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

WuChengyue authored a paper 5 days ago

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

yxgeee authored a paper 14 days ago

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

tttoaster authored a paper 14 days ago

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

View all activity

WuChengyue

authored a paper 5 days ago

Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

Paper • 2507.01957 • Published 6 days ago • 16

yxgeee

authored a paper 14 days ago

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

Paper • 2506.16141 • Published 20 days ago • 27

tttoaster

authored a paper 14 days ago

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

Paper • 2506.16141 • Published 20 days ago • 27

Liangbin

authored a paper 14 days ago

SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution

Paper • 2506.19838 • Published 14 days ago • 11

pookiefoof

authored a paper 14 days ago

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models

Paper • 2506.19851 • Published 14 days ago • 56

ChenYi99

in TencentARC/GRPO-CARE 15 days ago

Improve model card for GRPO-CARE

#1 opened 16 days ago by

ChenYi99

updated a model 16 days ago

TencentARC/GRPO-CARE

Video-Text-to-Text • Updated 15 days ago • 30 • 1

ChenYi99

updated a model 19 days ago

TencentARC/Moto

Updated 19 days ago • 13 • 6

ChenYi99

published a model 19 days ago

TencentARC/GRPO-CARE

Video-Text-to-Text • Updated 15 days ago • 30 • 1

multimodalart

posted an update 20 days ago

Post

5667

Self-Forcing - a real-time video distilled model from Wan 2.1 by @adobe is out, and they open sourced it 🐐

I've built a live real time demo on Spaces 📹💨

multimodalart/self-forcing

4 replies

·

ZyZcuhk

authored a paper 22 days ago

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation

Paper • 2506.02975 • Published Jun 3

EasonXiao-888

authored 6 papers 23 days ago

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Paper • 2305.17011 • Published May 26, 2023

GrootVL: Tree Topology is All You Need in State Space Model

Paper • 2406.02395 • Published Jun 4, 2024 • 1

COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing

Paper • 2406.08850 • Published Jun 13, 2024

HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding

Paper • 2503.14694 • Published Mar 12

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Paper • 2505.13031 • Published May 19 • 4

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation

Paper • 2506.02975 • Published Jun 3

wybertwang

authored 3 papers about 1 month ago

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Paper • 2305.02677 • Published May 4, 2023

Video Understanding with Large Language Models: A Survey

Paper • 2312.17432 • Published Dec 29, 2023 • 3

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

Paper • 2307.14061 • Published Jul 26, 2023