Fangyuan Yu PRO

Ksgk-fy's activity

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

upvoted 2 papers 12 days ago

Tool Learning with Foundation Models

Paper • 2304.08354 • Published Apr 17, 2023 • 3

How Far is Video Generation from World Model: A Physical Law Perspective

Paper • 2411.02385 • Published 15 days ago • 32

upvoted 6 papers 13 days ago

Improving Steering Vectors by Targeting Sparse Autoencoder Features

Paper • 2411.02193 • Published 15 days ago • 1

Adaptive Length Image Tokenization via Recurrent Allocation

Paper • 2411.02393 • Published 15 days ago • 12

Thinking Forward and Backward: Effective Backward Planning with Large Language Models

Paper • 2411.01790 • Published 15 days ago • 1

Wave Network: An Ultra-Small Language Model

Paper • 2411.02674 • Published 14 days ago • 3

DroidSpeak: Enhancing Cross-LLM Communication

Paper • 2411.02820 • Published 14 days ago • 1

Inference Optimal VLMs Need Only One Visual Token but Larger Models

Paper • 2411.03312 • Published 14 days ago • 6

upvoted a paper 15 days ago

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Paper • 2410.23218 • Published 20 days ago • 46

upvoted a paper 17 days ago

nGPT: Normalized Transformer with Representation Learning on the Hypersphere

Paper • 2410.01131 • Published Oct 1 • 8

upvoted 2 papers 19 days ago

iVideoGPT: Interactive VideoGPTs are Scalable World Models

Paper • 2405.15223 • Published May 24 • 12

Energy-Based Diffusion Language Models for Text Generation

Paper • 2410.21357 • Published 22 days ago • 1

upvoted 6 papers 21 days ago

Pyramidal Flow Matching for Efficient Video Generative Modeling

Paper • 2410.05954 • Published Oct 8 • 37

Hyperbolic Deep Reinforcement Learning

Paper • 2210.01542 • Published Oct 4, 2022 • 1

AgentKit: Flow Engineering with Graphs, not Coding

Paper • 2404.11483 • Published Apr 17 • 2

The Scene Language: Representing Scenes with Programs, Words, and Embeddings

Paper • 2410.16770 • Published 28 days ago • 1

MCSD: An Efficient Language Model with Diverse Fusion

Paper • 2406.12230 • Published Jun 18 • 1

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Paper • 2410.10812 • Published Oct 14 • 14

upvoted 2 papers 22 days ago

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Paper • 2410.13835 • Published Oct 17 • 1

In-Context Learning Enables Robot Action Prediction in LLMs

Paper • 2410.12782 • Published Oct 16 • 1