Tencent

Verified

AI & ML interests

None defined yet.

Recent Activity

XD-MU authored a paper 2 days ago

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

shenyunhang updated a collection 2 days ago

shenyunhang submitted a paper 2 days ago

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

View all activity

Papers

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

View all Papers

tencent 's papers 139

Submitted by

沈云航 Yunhang Shen

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

tencent

3

Submitted by

Xingsong Ye

WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video

tencent

Submitted by

Yuqing Li

A Broader Look into MLLM's Retrieval Heads

tencent

Submitted by

Eddie

Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation

tencent

Submitted by

Zecong Tang

HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games

tencent

Submitted by

Tianming Liang

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

tencent

Submitted by

Wei Tao

Training the Whole Agent, Not Just the Model

tencent

Submitted by

Junyao

Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine

tencent

2

Submitted by

JR QIN

Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

tencent

2

Submitted by

Lingdong Kong

Orbia: Do Generated Videos Form a Consistent 3D World?

tencent

Submitted by

cc

When Left Is Right? Camera-Motion Understanding beyond Screen

tencent

Submitted by

NaiveBayes

SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation

tencent