activity
20242026
most citedLazarus: Resilient and Elastic Training of Mixture-of-Experts Models

2 citations · 3 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models

Linfeng Fan, Yuan Tian, Ziwei Li +1

Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing miti…