wongyukim

wongyukim's activity

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

upvoted 3 papers 1 day ago

MARVIS: Modality Adaptive Reasoning over VISualizations

Paper • 2507.01544 • Published 3 days ago • 10

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Paper • 2507.01925 • Published 3 days ago • 29

Kwai Keye-VL Technical Report

Paper • 2507.01949 • Published 3 days ago • 108

upvoted 3 papers 2 days ago

SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks

Paper • 2507.01001 • Published 4 days ago • 38

MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings

Paper • 2506.23115 • Published 6 days ago • 32

GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Paper • 2507.01006 • Published 4 days ago • 165

upvoted 5 papers 3 days ago

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Paper • 2506.16500 • Published 16 days ago • 13

Listener-Rewarded Thinking in VLMs for Image Preferences

Paper • 2506.22832 • Published 7 days ago • 23

Ovis-U1 Technical Report

Paper • 2506.23044 • Published 7 days ago • 57

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Paper • 2506.23858 • Published 5 days ago • 30

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Paper • 2506.24119 • Published 5 days ago • 39

upvoted 3 papers 7 days ago

Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

Paper • 2506.21551 • Published 9 days ago • 26

WorldVLA: Towards Autoregressive Action World Model

Paper • 2506.21539 • Published 9 days ago • 36

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Paper • 2506.21506 • Published 9 days ago • 45

upvoted 3 papers 8 days ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published 10 days ago • 57

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published 10 days ago • 42

ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

Paper • 2506.18095 • Published 13 days ago • 64

upvoted 3 papers 9 days ago

OAgents: An Empirical Study of Building Effective Agents

Paper • 2506.15741 • Published 18 days ago • 35

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Paper • 2506.19767 • Published 11 days ago • 12

Unified Vision-Language-Action Model

Paper • 2506.19850 • Published 11 days ago • 22