Fangyuan Yu PRO

Ksgk-fy's activity

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

updated a collection 13 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

upvoted a paper 13 days ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 18 days ago • 108

updated a collection 18 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

updated a model 23 days ago

Ksgk-fy/forgetting-gap-qwen3-4b-s0

Text Generation • 4B • Updated 23 days ago • 320

published a model 23 days ago

Ksgk-fy/forgetting-gap-qwen3-4b-s0

Text Generation • 4B • Updated 23 days ago • 320

updated a dataset about 1 month ago

Ksgk-fy/open-reasoning-rlvr-24k

Viewer • Updated about 1 month ago • 25.5k • 190

published a dataset about 1 month ago

Ksgk-fy/open-reasoning-rlvr-24k

Viewer • Updated about 1 month ago • 25.5k • 190

updated a collection about 1 month ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

upvoted 2 papers about 1 month ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published Jul 22 • 36

An Exam for Active Observers

Paper • 2607.16165 • Published Jul 17 • 25

updated a collection about 2 months ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

upvoted a paper about 2 months ago

Distilled Reinforcement Learning for LLM Post-training

Paper • 2607.17247 • Published Jul 19 • 12

updated a collection about 2 months ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

upvoted a paper about 2 months ago

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

Paper • 2607.11886 • Published Jul 13 • 86

updated a collection about 2 months ago

Cognition

Collection

Perception and abstraction. Each modality is tokenized and embedded into vectors for model to comprehend. • 201 items • Updated Jul 20 • 6

upvoted a paper about 2 months ago

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

Paper • 2607.13124 • Published Jul 14 • 20

updated 2 collections about 2 months ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7

RL

Collection

7 items • Updated Jul 20 • 1

upvoted a paper about 2 months ago

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

Paper • 2607.05394 • Published Jul 8 • 150

updated a collection about 2 months ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 141 items • Updated 13 days ago • 7