Parisa Kordjamshidi

Michigan State University

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (2)Robotics & Embodied AI (1)World Models & Planning (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Tianyi Ma (1)Kanishk Jain (1)Shravan Nayak (1)Nishanth Anand (1)

Papers (2)

Sep 8, 2026

1w ago

CLAMP: Constrained Decoding for Vision-Language Embodied Planning

Hallucinated objects and unexecutable actions in embodied planning don't require fine-tuning to fix: pairing a frozen VLM with inference-time symbolic masking and an HMM state lookahead guarantees feasible, grounded plans out of the box.

Tianyi Ma, Parisa Kordjamshidi

Multimodal Models Robotics & Embodied AI World Models & Planning

Apr 6, 2026

MilaApr 6, 2026·also CIFAR, McGill, Michigan State

Discovering Failure Modes in Vision-Language Models using RL

Forget hand-crafted prompts: RL can automatically unearth 36 new failure modes in VLMs that humans miss, revealing surprising blind spots in counting, spatial reasoning, and viewpoint understanding.

Kanishk Jain, Shravan Nayak, Parisa Kordjamshidi +2

Eval Frameworks & Benchmarks Multimodal Models Red-Teaming & Adversarial Robustness

Search

Parisa Kordjamshidi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)