Chuanming Liu's picture

Chuanming Liu

Chuanming

·

Chuanming

AI & ML interests

Artificial Intelligence, AGI, NLP, LLMs, Multimodality, MLSys. Python/Golang/C/C++/Shell/awk&sed

Recent Activity

liked a dataset about 3 hours ago

omlab/VLM-R1

liked a model about 3 hours ago

omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps

reacted to tianchez's post with 👍 about 3 hours ago

Introducing VLM-R1! GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks? The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task). https://github.com/om-ai-lab/VLM-R1

View all activity

Organizations

Chuanming's activity

upvoted a collection 1 day ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated 1 day ago • 30

upvoted an article 2 days ago

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

3 days ago

• 50

upvoted a collection 2 days ago

PaliGemma 2 Mix

13 items • Updated 3 days ago • 51

upvoted an article 6 days ago

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Dec 9, 2022

• 167

upvoted a paper 9 days ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1, 2024 • 73

upvoted an article 9 days ago

Article

Open-source DeepResearch – Freeing our search agents

18 days ago

• 1.07k

upvoted an article 12 days ago

Article

Welcome to Inference Providers on the Hub 🔥

25 days ago

• 381

upvoted a collection 14 days ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated Nov 28, 2024 • 526

upvoted a paper 19 days ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 25 days ago • 106

upvoted a collection 21 days ago

OLMo 2 Preview Post-trained Models

These model's tokenizer did not use HF's fast tokenizer, resulting in variations in how pre-tokenization was applied. Resolved in latest versions. • 6 items • Updated 11 days ago • 2

upvoted 2 collections 26 days ago

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 2 items • Updated 27 days ago • 100

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 3 items • Updated 26 days ago • 359

upvoted an article 26 days ago

Article

We now support VLMs in smolagents!

29 days ago

• 84

upvoted a paper 27 days ago

LIMA: Less Is More for Alignment

Paper • 2305.11206 • Published May 18, 2023 • 23

upvoted an article about 1 month ago

Article

AI Agents Are Here. What Now?

Jan 13

• 66

upvoted 3 collections about 2 months ago

Deepseek V3 (All Versions)

Deepseek V3 - available in bf16, original, and GGUF formats, with support for 2, 3, 4, 5, 6 and 8-bit quantized versions. • 3 items • Updated 18 days ago • 33

OLMo 2

Artifacts for the second set of OLMo models. • 22 items • Updated 11 days ago • 83

Reasoning Datasets

Reasoning datasets that are trending 🔥 • 10 items • Updated Jan 3 • 24

upvoted a collection 2 months ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 138

upvoted a paper 2 months ago

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published Dec 13, 2024 • 140