Madhav Kanda — accepted AI-conference papers

2026

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping

Dwip Dalal, Gautam Vashishtha, Utkarsh Mishra, Jeonghwan Kim, Madhav Kanda, Hyeonjeong Ha +3

ICLR 2026poster

Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perceptual grounding. We introduce AttWarp, a lightweight method that allocates more resolution to query-relevant content while compressing less informative…

Cited by 0 Source ↗Scholar ↗

2026

RefineStat: Efficient Exploration for Probabilistic Program Synthesis

Madhav Kanda, Shubham Ugare, Sasa Misailovic

ICLR 2026oral

Probabilistic programming offers a powerful framework for modeling uncertainty, yet statistical model discovery in this domain entails navigating an immense search space under strict domain‐specific constraints. When small language models are tasked with generating probabilistic programs, they frequ…

Cited by 0 Source ↗code ↗Scholar ↗