Kai Chen's picture

8 6 9

Kai Chen

KaiChen1998

·

https://kaichen1998.github.io/

AI & ML interests

Omni-modal Large Language Models & Controllable Visual World Modeling & Autonomous Driving

Recent Activity

liked a Space 2 days ago

Emova-ollm/RACRO-demo

posted an update 3 days ago

🤔 Advanced reasoning LLMs keep releasing before your current MLLM alignment is done? Try our RACRO! Train once, flexible change to novel LLM reasoners during inference time! 📢 RACRO is a novel methodology to build multi-modal large reasoning models. By decoupling multi-modal reasoning into 1) query-conditioned captioning and 2) text-only reasoning, we achieve SoTA results on multi-modal reasoning benchmarks, while supporting flexible changes to any advanced reasoning models during inference. We further propose CRO, a novel GRPO-variant to reinforce query-conditioned captioning with only verifiable data for multi-modal mathematical questions. ✨ Highlights ✅ State-of-the-art multi-modal reasoning: we achieve SoTA performance on multi-modal mathematical benchmarks, exceeding advanced commercial models like Claude-3.7-Sonnet and Gemini-2.0-Flash. ✅ Inference-time scalability: thanks to the perceptual decoupling, we can flexibly change LLM reasoners during inference, providing a unique inference-time scalability for multi-modal reasoning. ✅ Highly efficient: With only a single round of Caption Reward Optimization (CRO) training on ~39K samples, RACRO gets rid of burdensome multi-modal alignment (e.g., 4.1T tokens for Qwen2.5-VL). 🔥 You are all welcome to try and star! - Paper: https://huggingface.co/papers/2506.04559 - Github: https://github.com/gyhdog99/RACRO2 - Demo: https://huggingface.co/spaces/Emova-ollm/RACRO-demo

updated a Space 3 days ago

Emova-ollm/RACRO-demo

View all activity

Organizations

KaiChen1998's activity

liked a Space 2 days ago

RACRO Online Interactive Demo

Live Interactive demo for RACRO-7B-CRO-GRPO backbone

liked 7 models 3 months ago

Emova-ollm/emova_speech_tokenizer_hf

Feature Extraction • Updated Mar 12 • 96 • 2

Emova-ollm/emova-qwen-2-5-72b-hf

Feature Extraction • Updated Mar 14 • 13 • 2

Emova-ollm/emova-qwen-2-5-72b

Text Generation • Updated Mar 13 • 24 • 1

Emova-ollm/emova-qwen-2-5-7b

Text Generation • Updated Mar 13 • 24 • 1

Emova-ollm/emova-qwen-2-5-3b-hf

Feature Extraction • Updated Mar 13 • 19 • 5

Emova-ollm/emova-qwen-2-5-3b

Text Generation • Updated Mar 13 • 33 • 2

Emova-ollm/emova-qwen-2-5-7b-hf

Feature Extraction • Updated Mar 13 • 31 • 2

liked a Space 3 months ago

EMOVA Online Interactive Demo

Live Interactive demo for EMOVA with Qwen-2.5 backbone