Melih Özcan

staycoolish's activity

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

upvoted a paper 3 days ago

START: Self-taught Reasoner with Tools

Paper • 2503.04625 • Published 3 days ago • 77

upvoted 4 papers 4 days ago

Iterative Value Function Optimization for Guided Decoding

Paper • 2503.02368 • Published 6 days ago • 14

Wikipedia in the Era of LLMs: Evolution and Risks

Paper • 2503.02879 • Published 5 days ago • 19

MPO: Boosting LLM Agents with Meta Plan Optimization

Paper • 2503.02682 • Published 6 days ago • 23

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs

Paper • 2503.02846 • Published 5 days ago • 18

upvoted 3 papers 6 days ago

Visual-RFT: Visual Reinforcement Fine-Tuning

Paper • 2503.01785 • Published 6 days ago • 59

Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids

Paper • 2502.20396 • Published 10 days ago • 12

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

Paper • 2502.20900 • Published 10 days ago • 7

upvoted 4 papers 13 days ago

CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models

Paper • 2502.16614 • Published 15 days ago • 24

Audio-FLAN: A Preliminary Release

Paper • 2502.16584 • Published 15 days ago • 33

Thus Spake Long-Context Large Language Model

Paper • 2502.17129 • Published 14 days ago • 67

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

Paper • 2502.17157 • Published 14 days ago • 51

upvoted 4 papers 17 days ago

S*: Test Time Scaling for Code Generation

Paper • 2502.14382 • Published 18 days ago • 59

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 17 days ago • 94

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Paper • 2502.13144 • Published 19 days ago • 37

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 18 days ago • 157

upvoted 4 papers 19 days ago

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

Paper • 2502.10248 • Published 23 days ago • 51

Phantom: Subject-consistent video generation via cross-modal alignment

Paper • 2502.11079 • Published 22 days ago • 52

Soundwave: Less is More for Speech-Text Alignment in LLMs

Paper • 2502.12900 • Published 20 days ago • 76

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

Paper • 2502.13145 • Published 19 days ago • 36