4 16 12

Zesen Cheng

ClownRat

AI & ML interests

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

Organizations

ClownRat's activity

upvoted 2 papers 14 days ago

Enhancing Training Efficiency Using Packing with Flash Attention

Paper • 2407.09105 • Published Jul 12 • 14

Chain of Ideas: Revolutionizing Research in Novel Idea Development with LLM Agents

Paper • 2410.13185 • Published 24 days ago • 6

upvoted a paper 15 days ago

Why Does the Effective Context Length of LLMs Fall Short?

Paper • 2410.18745 • Published 17 days ago • 16

upvoted a paper 16 days ago

Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

Paper • 2410.12490 • Published 25 days ago • 8

upvoted 2 collections 16 days ago

DiGIT

Collection

The corresponding checkpoints of [NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective • 2 items • Updated 16 days ago • 1

Inf-CL

Collection

The corresponding demos/checkpoints/papers/datasets of Inf-CL. • 2 items • Updated 16 days ago • 2

upvoted a paper 16 days ago

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

Paper • 2410.17243 • Published 19 days ago • 87

upvoted a paper 24 days ago

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

Paper • 2410.12787 • Published 25 days ago • 30

upvoted a paper about 1 month ago

A Survey on the Honesty of Large Language Models

Paper • 2409.18786 • Published Sep 27 • 29

upvoted a paper 3 months ago

SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages

Paper • 2407.19672 • Published Jul 29 • 54

upvoted a paper 4 months ago

MAVIS: Mathematical Visual Instruction Tuning

Paper • 2407.08739 • Published Jul 11 • 30

upvoted 2 papers 5 months ago

The Road Less Scheduled

Paper • 2405.15682 • Published May 24 • 20

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19 • 150

upvoted a collection 5 months ago

VideoLLaMA 2

Collection

Optimized VideoLLaMA with improved spatial-temporal modeling and better audio understanding capability • 15 items • Updated 6 days ago • 20

upvoted a paper 5 months ago

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Paper • 2406.07476 • Published Jun 11 • 32