Mi Luo

PhD student, University of Texas at Austin

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

#5005 · Mi Luo, Zihui Xue, Alex Dimakis, Kristen Grauman

Debugging today's chain-of-thought reasoning for video understanding and introducing a novel reward for MLLM post-training to ground video reasoning in visual evidence.

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Seeing the Arrow of Time in Large Multimodal Models

#5306 · Zihui Xue, Mi Luo, Kristen Grauman

Finding that today's LMMs poorly grasp the arrow of time in video, we propose ArrowRL to enhance their temporal perception and AoTBench for rigorous evaluation.