Agentic RL Training Recipes Training recipes, reward hacking, data mixing Agent Benchmarks and Evaluation Benchmarks, environments, and evaluation methodology for coding, tool use, computer use, and expert-level professional work. Agent Teams Coordination, communication, and cost efficiency in multi-agent systems, so that teams of agents can take on long-horizon work that no single agent finishes reliably. ML Systems Orchestration, parallelism, kernel-level efficiency, and the machinery that moves models from training runs into products. Probabilistic Graphical Models AI for Science Agentic laboratories and automated research systems, from scientific world models to benchmarks for drug discovery. Video Retrieval Video retrieval at TRECVID, from shot boundary detection and concept detection to search. Self-driving Vehicles Mining vehicle behaviors from multi-sensor data for scenario parsing, surveillance, and collision warning.