HuggingFace
ReLift: Dense 3D Tracking as Lifted Trajectory Repair
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth,...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement
Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simp...
HuggingFace
TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation
Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses thi...
HuggingFace
Latent Reasoning in Continuous Space for Unified Multimodal Models
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks,...
HuggingFace
GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degrad...
HuggingFace
REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control
Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to se...
HuggingFace
No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly ex...
HuggingFace
SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law infe...
HuggingFace
VoxLock: Target-Speaker Extraction for Voice Agents Without an Enrollment Step
A voice agent's speech recognizer transcribes everyone near the microphone, including people other than the caller. I...
HuggingFace
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization
An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision ...
HuggingFace
Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical sp...
HuggingFace
Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motio...