Mingsong_Li

Mingsong07's activity

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

upvoted a paper 1 day ago

Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR

Paper • 2610.16105 • Published 6 days ago • 8

upvoted a paper 12 days ago

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

Paper • 2610.05303 • Published 14 days ago • 24

upvoted a paper about 1 month ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 183

upvoted a paper 4 months ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 178

upvoted a paper 7 months ago

MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning

Paper • 2603.16929 • Published Mar 14 • 13

authored a paper 7 months ago

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Paper • 2603.27481 • Published Mar 29 • 33

upvoted 2 papers 7 months ago

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

Paper • 2601.15968 • Published Jan 22 • 9

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Paper • 2603.27481 • Published Mar 29 • 33

liked a Space 11 months ago

Running on CPU Upgrade

Featured

3.33k

The Smol Training Playbook

📚

3.33k

The secrets to building world-class LLMs

upvoted a paper 12 months ago

The Art of Scaling Reinforcement Learning Compute for LLMs

Paper • 2510.13786 • Published Oct 15, 2025 • 34

updated a collection 12 months ago

LLM-Reasoning-Data

Collection

2 items • Updated Oct 19, 2025

upvoted a paper about 1 year ago

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Paper • 2510.02263 • Published Oct 2, 2025 • 9

updated a Space about 1 year ago

Running

VibeCoder Flowstate

🐳

Enhance coding flow with ambient visuals and music

published a Space about 1 year ago

Running

VibeCoder Flowstate

🐳

Enhance coding flow with ambient visuals and music

liked a dataset about 1 year ago

inclusionAI/MultiEdit

Viewer • Updated Sep 19, 2025 • 108k • 65 • 21

authored a paper about 1 year ago

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

Paper • 2509.14638 • Published Sep 18, 2025 • 15

upvoted a paper about 1 year ago

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

Paper • 2509.15194 • Published Sep 18, 2025 • 33

New activity in inclusionAI/MultiEdit about 1 year ago

Sourcing

1

#1 opened about 1 year ago by deleted

upvoted 2 papers about 1 year ago

MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks

Paper • 2509.14638 • Published Sep 18, 2025 • 15

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Paper • 2509.08721 • Published Sep 10, 2025 • 665