Zesen Cheng's picture

Zesen Cheng

ClownRat

·

AI & ML interests

multi-modal foundation model; Segmentation, Detection, and Tracking;

Recent Activity

upvoted a paper 4 days ago

Kimi k1.5: Scaling Reinforcement Learning with LLMs

upvoted a paper 4 days ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

liked a dataset 9 days ago

OpenGVLab/OmniCorpus-YT

View all activity

Organizations

ClownRat's activity

New activity in DAMO-NLP-SG/VideoLLaMA2.1-7B-AV about 1 month ago

Some weights of Videollama2Qwen2ForCausalLM were not initialized from the model checkpoint at ./VideoLLaMA2.1-7B-AV and are newly initialized:

#4 opened about 2 months ago by

New activity in MLVU/MVLU 3 months ago

[Typos] The dataset name seems to be wrong.

#2 opened 3 months ago by

[Typos] The dataset name seems error.

#1 opened 3 months ago by

commented a paper 4 months ago

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published Oct 22, 2024 • 89 •

New activity in lixin4ever/VideoLLaMA2 4 months ago

Fix frame sampling scheme.

#2 opened 7 months ago by

New activity in DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained 5 months ago

could not parse ModelProto

#1 opened 5 months ago by

New activity in DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base 5 months ago

Problem in config.json file

#1 opened 5 months ago by

New activity in lixin4ever/VideoLLaMA2 7 months ago

Fix frame sampling scheme.

#2 opened 7 months ago by