Sep 08, 2026

Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher

A workshop by Harshul Jain and Tanmay Sah breaks down LLM inference optimization from first principles, addressing memory, TTFT, and throughput issues. It covers foundational concepts like KV cache mathematics and the prefill/decode phases, then dives into model-side optimizations (quantization, attention variants like GQA, FlashAttention) and serving-side techniques (Paged Attention, continuous batching, prefix caching, KV quantization). The session concludes with benchmarks of popular inference engines like vLLM and SGLang, highlighting their strengths for different workloads, and outlines future research directions.

Sep 01, 2026

Building AI That Optimizes AI

Wafer (S24) is a fast AI inference cloud that runs open-source models at industry-leading speeds by using AI agents to optimize GPUs across the entire stack. This unique approach allows them to deliver the low cost of open source with the latency of much smaller models. The company recently raised a $40 million Series A after achieving rapid growth by making GLM 5.2 run 2-3x faster than competitors, driving significant customer adoption due to speed, not just cost, which is crucial for latency-sensitive applications like voice agents.

Aug 25, 2026

Einstein Arena: Harnessing Collective Agent Intelligence for Open Science — James Zou, Together AI

James Zou presents a novel approach to AI development by advocating for the design of environments over workflows, fostering emergent intelligence and creativity. He introduces the **Einstein Arena**, where AI agents collaboratively and competitively solved open scientific problems like the kissing number problem, achieving breakthrough results (e.g., 604 spheres in 11 dimensions). The same principles successfully optimized GPU kernels, leading to 2x+ speedups. He also discusses **DSGym**, an environment for data science agents, addressing shortcomings of existing benchmarks by eliminating 'shortcuts' and enabling the training of high-performing, fine-tuned open-source models runnable on laptops.

Jul 31, 2026

Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Olive Song

Olive Song, RL lead at MiniMax, details the engineering behind MiniMax's open-weight models, focusing on M3's multimodal and agentic capabilities, the necessity of day-zero inference stack readiness, and continuous GPU kernel optimization. She discusses multimodal training challenges, long-horizon task evaluation, and expresses optimism for open models rapidly closing the gap with frontier labs.

Jul 30, 2026

First Steps Toward Automated AI Research — Richard Socher, CEO Recursive AI

Richard Socher introduces the "Eureka machine," a concept for automating scientific research and invention through AI. Inspired by open-ended evolution and Karl Popper's philosophy of science, he argues that AI can compress the timeline of scientific discovery, overcoming human-centric bottlenecks. The machine relies on four pillars (knowledge, data, simulations, physical labs) orchestrated by an agent swarm, requiring a rethinking of existing infrastructure. Recursive Self-Improvement (RSI), where AI improves its own code and addresses its shortcomings, is presented as the path forward, with early proof points in model optimization, training speed, and GPU kernel efficiency.

Jul 15, 2026

Computer-Use 2.0: Agents Just Got Multi-Cursor — Francesco Bonacci, Cua

This talk introduces cua driver, an open-source tool enabling AI agents to interact with computer GUIs in the background across macOS, Windows, and Linux by leveraging accessibility APIs. It details CUABench, a robust evaluation framework with over 130 verifiable tasks designed to benchmark and ensure the trustworthiness of computer-using agents, revealing current limitations in complex tasks like circuit design. Finally, it presents cua fleet, an infrastructure solution that optimizes GPU utilization and reduces costs for RL training of these agents by dynamically managing sandbox environments.