Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions Paper • 2412.08737 • Published 15 days ago • 51
TLDR: Token-Level Detective Reward Model for Large Vision Language Models Paper • 2410.04734 • Published Oct 7 • 16
TLDR: Token-Level Detective Reward Model for Large Vision Language Models Paper • 2410.04734 • Published Oct 7 • 16
TLDR: Token-Level Detective Reward Model for Large Vision Language Models Paper • 2410.04734 • Published Oct 7 • 16 • 2
Pre-trained Large Language Models Use Fourier Features to Compute Addition Paper • 2406.03445 • Published Jun 5
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models Paper • 2310.17086 • Published Oct 26, 2023 • 1
IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations Paper • 2404.01266 • Published Apr 1 • 2
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback Paper • 2311.17946 • Published Nov 29, 2023 • 1