Profiles2024-2025
Haonan Lin
Xi'an Jiaotong University
8Papers
0Last author
20Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- SpotActor: Training-Free Layout-Controlled Consistent Image GenerationAuthor 4 of 9AAAI 2025 · 13 citations
- Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention ReallocationAuthor 4 of 9NeurIPS 2025 · 4 citations
- Unleashing the Potential of Model Bias for Generalized Category DiscoveryAuthor 2 of 8AAAI 2025 · 1 citation
- Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion SamplingAuthor 4 of 7ICLR 2025
- Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local AttentionAuthor 5 of 9CVPR 2025
- OneActor: Consistent Subject Generation via Cluster-Conditioned GuidanceAuthor 3 of 8NeurIPS 2024 · 16 citations
- Generalized Category Discovery with Large Language Models in the LoopAuthor 4 of 11ACL Findings 2024 · 10 citations
- DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face GenerationAuthor 1 of 9CVPR 2024
