Topics

3 Interpretability Opening the model up — circuits, features, and what "explaining a behaviour" actually means. 4 Reasoning & Memory How models hold context, carry state, and compose steps beyond next-token prediction. 1 Alignment & RLHF What training on human preference does to a model over time, and what it quietly costs. 4 Evaluation & Detection Measuring what models do rather than what benchmarks say they do. 2 Multilingual & Indic NLP Failure modes that only appear once you leave English. 1 Multi-Agent Systems What emerges when models talk to each other instead of to us. 3 Safety & Verification Guarantees, specifications, and the gap between a proof and a deployed system. 2 Vision & Video Perception systems, and what they can and cannot infer from what they see. 1 Systems & Hardware Inference where the compute budget is real — on-device, at the edge, off the datacentre. 1 Accessibility & Low-Resource Research agendas for the users and languages that datasets leave out. 4 Mathematical Foundations Category theory, sheaves, and formal structure applied to systems that were built empirically. 2 Cognition & Consciousness The uncomfortable questions at the edge of the field. 1 Security & Defence Applied systems built for threat detection and situational awareness.