Profiles2023-2026ORCID 0000-0002-2120-5588
Li Yuan
Peng Cheng Laboratory
25Papers
10Last author
52Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers25
- WISE: World Knowledge-Informed Semantic Evaluation for Text-to-Image GenerationAuthor 12 of 12ICML 2026 · 195 citations
- Next Patch Prediction for AutoRegressive Visual GenerationAuthor 11 of 12AAAI 2026 · 24 citations
- AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety BasinAuthor 10 of 10AAAI 2026 · 19 citations
- SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE ModelsAuthor 5 of 5ICLR 2026 · 3 citations
- One-Way Policy Optimization for Self-Evolving LLMsAuthor 9 of 9ICML 2026 · 2 citations
- BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous ScienceAuthor 5 of 6ICML 2026
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger ScenesAuthor 6 of 7AAAI 2025 · 21 citations
- CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-stepAuthor 11 of 11NeurIPS 2025 · 9 citations
- Rethinking Text-based Protein Understanding: Retrieval or LLM?Author 7 of 8EMNLP 2025 · 7 citations
- HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationAuthor 5 of 6ACM MM 2025 · 4 citations
- E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event CamerasAuthor 7 of 8ACM MM 2025 · 3 citations
- MoH: Multi-Head Attention as Mixture-of-Head AttentionAuthor 3 of 4ICML 2025 · 2 citations
- Identity-Preserving Text-to-Video Generation by Frequency DecompositionAuthor 8 of 8CVPR 2025
- MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation ExpertsAuthor 3 of 4ICLR 2025
- Orthogonal Subspace Decomposition for Generalizable AI-Generated Image DetectionAuthor 10 of 10ICML 2025
- PiCO: Peer Review in LLMs based on Consistency OptimizationAuthor 8 of 8ICLR 2025
- UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model EvaluationAuthor 10 of 10CVPR 2025
- Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video UnderstandingAuthor 5 of 5CVPR 2024
- Regressor-Segmenter Mutual Prompt Learning for Crowd CountingAuthor 2 of 6CVPR 2024
- SynSP: Synergy of Smoothness and Precision in Pose Sequences RefinementAuthor 8 of 11CVPR 2024
- DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelAuthor 7 of 8ICCV 2023 · 95 citations
- IDRNet: Intervention-Driven Relation Network for Semantic SegmentationAuthor 5 of 6NeurIPS 2023 · 27 citations
- Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental LearningAuthor 5 of 6CVPR 2023
- Out-of-Candidate Rectification for Weakly Supervised Semantic SegmentationAuthor 7 of 9CVPR 2023
- Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation LearningAuthor 7 of 8CVPR 2023
