Fangyuan Yu PRO

Ksgk-fy's activity

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

upvoted 2 papers 2 days ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published 4 days ago • 30

An Exam for Active Observers

Paper • 2607.16165 • Published 9 days ago • 24

upvoted a paper 3 days ago

Distilled Reinforcement Learning for LLM Post-training

Paper • 2607.17247 • Published 7 days ago • 9

upvoted 2 papers 5 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 13 days ago • 84

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Paper • 2607.13124 • Published 12 days ago • 19

upvoted a paper 10 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 18 days ago • 137

upvoted 3 papers 28 days ago

Less is More: Early Stopping Rollout for On-Policy Distillation

Paper • 2605.27028 • Published May 26 • 15

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

Paper • 2605.28421 • Published May 27 • 48

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

Paper • 2606.26080 • Published Jun 24 • 11

upvoted a paper about 2 months ago

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published Jun 5 • 99

upvoted a paper 2 months ago

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Paper • 2605.18678 • Published May 18 • 79

upvoted a collection 2 months ago

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 227 items • Updated about 19 hours ago • 50

upvoted a paper 2 months ago

Dynamic Latent Routing

Paper • 2605.14323 • Published May 14 • 4

upvoted 2 papers 5 months ago

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Paper • 2602.22766 • Published Feb 26 • 45

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

Paper • 2602.12099 • Published Feb 12 • 62

upvoted 5 papers 6 months ago

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

Paper • 2602.03392 • Published Feb 3 • 59

Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention

Paper • 2602.01801 • Published Feb 2 • 29

LoopViT: Scaling Visual ARC with Looped Transformers

Paper • 2602.02156 • Published Feb 2 • 12

Towards Pixel-Level VLM Perception via Simple Points Prediction

Paper • 2601.19228 • Published Jan 27 • 19

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published Jan 28 • 21