Lune

Profiles2023-2026

Zhihong Zhu

Peking University

19Papers
0Last author
27Unique co-authors
2First author
0Solo

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

Recent papers19

  1. MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language ModelsAuthor 7 of 9ACL 2026 · 9 citations
  2. Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-AugmentationAuthor 5 of 10AAAI 2025 · 14 citations
  3. LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context InferenceAuthor 5 of 8EMNLP Findings 2024 · 21 citations
  4. Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task AlignmentAuthor 1 of 5AAAI 2024 · 16 citations
  5. Exploiting Auxiliary Caption for Video GroundingAuthor 5 of 6AAAI 2024 · 16 citations
  6. Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive DecodingAuthor 3 of 10EMNLP Findings 2024 · 11 citations
  7. MoBA: Mixture of Bi-directional Adapter for Multi-modal Sarcasm DetectionAuthor 2 of 5ACM MM 2024 · 11 citations
  8. XMeCap: Meme Caption Generation with Sub-Image AdaptabilityAuthor 3 of 5ACM MM 2024 · 7 citations
  9. Dual-oriented Disentangled Network with Counterfactual Intervention for Multimodal Intent DetectionAuthor 2 of 5EMNLP 2024 · 4 citations
  10. Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language UnderstandingAuthor 2 of 6ACL Findings 2024 · 3 citations
  11. MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-ExpertsAuthor 2 of 6ACL Findings 2024 · 2 citations
  12. Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game TheoryAuthor 2 of 6EMNLP 2024 · 1 citation
  13. Towards Multimodal-augmented Pre-trained Language Models via Self-balanced Expectation-Maximization IterationAuthor 3 of 6ACM MM 2024 · 1 citation
  14. Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report GenerationAuthor 4 of 6ICCV 2023 · 47 citations
  15. G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game TheoryAuthor 5 of 6ICCV 2023 · 32 citations
  16. ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language UnderstandingAuthor 4 of 6ACL Findings 2023 · 28 citations
  17. Towards Unified Spoken Language Understanding Decoding via Label-aware Compact Linguistics RepresentationsAuthor 1 of 5ACL Findings 2023 · 16 citations
  18. MRRL: Modifying the Reference via Reinforcement Learning for Non-Autoregressive Joint Multiple Intent Detection and Slot FillingAuthor 2 of 5EMNLP Findings 2023 · 13 citations
  19. MCLF: A Multi-grained Contrastive Learning Framework for ASR-robust Spoken Language UnderstandingAuthor 3 of 4EMNLP Findings 2023 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines