Profiles2022-2026ORCID 0000-0001-6332-2785
Haonan Lu
OPPO AI Center
20Papers
6Last author
51Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation LearningAuthor 7 of 7AAAI 2026 · 15 citations
- Pluggable Pruning with Contiguous Layer Distillation for Diffusion TransformersAuthor 6 of 6CVPR 2026 · 7 citations
- DRIFT: Difference-Aware Reinforcement Through Iterative Fine-Tuning for Language ModelAuthor 3 of 3AAAI 2026 · 1 citation
- Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile AutomationAuthor 4 of 5AAAI 2026 · 1 citation
- HAIT: Hybrid Adversarial Iterative Training for Mitigating Object Hallucination in Large Vision–Language ModelsAuthor 6 of 6CVPR Findings 2026
- StreamRAG: Enhancing Real-Time Video Understanding with Retrieval AugmentationAuthor 7 of 9CVPR 2026
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language ModelsAuthor 5 of 6AAAI 2025 · 28 citations
- SCott: Accelerating Diffusion Models with Stochastic Consistency DistillationAuthor 8 of 9AAAI 2025 · 17 citations
- InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction DetectionAuthor 7 of 8NeurIPS 2025 · 3 citations
- X2i: Seamless Integration of Multimodal Understanding Into Diffusion Transformer Via Attention DistillationAuthor 5 of 6ICCV 2025 · 1 citation
- Advancing Text-to-3D Generation with Linearized Lookahead Variational Score DistillationAuthor 4 of 5ICCV 2025
- Free-Moref: Instantly Multiplexing Context Perception Capabilities of Video-Mllms Within Single InferenceAuthor 6 of 9ICCV 2025
- HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility EvaluatorAuthor 6 of 11CVPR 2025
- Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion ModelsAuthor 5 of 6AAAI 2024 · 97 citations
- Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuningAuthor 4 of 4SIGGRAPH 2024 · 71 citations
- Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360° Image OutpaintingAuthor 3 of 9IEEE VR 2024 · 12 citations
- An Evaluation Mechanism of LLM-based Agents on Manipulating APIsAuthor 4 of 4EMNLP Findings 2024 · 4 citations
- Probing Language Models for Pre-training Data DetectionAuthor 4 of 6ACL 2024 · 4 citations
- Interactive Interior Design Recommendation via Coarse-to-fine Multimodal Reinforcement LearningAuthor 5 of 7ACM MM 2023 · 12 citations
- GammaE: Gamma Embeddings for Logical Queries on Knowledge GraphsAuthor 4 of 5EMNLP 2022 · 14 citations
