Kun Gai

αMatte4K & μMatting: Dataset and Model for Ultra-Micro Precision Alpha Video Matting CVPR 2026 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation CVPR 2026 Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings AAAI 2026 CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning ACL 2026 FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion AAAI 2026 LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation AAAI 2026 Monet: Reasoning in Latent Visual Space Beyond Image and Language CVPR 2026 MultiShotMaster: A Controllable Multi-Shot Video Generation Framework CVPR 2026 OneRec-Think: In-Text Reasoning for Generative Recommendation ACL 2026 SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modeling CVPR 2026 Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models CVPR 2026 VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction CVPR 2026 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention ICCV 2025 Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering AAAI 2025 Imbalance in Balance: Online Concept Balancing in Generation Models ICCV 2025 Learning Cascade Ranking as One Network ICML 2025 Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains ICML 2025 LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application AAAI 2025 Making Transformer Decoders Better Differentiable Indexers ICLR 2025 RecFlow: An Industrial Full Flow Recommendation Dataset ICLR 2025 Towards Precise Scaling Laws for Video Diffusion Transformers CVPR 2025 Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs COLING 2024 DialogBench: Evaluating LLMs as Human-like Dialogue Systems NAACL 2024 Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues EMNLP 2024 Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios ACL 2024 Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models ACL 2024 RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance NeurIPS 2024 Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector EMNLP 2024 Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization ICLR 2024 Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization ICML 2024 KuaiSim: A Comprehensive Simulator for Recommender Systems NeurIPS 2023 ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor ICLR 2023 State Regularized Policy Optimization on Data with Dynamics Shift NeurIPS 2023 Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising ICML 2020 Learning Optimal Tree Models under Beam Search ICML 2020 Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising IJCAI 2020 Progressive Feature Polishing Network for Salient Object Detection AAAI 2020 Deep Interest Evolution Network for Click-Through Rate Prediction AAAI 2019 Joint Optimization of Tree-based Index and Deep Model for Recommender Systems NeurIPS 2019 Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation EMNLP 2019 Learning Kernels with Radiuses of Minimum Enclosing Balls NeurIPS 2010