Sandeep P. Chinchali

Papers on Lattice

Total citations

Topics

h-index

Research focus

Multimodal Models (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Po-han Li (1)Shenghui Chen (1)U. Topcu (1)

Papers (1)

Jan 14, 2026

Po-han Li +3Jan 14, 2026

ViSIL: Unified Evaluation of Information Loss in Multimodal Video Captioning

Ditch BLEU and ROUGE: ViSIL offers a unified metric for multimodal video captioning that actually correlates with VQA performance and human judgment by measuring information loss via VLM inference.

Po-han Li, Shenghui Chen, U. Topcu +1

Multimodal Models Reasoning & Chain-of-Thought

Search

Sandeep P. Chinchali

Research focus

Frequent co-authors

Papers (1)