Penghui Yang's picture

9 7 3

Penghui Yang

phyang

·

penghui-yang

AI & ML interests

Knowledge Distillation, Speculative Decoding

Recent Activity

upvoted a collection 8 days ago

authored a paper about 2 months ago

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

authored a paper about 2 months ago

AutoMAT: A Hierarchical Framework for Autonomous Alloy Discovery

View all activity

Organizations

upvoted a collection 8 days ago

SpecBundle

A collection of production-grade draft models for speculative decoding • 14 items • Updated 9 days ago • 11

upvoted a paper about 2 months ago

Diffusion Language Models are Super Data Learners

Paper • 2511.03276 • Published Nov 5, 2025 • 128

upvoted a paper 2 months ago

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published Oct 17, 2025 • 50

upvoted 3 papers 3 months ago

Imperceptible Jailbreaking against Large Language Models

Paper • 2510.05025 • Published Oct 6, 2025 • 33

Variational Reasoning for Language Models

Paper • 2509.22637 • Published Sep 26, 2025 • 69

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Paper • 2509.22638 • Published Sep 26, 2025 • 70

upvoted a paper 4 months ago

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

Paper • 2509.02479 • Published Sep 2, 2025 • 83