Zhongpai Gao

gaozhongpai's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published 5 days ago • 58

upvoted a paper 19 days ago

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

Paper • 2510.23473 • Published 22 days ago • 82

upvoted a paper 26 days ago

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Paper • 2510.18927 • Published 28 days ago • 82

upvoted a paper 2 months ago

Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

Paper • 2509.04434 • Published Sep 4 • 10

upvoted 12 papers 3 months ago

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

Paper • 2412.01064 • Published Dec 2, 2024 • 47

TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

Paper • 2508.13618 • Published Aug 19 • 17

Multi-View 3D Point Tracking

Paper • 2508.21060 • Published Aug 28 • 22

Gaze into the Heart: A Multi-View Video Dataset for rPPG and Health Biomarkers Estimation

Paper • 2508.17924 • Published Aug 25 • 14

MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation

Paper • 2508.19320 • Published Aug 26 • 29

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

Paper • 2508.13154 • Published Aug 18 • 62

FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

Paper • 2508.11255 • Published Aug 15 • 11

DisTime: Distribution-based Time Representation for Video Large Language Models

Paper • 2505.24329 • Published May 30 • 1

DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO

Paper • 2506.07464 • Published Jun 9 • 13

VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding

Paper • 2507.13353 • Published Jul 17 • 1

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Paper • 2506.21862 • Published Jun 27 • 36

DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework

Paper • 2508.02807 • Published Aug 4 • 13

upvoted 4 papers 4 months ago

Phi-Ground Tech Report: Advancing Perception in GUI Grounding

Paper • 2507.23779 • Published Jul 31 • 44

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

Paper • 2507.10065 • Published Jul 14 • 24

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Paper • 2507.09862 • Published Jul 14 • 49

CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering

Paper • 2507.08776 • Published Jul 11 • 54