Institution profile

HHMI Janelia Research Campus

Academic institutionnorthamerica · us
Official website
Research library14linked papers
Opportunities0open roles
Selected work

Representative Papers

Agent-Centric Animal Pose Forecasting

Jul 21, 2026

This work proposes an agent-centric autoregressive generative model to algorithmically elucidate the mechanisms of perception, internal modeling, planning, and action generation in individual and collective animal behavior. Operating in an egocentric coordinate frame, the model processes pose trajectory data and predicts discretized action sequences to naturally emulate the behavioral constraints inherent to an organism’s self-referential perspective. The framework supports parallel multi-agent representations, enabling complex social behaviors to emerge spontaneously from each agent’s independent perception of and response to others. An accompanying open-source library provides composable action representations and systematic evaluation tools. Experiments demonstrate that the model accurately captures the distribution of social behaviors in courting fruit fly groups and exhibits strong cross-domain transferability.

0 citationsRead paper

A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline

Jun 05, 2026

Current AI systems struggle to autonomously execute end-to-end scientific discovery pipelines in neuroscience, particularly due to a lack of capability in assessing scientific plausibility. This work presents the first systematic evaluation of general-purpose code-generating agents on a real-world, large-scale optogenetics task in Drosophila, whose scale and complexity substantially exceed existing benchmarks. By integrating iterative code generation, visualization of intermediate outputs, and rigorous domain-expert-driven assessment, the study reveals that while agents can successfully complete individual pipeline stages, they fail to reliably orchestrate the full workflow. Performance degrades markedly in the absence of predefined evaluation criteria. These findings highlight critical limitations in AI’s capacity for scientific reasoning and self-evaluation, and propose principles for constructing and evaluating agent-based approaches to open-ended scientific problems.

0 citationsRead paper

Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model

May 15, 2026

This study addresses the challenge of simultaneously extracting abstract relational structures from continuous high-dimensional dynamic experiences and enabling cross-context knowledge transfer. Inspired by the neural mechanisms of the hippocampus (HPC) and medial entorhinal cortex (MEC), the work proposes the first self-supervised hierarchical world model that functionally disentangles these two brain regions: an inverse model captures relational structure, while velocity-driven path integration decouples structural representations in the MEC from episodic details encoded in the HPC. This framework unifies structure discovery and reuse, demonstrating superior abstraction capabilities on raw transformation-based dynamic tasks and achieving robust prediction and generalization across multiple contexts.

0 citationsRead paper
Recent publications

Latest Papers

Agent-Centric Animal Pose Forecasting

Jul 21, 2026

This work proposes an agent-centric autoregressive generative model to algorithmically elucidate the mechanisms of perception, internal modeling, planning, and action generation in individual and collective animal behavior. Operating in an egocentric coordinate frame, the model processes pose trajectory data and predicts discretized action sequences to naturally emulate the behavioral constraints inherent to an organism’s self-referential perspective. The framework supports parallel multi-agent representations, enabling complex social behaviors to emerge spontaneously from each agent’s independent perception of and response to others. An accompanying open-source library provides composable action representations and systematic evaluation tools. Experiments demonstrate that the model accurately captures the distribution of social behaviors in courting fruit fly groups and exhibits strong cross-domain transferability.

0 citationsRead paper

A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline

Jun 05, 2026

Current AI systems struggle to autonomously execute end-to-end scientific discovery pipelines in neuroscience, particularly due to a lack of capability in assessing scientific plausibility. This work presents the first systematic evaluation of general-purpose code-generating agents on a real-world, large-scale optogenetics task in Drosophila, whose scale and complexity substantially exceed existing benchmarks. By integrating iterative code generation, visualization of intermediate outputs, and rigorous domain-expert-driven assessment, the study reveals that while agents can successfully complete individual pipeline stages, they fail to reliably orchestrate the full workflow. Performance degrades markedly in the absence of predefined evaluation criteria. These findings highlight critical limitations in AI’s capacity for scientific reasoning and self-evaluation, and propose principles for constructing and evaluating agent-based approaches to open-ended scientific problems.

0 citationsRead paper

Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model

May 15, 2026

This study addresses the challenge of simultaneously extracting abstract relational structures from continuous high-dimensional dynamic experiences and enabling cross-context knowledge transfer. Inspired by the neural mechanisms of the hippocampus (HPC) and medial entorhinal cortex (MEC), the work proposes the first self-supervised hierarchical world model that functionally disentangles these two brain regions: an inverse model captures relational structure, while velocity-driven path integration decouples structural representations in the MEC from episodic details encoded in the HPC. This framework unifies structure discovery and reuse, demonstrating superior abstraction capabilities on raw transformation-based dynamic tasks and achieving robust prediction and generalization across multiple contexts.

0 citationsRead paper