Melih Özcan

staycoolish's activity

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

upvoted 16 papers 2 days ago

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space

Paper • 2504.13835 • Published 11 days ago • 36

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published 13 days ago • 27

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

Paper • 2504.13816 • Published 11 days ago • 17

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published 11 days ago • 114

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation

Paper • 2504.14899 • Published 8 days ago • 17

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 8 days ago • 46

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Paper • 2504.14239 • Published 10 days ago • 13

OTC: Optimal Tool Calls via Reinforcement Learning

Paper • 2504.14870 • Published 8 days ago • 33

Learning to Reason under Off-Policy Guidance

Paper • 2504.14945 • Published 8 days ago • 77

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

Paper • 2504.16030 • Published 7 days ago • 32

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks

Paper • 2504.15521 • Published 8 days ago • 61

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published 7 days ago • 93

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning

Paper • 2504.14509 • Published 9 days ago • 48

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Paper • 2504.15279 • Published 8 days ago • 69

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

Paper • 2504.17789 • Published 5 days ago • 21

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published 5 days ago • 81

upvoted 4 papers 11 days ago

VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Paper • 2504.07615 • Published 19 days ago • 31

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Paper • 2504.08600 • Published 18 days ago • 26

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Paper • 2504.08736 • Published 18 days ago • 47

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published 18 days ago • 122