ARC Lab, Tencent PCG

company

Verified

TencentARC

Activity Feed Request to join this org

AI & ML interests

ARC mainly focuses on areas of computer vision, speech, and natural language processing, including speech/video generation, enhancement, retrieval, understanding, AutoML, etc. Considering research developments and industry trends, ARC consistently pursues exploration, innovation, and breakthroughs in technologies.

Recent Activity

ZyZcuhk authored a paper 1 day ago

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

zhousc updated a dataset 11 days ago

TencentARC/DSR_Suite-Data

zhousc new activity 13 days ago

TencentARC/DSR_Suite-Data:Add paper link, task categories and dataset description

View all activity

Papers

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries

View all Papers

ZyZcuhk

authored a paper 1 day ago

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Paper • 2601.02356 • Published 2 days ago • 12

zhousc

updated a dataset 11 days ago

TencentARC/DSR_Suite-Data

Viewer • Updated 11 days ago • 55.2k • 96 • 4

zhousc

in TencentARC/DSR_Suite-Data 13 days ago

Add paper link, task categories and dataset description

#1 opened 13 days ago by

zhousc

in TencentARC/DSR_Suite-Model 13 days ago

Add model card and metadata for DSR Suite model

#1 opened 13 days ago by

zhousc

authored 2 papers 13 days ago

UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View

Paper • 2303.15083 • Published Mar 27, 2023

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

Paper • 2512.20557 • Published 15 days ago • 49

Uasonchen

authored a paper 13 days ago

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

Paper • 2512.20557 • Published 15 days ago • 49

zhousc

updated a collection 15 days ago

DSR_Suite

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models • 3 items • Updated 15 days ago • 6

zhousc

updated a model 15 days ago

TencentARC/DSR_Suite-Model

Video-Text-to-Text • 9B • Updated 13 days ago • 70 • 4

zhousc

published a dataset 15 days ago

TencentARC/DSR_Suite-Data

Viewer • Updated 11 days ago • 55.2k • 96 • 4

zhousc

published a model 15 days ago

TencentARC/DSR_Suite-Model

Video-Text-to-Text • 9B • Updated 13 days ago • 70 • 4

zhousc

updated a collection 16 days ago

DSR_Suite

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models • 3 items • Updated 15 days ago • 6

JungleGym

authored a paper 17 days ago

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Paper • 2512.14698 • Published 22 days ago • 19

JungleGym

updated 2 datasets 20 days ago

TencentARC/TimeLens-Bench

Viewer • Updated 20 days ago • 2.32k • 316 • 2

TencentARC/TimeLens-100K

Viewer • Updated 20 days ago • 19.2k • 1.1k • 3

JungleGym

updated 2 models 20 days ago

TencentARC/TimeLens-8B

Video-Text-to-Text • 9B • Updated 20 days ago • 212 • 4

TencentARC/TimeLens-7B

Video-Text-to-Text • 8B • Updated 20 days ago • 46 • 4

JungleGym

updated a collection 21 days ago

TimeLens

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs • 5 items • Updated 21 days ago • 8

JungleGym

submitted a paper to Daily Papers 21 days ago

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Paper • 2512.14698 • Published 22 days ago • 19