Research archive
Publications and preprints.
Find me on Google Scholar9 papers
Findings of EMNLP 2026 · Accepted
Evaluating how anti-sycophancy interventions affect a model's ability to revise answers when new evidence is valid.
arXiv 2026 · Preprint
A benchmark that audits what an agent's long-term memory actually retains about its users.
2026 · Survey preprint
A survey of time-series agents that connects perception, reasoning, action, memory, and world models with reliability.
arXiv 2026 · Preprint
Auditable correction of PDE foundation-model forecasts through global correction and targeted local refinement.
COLM 2026 · Accepted
Understanding and improving the trade-off between answer quality and reasoning-path exploration in diffusion LLMs.
arXiv 2026 · Preprint
An AI agent for interpretable cell-type annotation with expert feedback and zero-shot biological reasoning.
arXiv 2025 · Preprint
A world model that simulates future visual states from interaction history and natural-language actions.
ACM Multimedia 2025 · Demo
An interactive video analysis system that grounds detected actions and their arguments in 3D space.
NeurIPS 2025 · Poster
LLMs reason directly over single-cell data and bioinformatics tools to produce interpretable scientific analyses.
No papers match your search. Try a different keyword or filter.