ASSET Seminar: “Better Algorithms for Better Neighbors”
Nearest neighbor search has a long history in theoretical computer science, and in the past decade has seen an explosion of usage. This has been primarily driven by embedding models […]
Eli Burstein Lecture in Materials Science: “Toward Intelligent Metamaterial Machines,” Katia Bertoldi – Harvard University
Flexible mechanical metamaterials are engineered structures whose unique geometries allow them to display remarkable behaviors, especially in the nonlinear regime. These systems hold promise for enabling the next generation of […]
ASSET Seminar: “Formal Methods for Language Model Systems”
Formal methods are often dismissed as too rigid, complex, or unscalable for frontier language model systems (e.g., LLMs, VLMs, agentic systems). In this talk, I will challenge this assumption with […]
ASSET Seminar: “How can we enable LLM auditing?”
Oversight and auditing of AI systems is becoming increasingly difficult as people use systems in a wide variety of ways, with instructions expressed in natural language prompts. We can no […]
ASSET Seminar: “Towards discrete diffusion models for language and image generation”
We discuss discrete diffusion models that offer a unified framework for jointly modeling categorical data such as text and images. We present a new model that we have developed for […]
ASSET Seminar: “Beyond Photorealism: 3D Reconstruction and Generation with Multimodal and Physical Grounding”
Progress in 3D reconstruction and generation has accelerated rapidly, producing increasingly detailed geometry and photorealistic rendering. However, moving beyond photorealism requires models that not only look correct, but are also […]
ASSET Seminar: “From kernel machines to the linear representation hypothesis for monitoring and steering LLMs”
A trained Large Language Model (LLM) contains much of human knowledge. Yet, it is difficult to gauge the extent or accuracy of that knowledge, as LLMs do not always “know […]
ASSET Seminar: “Machine learning for discrete optimization: Theoretical foundations”
Many of the most important optimization problems in practice are massive in scale, mathematically complex, and involve numerous unknown parameters. Machine learning offers a powerful way to address these challenges […]
ASSET Seminar: “Why We Need Multimodal Generative AI for Time Series (and Video)”
“Synthesize a realistic electrocardiogram (ECG) from a patient’s medical record to stress-test a disease classifier while preserving privacy.” “Forecast home energy demand given location, EV usage, and an incoming winter […]
ASSET Seminar: “Improving Generative AI at Inference Time: Alignment, Reasoning, & Efficiency”
Modern generative AI is often improved through costly post-training (e.g., RLHF or preference tuning). This talk highlights a complementary alternative called inference-time methods. With the right inference-time objectives, search procedures, […]