Miyazaki

miiyazaki's activity

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

upvoted 10 papers 1 day ago

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Paper • 2408.04682 • Published Aug 8, 2024 • 17

Enabling Scalable Oversight via Self-Evolving Critic

Paper • 2501.05727 • Published 7 days ago • 62

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

Paper • 2501.01895 • Published 13 days ago • 46

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Paper • 2501.02976 • Published 10 days ago • 51

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Paper • 2501.03262 • Published 13 days ago • 82

Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Paper • 2501.03847 • Published 9 days ago • 22

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

Paper • 2501.05040 • Published 8 days ago • 14

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Paper • 2501.05452 • Published 7 days ago • 14

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Paper • 2501.06842 • Published 4 days ago • 14

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Paper • 2501.07730 • Published 3 days ago • 16