HuggingFace
ActionSplice: In-Flight Action Editing for Interactive World Models
Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received du...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents
GUI agents accumulate high-resolution screenshots as the trajectory unfolds, increasing inference latency and memory ...
HuggingFace
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reus...
HuggingFace
Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
We describe our entry to the EgoLongQA track of the Wearable-AI Challenge in ECCV 2026, which placed first in the <=2...
HuggingFace
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
We present our submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, which ranked first in the...
HuggingFace
Towards a Deterministic Math Solver for Clinical Language Models
Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numeri...
HuggingFace
Feature Recovery for Object Understanding After Irreversible Fire Damage
Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, mat...
HuggingFace
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
In hybrid forecasting, a language model is often one of several available signals. A system may already have a market...
HuggingFace
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs
Reacting to sudden physical hazards (catching a slipping plate, dodging a falling knife) is both a meaningful test of...
HuggingFace
Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence
In this technical report, we propose Pelican-Sim 1.0, a general world model simulator for embodied intelligence that ...
HuggingFace
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation ...
HuggingFace
MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control
Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for visi...