Sicong Leng

8

Papers

484

Total Citations

Papers (8)

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio

Advancing Expert Specialization for Better MoE

From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning

Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy

Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

Constrained Layout Generation with Factor Graphs

Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention