wongyukim (wongyukim)

upvoted a paper about 17 hours ago

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

Paper • 2410.19133 • Published 5 days ago • 10

upvoted 6 papers 2 days ago

Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

Paper • 2410.18558 • Published 6 days ago • 15

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

Paper • 2410.17243 • Published 7 days ago • 80

Teach Multimodal LLMs to Comprehend Electrocardiographic Images

Paper • 2410.19008 • Published 8 days ago • 22

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Paper • 2410.12784 • Published 13 days ago • 32

HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks

Paper • 2410.12381 • Published 14 days ago • 41

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

Paper • 2410.12787 • Published 13 days ago • 30

upvoted 13 papers 5 days ago

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation

Paper • 2410.09584 • Published 17 days ago • 44

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Paper • 2410.10139 • Published 16 days ago • 49

From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning

Paper • 2410.06456 • Published 21 days ago • 35

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Paper • 2410.10563 • Published 15 days ago • 35

wongyukim

AI & ML interests

Organizations

wongyukim's activity

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

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

Teach Multimodal LLMs to Comprehend Electrocardiographic Images

JudgeBench: A Benchmark for Evaluating LLM-based Judges

HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks

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

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Response Tuning: Aligning Large Language Models without Instruction

MM-Ego: Towards Building Egocentric Multimodal LLMs

Personalized Visual Instruction Tuning

Aria: An Open Multimodal Native Mixture-of-Experts Model

Pixtral 12B

UniMuMo: Unified Text, Music and Motion Generation

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

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks