ERI

From GISAXS
Revision as of 15:45, 11 January 2025 by KevinYager (talk | contribs) (Created page with "'''ERI''' =Research Thrusts= ==Models== '''How to adapt frontier methods and foundation models to science?''' # Topical fine-tuning # Tool-use # Advanced retrieval-augmented...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

ERI

Research Thrusts

Models

How to adapt frontier methods and foundation models to science?

  1. Topical fine-tuning
  2. Tool-use
  3. Advanced retrieval-augmented generation (RAG++)
    • Novel: Pre-generation: Agents continually add content to RAG corpus. ("Pre-thinking" across many vectors.)
  4. Specialized tokenization/embedding (xVal, [IDK])
  5. Specialized sampling
    • Entropy sampling: measure uncertainty of CoT trajectories
    • Novel: Handoff sampling:
      • text-to-text (specialization, creativity, etc.)
      • text-to-tool (e.g. math)
      • test-to-field (integrate non-textual FM)


Agents

How to make AI agents smarter?

Exocortex

What is the right architecture for AI swarms?

Infrastructure

Architecture

What software architecture is needed?

  1. Code for scaffolding
  2. Scheme for inter-agent messaging (plain English w/ pointers, etc.)
  3. Data management

Hardware

How to implement inference-time compute for exocortex?

  1. Heterogeneous hardware
  2. Elastic (combine local & cloud)
  3. Workflow management

Human-Computer Interaction (HCI)

What should the HCI be?