IXCLab@Shanghai AI Lab

community

https://github.com/OpenIXCLab

OpenIXCLab

AI & ML interests

None defined yet.

Recent Activity

yuhangzang authored a paper 4 days ago

$\text{G}^2$RPO: Granular GRPO for Precise Reward in Flow Models

myownskyW7 authored a paper 14 days ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

myownskyW7 authored a paper 14 days ago

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

View all activity

Papers

G^2RPO: Granular GRPO for Precise Reward in Flow Models

View all Papers

yuhangzang

authored a paper 4 days ago

$\text{G}^2$RPO: Granular GRPO for Precise Reward in Flow Models

Paper • 2510.01982 • Published 10 days ago • 5

myownskyW7

authored 4 papers 14 days ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published Aug 27 • 36

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Paper • 2508.20751 • Published Aug 28 • 89

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Paper • 2508.20751 • Published Aug 28 • 89

SIM-CoT: Supervised Implicit Chain-of-Thought

Paper • 2509.20317 • Published 18 days ago • 39

yuhangzang

authored a paper 14 days ago

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper • 2509.22186 • Published 16 days ago • 101

myownskyW7

authored a paper 14 days ago

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Paper • 2509.22186 • Published 16 days ago • 101

yuhangzang

authored a paper 14 days ago

SPARK: Synergistic Policy And Reward Co-Evolving Framework

Paper • 2509.22624 • Published 16 days ago • 16

myownskyW7

authored a paper 14 days ago

SPARK: Synergistic Policy And Reward Co-Evolving Framework

Paper • 2509.22624 • Published 16 days ago • 16

yuhangzang

authored a paper 14 days ago

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Paper • 2509.22647 • Published 16 days ago • 31

myownskyW7

authored a paper 14 days ago

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

Paper • 2509.22647 • Published 16 days ago • 31

yuhangzang

updated a Space 15 days ago

MMLongBench Doc

A long-context, multimodal document understanding benchmark

yuhangzang

authored a paper 16 days ago

SIM-CoT: Supervised Implicit Chain-of-Thought

Paper • 2509.20317 • Published 18 days ago • 39

Zery

in OpenIXCLab/CODA-PLANNER-TARS-32B about 1 month ago

Improve model card: add abstract, usage, features, and fix license metadata

#1 opened about 1 month ago by

yuhangzang

authored a paper about 1 month ago

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Paper • 2508.20751 • Published Aug 28 • 89

Zery

authored a paper about 2 months ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published Aug 27 • 36

yuhangzang

authored a paper about 2 months ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published Aug 27 • 36

rookiexiong

authored a paper about 2 months ago

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

Paper • 2508.20096 • Published Aug 27 • 36

Zery

updated a model about 2 months ago

OpenIXCLab/CODA-PLANNER-TARS-32B

Image-Text-to-Text • 33B • Updated Aug 31 • 5 • 3

Zery

published a model about 2 months ago

OpenIXCLab/CODA-PLANNER-TARS-32B

Image-Text-to-Text • 33B • Updated Aug 31 • 5 • 3