Ming Chen

ChenMing-thu14's activity

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

upvoted 2 papers 5 days ago

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression

Paper • 2512.05081 • Published 8 days ago • 30

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Paper • 2512.04677 • Published 8 days ago • 166

upvoted 3 papers 8 days ago

UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits

Paper • 2512.02790 • Published 11 days ago • 3

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

Paper • 2512.03041 • Published 10 days ago • 62

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published 10 days ago • 48

upvoted a paper 17 days ago

In-Video Instructions: Visual Signals as Generative Control

Paper • 2511.19401 • Published 18 days ago • 30

upvoted 2 papers 18 days ago

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

Paper • 2511.15705 • Published 23 days ago • 92

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published 22 days ago • 109

upvoted a paper 21 days ago

SAM 3D: 3Dfy Anything in Images

Paper • 2511.16624 • Published 22 days ago • 106

upvoted 2 papers 22 days ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published 23 days ago • 222

MHR: Momentum Human Rig

Paper • 2511.15586 • Published 23 days ago • 13

upvoted 4 papers about 1 month ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6 • 36

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published Oct 30 • 115

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30 • 107

LongCat-Video Technical Report

Paper • 2510.22200 • Published Oct 25 • 25

upvoted 5 papers about 2 months ago

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Paper • 2510.20187 • Published Oct 23 • 18

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Paper • 2510.09608 • Published Oct 10 • 50

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published Oct 18 • 48

Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published Oct 20 • 67

Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset

Paper • 2510.16258 • Published Oct 17 • 7