Xiang Li
- Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
- Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
- On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
- REOBench: Benchmarking Robustness of Earth Observation Foundation Models
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
- See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
- Statistical Inference under Performativity
- Towards Understanding the Mechanisms of Classifier-Free Guidance
- Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
- Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation