Kun Li

GLOBA: Rethinking Parameter Conflicts in Model Merging AAAI 2026 Sequence-Free for Compound Protein Interaction Prediction AAAI 2026 VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models AAAI 2026 DLVINet: Advancing Dual-Lens Video Inpainting Beyond Parallax Constraints AAAI 2026 Can Molecular Evolution Mechanism Enhance Molecular Representation? AAAI 2026 Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees ACL 2026 InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features AAAI 2026 CoMA-SLAM: Collaborative Multi-Agent Gaussian SLAM with Geometric Consistency AAAI 2026 Reinforcement Learning on Pre-Training Data ACL 2026 Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents ACL 2026 Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution ACL 2025 ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning AAAI 2025 Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition AAAI 2025 Patch-level Sounding Object Tracking for Audio-Visual Question Answering AAAI 2025 BotSim: LLM-Powered Malicious Social Botnet Simulation AAAI 2025 LLM-Based Behavior Prediction for Social Media Users with Continuous Memory AACL 2025 Capture the Key in Reasoning to Enhance CoT Distillation Generalization ACL 2025 Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains ACL 2025 DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent COLING 2025 AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment EMNLP 2025 RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning EMNLP 2025 Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning EMNLP 2025 Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots EMNLP 2025 RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters ICCV 2025 BVINet: Unlocking Blind Video Inpainting with Zero Annotations ICCV 2025 MMAD: Multi-label Micro-Action Detection in Videos ICCV 2025 Prompt-Aware Controllable Shadow Removal IJCAI 2025 Drafting and Revision: Advancing High-Fidelity Video Inpainting IJCAI 2025 LLM-Based Behavior Prediction for Social Media Users with Continuous Memory IJCNLP 2025 EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer AAAI 2024 Microkernel Goes General: Performance and Compatibility in the HongMeng Production Microkernel OSDI 2024 Beyond Read-Only: Crafting a Comprehensive Chinese Text-to-SQL Dataset for Database Manipulation and Query NAACL 2024 Zero-shot Learning for Preclinical Drug Screening IJCAI 2024 Contrastive Learning Drug Response Models from Natural Language Supervision IJCAI 2024 Solving Motion Planning Tasks with a Scalable Generative Model ECCV 2024 LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging CVPR 2024 Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints CVPR 2024 Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture CVPR 2024 Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers EMNLP 2024 Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation EMNLP 2024 KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matching AAAI 2024 CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability EMNLP 2023 MeaeQ: Mount Model Extraction Attacks with Efficient Queries EMNLP 2023 SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting EMNLP 2023 Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer ICCV 2023 Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning ICCV 2023 Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing CVPR 2023 Crowd3D: Towards Hundreds of People Reconstruction From a Single Image CVPR 2023 FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction NIPS 2022 AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds AAAI 2022 Grounded Dialogue Generation with Cross-encoding Re-ranker, Grounding Span Prediction, and Passage Dropout ACL 2022 High-Fidelity Human Avatars From a Single RGB Camera CVPR 2022 PISE: Person Image Synthesis and Editing With Decoupled GAN CVPR 2021 Transformer Based End-to-End Mispronunciation Detection and Diagnosis INTERSPEECH 2021 Implicit Transformer Network for Screen Content Image Continuous Super-Resolution NIPS 2021 Cross-MPI: Cross-Scale Stereo for Image Super-Resolution Using Multiplane Images CVPR 2021 Proposal-Free Video Grounding with Contextual Pyramid Network AAAI 2021 4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras CVPR 2020 Group Gated Fusion on Attention-Based Bidirectional Alignment for Multimodal Emotion Recognition INTERSPEECH 2020 GPS-Net: Graph-based Photometric Stereo Network NIPS 2020 Constituency Lattice Encoding for Aspect Term Extraction COLING 2020 Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation ACL 2020 Rebalancing Expanding EV Sharing Systems with Deep Reinforcement Learning IJCAI 2020 Unsupervised Discovery of Non-native Phonetic Patterns in L2 English Speech for Mispronunciation Detection and Diagnosis INTERSPEECH 2018 Personalized, Cross-Lingual TTS Using Phonetic Posteriorgrams INTERSPEECH 2016