Jinyeong Kim

rubatoyeong's activity

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

upvoted a paper 1 day ago

Medical large language models are easily distracted

Paper • 2504.01201 • Published 4 days ago • 2

upvoted 6 papers 2 days ago

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Paper • 2504.01308 • Published 3 days ago • 12

PaperBench: Evaluating AI's Ability to Replicate AI Research

Paper • 2504.01848 • Published 3 days ago • 27

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

Paper • 2504.00557 • Published 4 days ago • 14

Scaling Language-Free Visual Representation Learning

Paper • 2504.01017 • Published 4 days ago • 20

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Paper • 2503.22165 • Published 8 days ago • 23

Multi-Token Attention

Paper • 2504.00927 • Published 4 days ago • 30

upvoted 3 papers 4 days ago

On Large Multimodal Models as Open-World Image Classifiers

Paper • 2503.21851 • Published 9 days ago • 4

MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow

Paper • 2503.18968 • Published 15 days ago • 6

A Refined Analysis of Massive Activations in LLMs

Paper • 2503.22329 • Published 8 days ago • 11

upvoted a paper 6 days ago

Gemma 3 Technical Report

Paper • 2503.19786 • Published 11 days ago • 42

upvoted 2 papers 9 days ago

Attention IoU: Examining Biases in CelebA using Attention Maps

Paper • 2503.19846 • Published 11 days ago • 7

Reasoning to Learn from Latent Thoughts

Paper • 2503.18866 • Published 12 days ago • 13

upvoted 3 papers 10 days ago

Judge Anything: MLLM as a Judge Across Any Modality

Paper • 2503.17489 • Published 15 days ago • 19

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 12 days ago • 110

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published 16 days ago • 70

upvoted 2 papers 12 days ago

Where do Large Vision-Language Models Look at when Answering Questions?

Paper • 2503.13891 • Published 18 days ago • 8

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

Paper • 2503.16356 • Published 16 days ago • 15

upvoted 2 papers 15 days ago

M3: 3D-Spatial MultiModal Memory

Paper • 2503.16413 • Published 16 days ago • 15

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published 17 days ago • 43