wongyukim

wongyukim's activity

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

upvoted 3 papers 1 day ago

On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral

Paper • 2512.04220 • Published 4 days ago • 9

TV2TV: A Unified Framework for Interleaved Language and Video Generation

Paper • 2512.05103 • Published 3 days ago • 10

ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning

Paper • 2512.05111 • Published 3 days ago • 42

upvoted 5 papers 3 days ago

In-Context Representation Hijacking

Paper • 2512.03771 • Published 5 days ago • 3

Jina-VLM: Small Multilingual Vision Language Model

Paper • 2512.04032 • Published 4 days ago • 9

PretrainZero: Reinforcement Active Pretraining

Paper • 2512.03442 • Published 5 days ago • 39

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach

Paper • 2512.02834 • Published 5 days ago • 37

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 11 days ago • 109

upvoted 3 papers 4 days ago

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead

Paper • 2512.00903 • Published 7 days ago • 5

DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models

Paper • 2512.01715 • Published 6 days ago • 9

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published 11 days ago • 96

upvoted 5 papers 5 days ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published 6 days ago • 54

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Paper • 2511.20649 • Published 12 days ago • 43

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published 12 days ago • 148

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Paper • 2511.18538 • Published 14 days ago • 240

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 6 days ago • 172

upvoted 4 papers 6 days ago

RefineBench: Evaluating Refinement Capability of Language Models via Checklists

Paper • 2511.22173 • Published 11 days ago • 12

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models

Paper • 2511.23319 • Published 9 days ago • 21

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

Paper • 2511.22134 • Published 11 days ago • 21

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

Paper • 2511.22570 • Published 10 days ago • 65