孙奕辰's picture

孙奕辰

isabellat76

·

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

tencent/Hy-MT2-1.8B

liked a model 4 days ago

mokau/Zero-To-CAD-Qwen3-VL-2B

liked a model 4 days ago

tencent/Hy-MT2-30B-A3B

View all activity

Organizations

None yet

upvoted a paper 5 days ago

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Paper • 2605.14747 • Published 13 days ago • 143

upvoted 2 papers 6 days ago

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Paper • 2605.19995 • Published 8 days ago • 34

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published 15 days ago • 191

upvoted a paper 8 days ago

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

Paper • 2605.12882 • Published 14 days ago • 268

upvoted a paper 13 days ago

F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking

Paper • 2605.12995 • Published 14 days ago • 2

upvoted a paper 26 days ago

A Systematic Post-Train Framework for Video Generation

Paper • 2604.25427 • Published 29 days ago • 2

upvoted a paper about 1 month ago

Crowded in B-Space: Calibrating Shared Directions for LoRA Merging

Paper • 2604.16826 • Published Apr 18 • 18

upvoted 6 papers about 2 months ago

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published Apr 2 • 504

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published Apr 9 • 291

Therefore I am. I Think

Paper • 2604.01202 • Published Apr 2 • 33

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Paper • 2603.26164 • Published Mar 27 • 365

CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence

Paper • 2603.28032 • Published Mar 30 • 342

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Paper • 2603.19835 • Published Mar 20 • 351

upvoted 2 papers 2 months ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published Mar 16 • 153

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Paper • 2603.04597 • Published Mar 4 • 211