Deqing Fu PRO

deqing's activity

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

authored a paper 3 months ago

Are LLM Decisions Faithful to Verbal Confidence?

Paper • 2601.07767 • Published Jan 12 • 5

submitted a paper to Daily Papers 3 months ago

Are LLM Decisions Faithful to Verbal Confidence?

Paper • 2601.07767 • Published Jan 12 • 5

authored a paper 5 months ago

When Do Transformers Learn Heuristics for Graph Connectivity?

Paper • 2510.19753 • Published Oct 22, 2025 • 4

authored a paper 8 months ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Paper • 2507.16746 • Published Jul 22, 2025 • 34

authored 2 papers 10 months ago

Resa: Transparent Reasoning Models via SAEs

Paper • 2506.09967 • Published Jun 11, 2025 • 21

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Paper • 2505.14071 • Published May 20, 2025 • 1

authored a paper about 1 year ago

FoNE: Precise Single-Token Number Embeddings via Fourier Features

Paper • 2502.09741 • Published Feb 13, 2025 • 15

authored 2 papers over 1 year ago

VisualLens: Personalization through Visual History

Paper • 2411.16034 • Published Nov 25, 2024 • 18

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

Paper • 2410.04734 • Published Oct 7, 2024 • 19

authored 6 papers almost 2 years ago

Pre-trained Large Language Models Use Fourier Features to Compute Addition

Paper • 2406.03445 • Published Jun 5, 2024

Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models

Paper • 2310.17086 • Published Oct 26, 2023 • 2

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations

Paper • 2404.01266 • Published Apr 1, 2024 • 4

DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback

Paper • 2311.17946 • Published Nov 29, 2023 • 2

Simplicity Bias of Transformers to Learn Low Sensitivity Functions

Paper • 2403.06925 • Published Mar 11, 2024 • 1

DeLLMa: A Framework for Decision Making Under Uncertainty with Large Language Models

Paper • 2402.02392 • Published Feb 4, 2024 • 6