Fangyuan Yu PRO

Ksgk-fy's activity

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

upvoted 2 papers 1 day ago

Towards Pixel-Level VLM Perception via Simple Points Prediction

Paper • 2601.19228 • Published 4 days ago • 14

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published 2 days ago • 17

upvoted 2 papers 23 days ago

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published 25 days ago • 104

I-Con: A Unifying Framework for Representation Learning

Paper • 2504.16929 • Published Apr 23, 2025 • 30

upvoted 2 papers 29 days ago

Pretraining Frame Preservation in Autoregressive Video Memory Compression

Paper • 2512.23851 • Published Dec 29, 2025 • 24

Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process

Paper • 2512.23988 • Published Dec 30, 2025 • 16

upvoted 4 papers about 1 month ago

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published Dec 18, 2025 • 85

Latent Implicit Visual Reasoning

Paper • 2512.21218 • Published Dec 24, 2025 • 69

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

Paper • 2512.12602 • Published Dec 14, 2025 • 44

Bolmo: Byteifying the Next Generation of Language Models

Paper • 2512.15586 • Published Dec 17, 2025 • 17

upvoted 2 papers 3 months ago

Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 223

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Paper • 2510.25992 • Published Oct 29, 2025 • 48

upvoted 8 papers 4 months ago

Memory Retrieval and Consolidation in Large Language Models through Function Tokens

Paper • 2510.08203 • Published Oct 9, 2025 • 10

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 273

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26, 2025 • 186

The Three Regimes of Offline-to-Online Reinforcement Learning

Paper • 2510.01460 • Published Oct 1, 2025 • 1

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Paper • 2510.02263 • Published Oct 2, 2025 • 9

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26, 2025 • 43

Generalized Parallel Scaling with Interdependent Generations

Paper • 2510.01143 • Published Oct 1, 2025 • 6

Mem-α: Learning Memory Construction via Reinforcement Learning

Paper • 2509.25911 • Published Sep 30, 2025 • 14