HuggingFace
ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning
Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where mode...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-...
HuggingFace
SciForma: Structure-Faithful Generation of Scientific Diagrams
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams mu...
HuggingFace
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but stale...
HuggingFace
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically...
HuggingFace
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation...
HuggingFace
Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness
Evaluating the factuality of long-form generations has focused predominantly on precision, measuring whether the clai...
HuggingFace
HPD-Parsing: Hierarchical Parallel Document Parsing
Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflecte...
HuggingFace
Trajectory-aware Cross-view Geo-localization with Sequential Observations
Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods sh...
HuggingFace
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction,...
HuggingFace
ISO: An RLVR-Native Optimization Stack
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language mod...
HuggingFace
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation dur...