Papers by Walter Zimmer

1 papers
CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing Vision-language models are prone to hallucinating nonexistent entities or events and missing subtle but critical visual cues.
Approach: They propose a Traffic VideoQA Benchmark that enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, mutual-exclusivity violation.
Outcome: The proposed model detects true hazards when an accident occurs, and rejects plausible-but-false hypotheses under near-identical counterfactual scenes.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations