Deli Zhao

Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors AAAI 2026 GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning EMNLP 2025 ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning EMNLP 2025 Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting ICCV 2025 Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions ACL 2025 FineReason: Evaluating and Improving LLMs’ Deliberate Reasoning through Reflective Puzzle Solving ACL 2025 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining ICCV 2025 Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents EMNLP 2025 Large Language-Geometry Model: When LLM meets Equivariance ICML 2025 MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra ICLR 2025 CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer ICLR 2025 Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy CVPR 2025 VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM CVPR 2025 Space Group Constrained Crystal Generation ICLR 2024 Lipschitz Singularities in Diffusion Models ICLR 2024 UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training NIPS 2024 Latent Space Editing in Transformer-Based Flow Matching AAAI 2024 Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner CVPR 2024 AnyDoor: Zero-shot Object-level Image Customization CVPR 2024 The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition ICLR 2023 VideoComposer: Compositional Video Synthesis with Motion Controllability NIPS 2023 FaceComposer: A Unified Model for Versatile Facial Content Creation NIPS 2023 Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone NIPS 2023 Customizable Image Synthesis with Multiple Subjects NIPS 2023 MomentDiff: Generative Video Moment Retrieval from Random to Real NIPS 2023 MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition CVPR 2023 RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training CVPR 2023 Neural Dependencies Emerging From Learning Massive Categories CVPR 2023 Dimensionality-Varying Diffusion Process CVPR 2023 LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook CVPR 2023 LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis ICCV 2023 Space-time Prompting for Video Class-incremental Learning ICCV 2023 ViM: Vision Middleware for Unified Downstream Transferring ICCV 2023 Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models ICCV 2023 Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos ICCV 2023 Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning ICCV 2023 Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval ICCV 2023 Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers ICCV 2023 Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning ICCV 2023 RLIPv2: Fast Scaling of Relational Language-Image Pre-Training ICCV 2023 Composer: Creative and Controllable Image Synthesis with Composable Conditions ICML 2023 Cones: Concept Neurons in Diffusion Models for Customized Generation ICML 2023 RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation ICML 2023 Improving GANs with A Dynamic Discriminator NIPS 2022 Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator NIPS 2022 Weakly Supervised High-Fidelity Clothing Model Generation CVPR 2022 Region-Based Semantic Factorization in GANs ICML 2022 Principled Knowledge Extrapolation with GANs ICML 2022 Rank Diminishing in Deep Neural Networks NIPS 2022 Low-Rank Subspaces in GANs NIPS 2021 Understanding Noise Injection in GANs ICML 2021 Uncertainty Principles of Encoding GANs ICML 2021 In-Domain GAN Inversion for Real Image Editing ECCV 2020 DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning NIPS 2018 Sparse Coding and Dictionary Learning With Linear Dynamical Systems CVPR 2016 Learning Stable Linear Dynamical Systems with the Weighted Least Square Method IJCAI 2016 Scalable Gaussian Process Regression Using Deep Neural Networks IJCAI 2015 A New Retraction for Accelerating the Riemannian Three-Factor Low-Rank Matrix Completion Algorithm CVPR 2015 Network Representation Learning with Rich Text Information IJCAI 2015 Zeta Hull Pursuits: Learning Nonconvex Data Hulls NIPS 2014 Distant Supervision for Relation Extraction with Matrix Completion ACL 2014 Face Recognition Using Face Patch Networks ICCV 2013 Face Recognition via Archetype Hull Ranking ICCV 2013 Cyclizing Clusters via Zeta Function of a Graph NIPS 2008