Zhi Wang

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation ACL 2026 Bridging Lifelong and Multi-Task Representation Learning: An Algorithm and a Complexity Measure ALT 2026 DynamicEarth: How Far Are We from Open-Vocabulary Change Detection? AAAI 2026 IGen: Scalable Data Generation for Robot Learning from Open-World Images CVPR 2026 Medical Vision–Language Pretraining with LLM-Guided Temporal Supervision AAAI 2026 mmWaveFlow: Unified Enhancement and Generation of mmWave Human Point Clouds CVPR 2026 MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm AAAI 2026 Neural Collapse in Test-Time Adaptation CVPR 2026 Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation ACL 2026 SIAM: Towards Generalizable Articulated Object Modeling via Single Robot-Object Interaction AAAI 2026 Test-time Sparsity for Extreme Fast Action Diffusion CVPR 2026 Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World CVPR 2026 VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping CVPR 2026 Beyond A Single AI Cluster: A Survey of Decentralized LLM Training EMNLP 2025 CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning ICCV 2025 COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation CVPR 2025 DICE: Staleness-Centric Optimizations for Parallel Diffusion MoE Inference ICCV 2025 Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 Enhancing Implicit Neural Representations via Symmetric Power Transformation AAAI 2025 EVOS: Efficient Implicit Neural Training via EVOlutionary Selector CVPR 2025 JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration AAAI 2025 Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling ICCV 2025 PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment ICLR 2025 Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers CVPR 2025 SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images CVPR 2025 Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning ICLR 2024 Beyond task diversity: provable representation transfer for sequential multitask linear bandits NeurIPS 2024 Invertible Residual Rescaling Models IJCAI 2024 LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling NeurIPS 2024 MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation ECCV 2024 Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement NeurIPS 2024 Metric Learning from Limited Pairwise Preference Comparisons UAI 2024 Nonconvex Multiview Subspace Clustering Framework with Efficient Method Designs and Theoretical Analysis IJCAI 2024 OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments AAAI 2024 Procedural Level Generation with Diffusion Models from a Single Example AAAI 2024 Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning CVPR 2024 Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders AAAI 2024 Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding AAAI 2024 BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking NeurIPS 2023 Curriculum Multi-Negative Augmentation for Debiased Video Grounding AAAI 2023 ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices ICCV 2023 FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks AAAI 2023 GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization ICCV 2023 Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models ICCV 2023 Weakly-Supervised Semantic Segmentation for Histopathology Images Based on Dataset Synthesis and Feature Consistency Constraint AAAI 2023 bert2BERT: Towards Reusable Pretrained Language Models ACL 2022 Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance ECCV 2022 Online Continual Adaptation with Active Self-Training AISTATS 2022 Thompson Sampling for Robust Transfer in Multi-Task Bandits ICML 2022 Multitask Bandit Learning Through Heterogeneous Feedback Aggregation AISTATS 2021 Provably efficient multi-task reinforcement learning with model transfer NeurIPS 2021 A Spherical Convolution Approach for Learning Long Term Viewport Prediction in 360 Immersive Video AAAI 2020 Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition CVPR 2020 Better Fine-Tuning via Instance Weighting for Text Classification AAAI 2019