Jinyeong Kim

rubatoyeong's activity

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

upvoted 2 papers about 4 hours ago

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Paper • 2411.04986 • Published 4 days ago • 3

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

Paper • 2411.04097 • Published 5 days ago • 3

upvoted 4 papers 3 days ago

VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

Paper • 2411.04923 • Published 4 days ago • 20

Analyzing The Language of Visual Tokens

Paper • 2411.05001 • Published 4 days ago • 16

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Paper • 2411.04996 • Published 4 days ago • 40

Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination

Paper • 2411.03823 • Published 5 days ago • 41

upvoted a paper 5 days ago

Inference Optimal VLMs Need Only One Visual Token but Larger Models

Paper • 2411.03312 • Published 6 days ago • 6

upvoted 3 papers 6 days ago

Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge

Paper • 2411.02657 • Published 7 days ago • 5

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Paper • 2411.00743 • Published 10 days ago • 6

Sparsing Law: Towards Large Language Models with Greater Activation Sparsity

Paper • 2411.02335 • Published 7 days ago • 10

upvoted 2 papers 7 days ago

Zipfian Whitening

Paper • 2411.00680 • Published 10 days ago • 8

GPT or BERT: why not both?

Paper • 2410.24159 • Published 11 days ago • 11

upvoted 4 papers 8 days ago

Personalization of Large Language Models: A Survey

Paper • 2411.00027 • Published 14 days ago • 30

Randomized Autoregressive Visual Generation

Paper • 2411.00776 • Published 10 days ago • 17

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Paper • 2410.23743 • Published 11 days ago • 57

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Paper • 2410.22366 • Published 14 days ago • 72

upvoted 2 papers 10 days ago

BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

Paper • 2410.21969 • Published 13 days ago • 8

On Memorization of Large Language Models in Logical Reasoning

Paper • 2410.23123 • Published 12 days ago • 15

upvoted 2 papers 11 days ago

Measuring memorization through probabilistic discoverable extraction

Paper • 2410.19482 • Published 17 days ago • 4

Task Vectors are Cross-Modal

Paper • 2410.22330 • Published 13 days ago • 10