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.

  arXiv:2606.27288 · pdf

  bibtexhide bibtex

  @misc{chen2026whendoescombininglanguage,
    title={When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models},
    author={Josef Chen},
    year={2026},
    eprint={2606.27288},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2606.27288}
  }

• 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.

  arXiv:2606.18144 · pdf

  bibtexhide bibtex

  @misc{chen2026memoryasawasting,
    title={Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So},
    author={Josef Liyanjun Chen},
    year={2026},
    eprint={2606.18144},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2606.18144}
  }

• 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.

  arXiv:2606.06660 · pdf

  bibtexhide bibtex

  @misc{chen2026aegisabackupreflex,
    title={AEGIS: A Backup Reflex for Physical AI},
    author={Josef Chen},
    year={2026},
    eprint={2606.06660},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2606.06660}
  }

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

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

  arXiv:2606.02775 · pdf

  bibtexhide bibtex

  @misc{chen2026auraactiongatedmemory,
    title={AURA: Action-Gated Memory for Robot Policies at Constant VRAM},
    author={Josef Chen},
    year={2026},
    eprint={2606.02775},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2606.02775}
  }

• 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.

  arXiv:2605.30571 · pdf

  bibtexhide bibtex

  @misc{chen2026memoryboundbutnot,
    title={Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM Decode},
    author={Josef Chen},
    year={2026},
    eprint={2605.30571},
    archivePrefix={arXiv},
    primaryClass={cs.AR},
    url={https://arxiv.org/abs/2605.30571}
  }

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

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

  arXiv:2605.22391 · pdf · explorer

  bibtexhide bibtex

  @misc{radzikowski2026epicurenavigatingtheemergent,
    title={Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings},
    author={Jakub Radzikowski and Josef Chen},
    year={2026},
    eprint={2605.22391},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2605.22391}
  }

• Epicure: Multidimensional Flavor Structure in Food Ingredient EmbeddingsApr 2026

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

  arXiv:2604.22776 · pdf · explorer

  bibtexhide bibtex

  @misc{radzikowski2026epicuremultidimensionalflavorstructure,
    title={Epicure: Multidimensional Flavor Structure in Food Ingredient Embeddings},
    author={Jakub Radzikowski and Josef Chen},
    year={2026},
    eprint={2604.22776},
    archivePrefix={arXiv},
    primaryClass={cs.CY},
    url={https://arxiv.org/abs/2604.22776}
  }