Siyuan Feng

Siyuan's activity

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

authored 7 papers 2 months ago

CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario

Paper • 1905.05217 • Published May 13, 2019

WebLLM: A High-Performance In-Browser LLM Inference Engine

Paper • 2412.15803 • Published Dec 20, 2024

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

Paper • 2207.04296 • Published Jul 9, 2022

Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging

Paper • 2404.09151 • Published Apr 14, 2024

Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving

Paper • 2509.17863 • Published Sep 22, 2025 • 1

ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems

Paper • 2510.26475 • Published Oct 30, 2025

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

Paper • 2512.04987 • Published Dec 4, 2025 • 80

authored a paper over 2 years ago

Relax: Composable Abstractions for End-to-End Dynamic Machine Learning

Paper • 2311.02103 • Published Nov 1, 2023 • 20