PAST EVENTS
Self-Supervised Reinforcement Learning and Patterns in Time
Benjamin Eysenbach — Assistant Professor, Princeton
March 2026
Scalable Inference Algorithms for Large Language Models
Woomin Song — KAIST
March 2026
Artificial Hivemind: The Open-Ended Homogeneity of Language Models
Liwei Jiang — NVIDIA
March 2026
vLLM Compile Deep Dive
Ayush Satyam — PyTorch / vLLM Contributor
March 2026
Instance-wise Understanding in Computer Vision
Pierre Musacchio — Seoul National University, VGI Lab
Dec 2025
Determinism and Scalability in Post-Training RL Systems
Ethan Su — ex-AMD Research Scientist
Dec 13, 2025
OML: AI-native Cryptography for Open-Model Attribution and Control
Edoardo Contente — Sentient, AI Researcher
Dec 06, 2025
REFORM: Redefining Long-Context AI Inference
Woomin Song — KAIST PhD Student, NeurIPS 1st Author
Nov 22, 2025
NVIDIA Dynamo: High performance Open Source Interface
William Arnold — NVIDIA, Senior DL Algo Engineer
Nov 07, 2025
Introduction of dstack: AI container orchestration for AI teams
Andrey Cheptsov — dStack, CEO
Nov 01, 2025
Deep Dive: Embedding Model Inference in Production
Philip Kiely — Baseten, DevRel
Oct 11, 2025
Deep Dive: Optimizing Large-Scale RL with SGLang
Chenyang Zhao — ByteDance, SGLang Leader
Oct 18, 2025
Floating Point Non Associativity in Machine Learning
Brian Chau — IOI Gold Medalist, Network School
Oct 18, 2025
Deep Dive: Edge AI & Hardware co-Design
Marco Gonzalez — Red Hat, Senior Engineer
Sep 20, 2025
Understanding High Throughput LLM Inference Systems
Ayush Satyam — Red Hat, Software Engineer
Sep 13, 2025