Research

Papers on food embeddings, physical AI, and when combining language models actually helps.

• When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier ModelsJun 2026

  Combining LLMs rarely beats the single best model. A co-failure ceiling, measured across 67 frontier models.

• Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing SoJun 2026

  Robot flash memory as depreciating capital, with a shadow price on every write.

• AEGIS: A Backup Reflex for Physical AIJun 2026

  Detecting imminent manipulation failure from a weak policy's internal states, then switching to a stronger one just in time.

• AURA: Action-Gated Memory for Robot Policies at Constant VRAMJun 2026

  Write to memory only when it would change the next action.

• Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM DecodeMay 2026

  Why faster GPUs disappoint at batch-1: launch overhead, not bandwidth.

• Epicure: Navigating the Emergent Geometry of Food Ingredient EmbeddingsMay 2026

  Ingredient embeddings trained on 4.14M recipes, from chemistry to recipe context.

• Epicure: Multidimensional Flavor Structure in Food Ingredient EmbeddingsApr 2026

  Fifteen independent dimensions of taste, texture, geography and culture, recovered from embedding space.