Mihir Parmar

CANVAS: Continuity-Aware Narrative Generation via Visual Agentic Storyboarding . Findings of Empirical Methods in Natural Language Processing , 2026.

WhatIf-Bench: Benchmarking Intervention-Aware Time Series Forecasting

This work introduces WhatIf-Bench, a benchmark measuring how well forecasters use covariates to forecast a target's response to future events, and reveals generalization to Novel futures as the core challenge, and offers a testbed toward arbitrary scenario analysis.

Twice Upon a Time: Complementary Representations for Time-Series Reasoning

This model combines two visual views: line plots preserve absolute measurements and the observed coordinate frame, while normalized delay embeddings factor out positive amplitude rescaling and offsets while exposing temporal structure.

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

This work proposes SEER (Self-Evolving Event Reasoning and Retrieval), a closed-loop framework that dynamically optimizes event conditioning for time series forecasting and consistently outperforms state-of-the-art time series foundation models and language model baselines.

AIM: Agentic Idea Management for Automated Research

It is shown that explicit idea-level allocation makes semantic coverage directly controllable, and that broader coverage becomes increasingly valuable when competitive research directions are sparse among many plausible alternatives.

Locating Hidden Failures Makes Long-Horizon Agents More Reliable

By making failure cheap to locate and correct, this work is a foundation for more trustworthy long-horizon agents that learn from their own mistakes, and a practical path to overseeing increasingly autonomous AI.