Lune

Profiles2021-2026

Qiong Wu

Xiamen University

9Papers
0Last author
24Unique co-authors
5First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers9

  1. Grounded Chain-of-Thought for Multimodal Large Language ModelsAuthor 1 of 7CVPR 2026 · 55 citations
  2. ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models Via Spatial-Temporal Forest ModelingAuthor 5 of 9CVPR Findings 2026
  3. SEC-FinTables: Evaluating Large Language Models for Detecting Logical Inconsistencies on Tabular DataAuthor 2 of 4ACL Findings 2026
  4. Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language ModelsAuthor 2 of 4AAAI 2025 · 99 citations
  5. What Kind of Visual Tokens Do We Need? Training-Free Visual Token Pruning for Multi-Modal Large Language Models from the Perspective of GraphAuthor 2 of 5AAAI 2025 · 27 citations
  6. Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsAuthor 1 of 7NeurIPS 2025 · 16 citations
  7. Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language ModelsAuthor 1 of 5ICLR 2025
  8. Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained ModelsAuthor 1 of 6NeurIPS 2023 · 16 citations
  9. Discover Cross-Modality Nuances for Visible-Infrared Person Re-IdentificationAuthor 1 of 8CVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines