selected research

Publications.

Research across multimodal models, agents, conversational AI, and human-computer interaction.

  1. 01 MultiNet 2.0 · technical report · 2026 Goal progress decays with task horizon for frontier VLMs in interactive 2D environments
  2. 02 multimodal generalization · CVPR 2026 MMFM Benchmarking the generality of vision-language-action models
  3. 03 MultiNet v1.0 · comprehensive benchmark · 2025 A comprehensive benchmark for evaluating multimodal reasoning and action models across diverse domains
  4. 04 MultiNet · ICML 2025 CodeML An open-source software toolkit & benchmark suite for the evaluation and adaptation of multimodal action models
  5. 05 MultiNet v0.2 · procedural environments · 2025 Benchmarking vision, language, & action models in procedurally generated, open-ended action environments
  6. 06 MultiNet v0.1 · robotics · 2024 Benchmarking vision, language, & action models on robotic learning tasks
  7. 07 conversational AI · evaluation KULCQ: an unsupervised keyword-based utterance-level clustering quality metric
  8. 08 education · generative AI Jill Watson: a virtual teaching assistant powered by ChatGPT
  9. 09 handwriting · deep learning An end-to-end, interactive deep-learning-based annotation system for cursive and print English handwritten text