Yeqin Fan

yqfan's activity

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

upvoted a paper about 5 hours ago

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Paper • 2610.13912 • Published 6 days ago • 43

upvoted a paper 1 day ago

A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning

Paper • 2606.03335 • Published 9 days ago • 28

upvoted a paper 2 days ago

PhysEvo: Astra Can Act, Let It

Paper • 2610.08995 • Published 9 days ago • 89

upvoted a paper 4 days ago

Adaptive Latent Capacity for World Models

Paper • 2609.32921 • Published 19 days ago • 24

upvoted a paper 6 days ago

Capability-Driven Self-Evolution of Agent Memory

Paper • 2610.06361 • Published 10 days ago • 20

upvoted 2 papers 8 days ago

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 13 days ago • 34

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 16 days ago • 140

upvoted 2 papers 10 days ago

OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

Paper • 2609.39903 • Published 15 days ago • 64

HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents

Paper • 2609.38008 • Published 16 days ago • 48

upvoted 2 papers 12 days ago

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published 19 days ago • 327

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 17 days ago • 396

upvoted a paper 13 days ago

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published 17 days ago • 181

upvoted a paper 15 days ago

TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding

Paper • 2609.30670 • Published 20 days ago • 11

upvoted 5 papers 17 days ago

The Past Frames the Future: Memory for Autoregressive Video Generation

Paper • 2609.28466 • Published 22 days ago • 66

CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies

Paper • 2609.24118 • Published 24 days ago • 28

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 479

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Paper • 2609.26796 • Published 23 days ago • 37

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 29 days ago • 85

upvoted a paper 19 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 23 days ago • 56

upvoted a paper 20 days ago

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

Paper • 2609.23986 • Published 24 days ago • 30