World Models
When a camera revisits a previously observed region, a video world model should reproduce what was there before. This...
HuggingFace
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs
Before invoking external tools, an agentic LLM must select among a K-way action space: executing a call, seeking clar...
HuggingFace
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
Furnished floor plans support real-estate visualization, interior design, and architectural workflows, yet automatic ...
HuggingFace
JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces
LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computat...
HuggingFace
OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport
Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while ...
HuggingFace
Decoding Looped Transformers Better for (Almost) Free
Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each ...
HuggingFace
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by s...
HuggingFace
SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of dif...
HuggingFace
RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers
Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in ...
HuggingFace
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve ...