Cheng-Yu Hsieh

cydhsieh01's activity

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

authored a paper 14 days ago

Perception Tokens Enhance Visual Reasoning in Multimodal Language Models

Paper • 2412.03548 • Published 21 days ago • 16

updated a model about 1 month ago

vila-molmo/molmo-dense-captioner-v22-qwen2

Updated about 1 month ago • 24

upvoted a paper 5 months ago

Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model

Paper • 2408.00754 • Published Aug 1 • 21

authored a paper 6 months ago

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Paper • 2406.16008 • Published Jun 23 • 6

upvoted 3 papers 6 months ago

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

Paper • 2407.06723 • Published Jul 9 • 10

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Paper • 2407.07071 • Published Jul 9 • 11

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Paper • 2406.16008 • Published Jun 23 • 6

commented a paper 6 months ago

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Paper • 2406.16008 • Published Jun 23 • 6 •

1

authored 6 papers 6 months ago

On the (In)fidelity and Sensitivity for Explanations

Paper • 1901.09392 • Published Jan 27, 2019

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

Paper • 2306.14610 • Published Jun 26, 2023

Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

Paper • 2305.02301 • Published May 3, 2023 • 2

Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models

Paper • 2308.00675 • Published Aug 1, 2023 • 35

A Survey on Programmatic Weak Supervision

Paper • 2202.05433 • Published Feb 11, 2022

DataComp-LM: In search of the next generation of training sets for language models

Paper • 2406.11794 • Published Jun 17 • 50