Cihang Xie

cihangxie's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 4 months ago

ViLBench: A Suite for Vision-Language Process Reward Modeling

Paper • 2503.20271 • Published Mar 26 • 7

authored a paper 6 months ago

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Paper • 2502.03738 • Published Feb 6 • 11

authored a paper 11 months ago

VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges

Paper • 2409.01071 • Published Sep 2, 2024 • 28

authored a paper 12 months ago

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Paper • 2408.02900 • Published Aug 6, 2024 • 31

authored 2 papers about 1 year ago

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models

Paper • 2406.16338 • Published Jun 24, 2024 • 27

What If We Recaption Billions of Web Images with LLaMA-3?

Paper • 2406.08478 • Published Jun 12, 2024 • 42

authored 3 papers over 1 year ago

Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

Paper • 2404.08197 • Published Apr 12, 2024 • 30

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

Paper • 2404.09990 • Published Apr 15, 2024 • 13

Rejuvenating image-GPT as Strong Visual Representation Learners

Paper • 2312.02147 • Published Dec 4, 2023 • 7

authored 2 papers about 2 years ago

CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \$10,000 Budget; An Extra \$4,000 Unlocks 81.8% Accuracy

Paper • 2306.15658 • Published Jun 27, 2023 • 12

An Inverse Scaling Law for CLIP Training

Paper • 2305.07017 • Published May 11, 2023 • 3