Yong Li

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration CVPR 2026 CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments ACL 2026 DehazeGS: Seeing Through Fog with 3D Gaussian Splatting AAAI 2026 Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning ACL 2026 EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training AAAI 2026 EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering ACL 2026 EROICA: Online Performance Troubleshooting for Large-scale Model Training NSDI 2026 Fresco: Frequency-Spatial Consistent Optimization for Fine-Grained Head Avatar Modeling CVPR 2026 GeoProblem Factory: A Visual Interaction System for Solvable and Controllable Geometric Problem Generation by Leveraging Symbolic Deduction Engine AAAI 2026 Good-for-MDP State Reduction for Stochastic LTL Planning AAAI 2026 History-Aware Reasoning for GUI Agents AAAI 2026 ProBench: Benchmarking GUI Agents with Accurate Process Information AAAI 2026 Progressive Supernet Training for Efficient Visual Autoregressive Modeling CVPR 2026 RawMetaDiff: Unlocking Extreme Darkness from Dual-Exposure RAW with Meta-Guided Diffusion CVPR 2026 Realistic Face Reconstruction from Facial Embeddings via Diffusion Models AAAI 2026 ReFAct: Empowering Multimodal Web Agents with Visual and Context Focusing CVPR 2026 RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models ACL 2026 Tessera: A Holistic Pipeline Parallelism Framework for Trillion-Parameter Heterogeneous MoE Training (Operational Systems) OSDI 2026 TrainMover: An Interruption-Resilient Runtime for ML Training OSDI 2026 VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference CVPR 2026 WeightFlow: Learning Stochastic Dynamics via Evolving Weight of Neural Network AAAI 2026 WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens CVPR 2026 AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction NAACL 2025 AgentSquare: Automatic LLM Agent Search in Modular Design Space ICLR 2025 A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation ICLR 2025 Analyzing and Modeling LLM Response Lengths with Extreme Value Theory: Anchoring Effects and Hybrid Distributions EMNLP 2025 A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions ACL 2025 ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization AAAI 2025 Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution IJCAI 2025 Automated Fine-Grained Mixture-of-Experts Quantization ACL 2025 AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment EMNLP 2025 CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration ICML 2025 CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning IJCAI 2025 CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space EMNLP 2025 CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory ACL 2025 Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents ACL 2025 Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics ACL 2025 Depression Detection on Social Media with Large Language Models EMNLP 2025 Efficient Long Context Fine-tuning with Chunk Flow ICML 2025 Evolution of Aegis: Fault Diagnosis for AI Model Training Service in Production NSDI 2025 EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary ACL 2025 Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization ICML 2025 MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector AAAI 2025 Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning EMNLP 2025 OpenCarbon: A Contrastive Learning-based Cross-Modality Neural Approach for High-Resolution Carbon Emission Prediction Using Open Data IJCAI 2025 Open-Set Living Need Prediction with Large Language Models ACL 2025 Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning ICLR 2025 PychoAgent: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events EMNLP 2025 Re-Attentional Controllable Video Diffusion Editing AAAI 2025 Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems ICML 2025 SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation AAAI 2025 Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification ICCV 2025 Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers ICCV 2025 Solving MDPs with LTLf+ and PPLTL+ Temporal Objectives IJCAI 2025 Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length ICLR 2025 Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models ICML 2025 Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine ACL 2025 Treasures in Discarded Weights for LLM Quantization AAAI 2025 Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Prediction IJCAI 2025 UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence ICCV 2025 UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces ACL 2025 Angluin-Style Learning of Deterministic Büchi and Co-Büchi Automata IJCAI 2024 EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities ACL 2024 Estimating On-Road Transportation Carbon Emissions from Open Data of Road Network and Origin-Destination Flow Data AAAI 2024 From Pixels to Progress: Generating Road Network from Satellite Imagery for Socioeconomic Insights in Impoverished Areas IJCAI 2024 Giving Control Back to Models: Enabling Offensive Language Detection Models to Autonomously Identify and Mitigate Biases EMNLP 2024 GLOP: Learning Global Partition and Local Construction for Solving Large-Scale Routing Problems in Real-Time AAAI 2024 HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction NeurIPS 2024 Llumnix: Dynamic Scheduling for Large Language Model Serving OSDI 2024 Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction NeurIPS 2024 Long-term Detection and Monitory of Chinese Urban Village Using Satellite Imagery IJCAI 2024 Masked Face Recognition with Generative-to-Discriminative Representations ICML 2024 Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration NeurIPS 2024 Patch-Aware Sample Selection for Efficient Masked Image Modeling AAAI 2024 PolCLIP: A Unified Image-Text Word Sense Disambiguation Model via Generating Multimodal Complementary Representations ACL 2024 Social Physics Informed Diffusion Model for Crowd Simulation AAAI 2024 Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation ICLR 2024 Understanding Expressivity of GNN in Rule Learning ICLR 2024 UV-SAM: Adapting Segment Anything Model for Urban Village Identification AAAI 2024 VulnerabilityMap: An Open Framework for Mapping Vulnerability among Urban Disadvantaged Populations in the United States IJCAI 2024 Decoupled Multimodal Distilling for Emotion Recognition CVPR 2023 DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization NeurIPS 2023 Distribution-Consistent Modal Recovering for Incomplete Multimodal Learning ICCV 2023 DynaMS: Dyanmic Margin Selection for Efficient Deep Learning ICLR 2023 Efficient Hyper-parameter Optimization with Cubic Regularization NeurIPS 2023 Incomplete Multimodality-Diffused Emotion Recognition NeurIPS 2023 Learning Symbolic Models for Graph-structured Physical Mechanism ICLR 2023 PateGail: A Privacy-Preserving Mobility Trajectory Generator with Imitation Learning AAAI 2023 Relation-aware Ensemble Learning for Knowledge Graph Embedding EMNLP 2023 Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings ICLR 2023 Style Projected Clustering for Domain Generalized Semantic Segmentation CVPR 2023 TAM of SCNU at SemEval-2023 Task 1: FCLL: A Fine-grained Contrastive Language-Image Learning Model for Cross-language Visual Word Sense Disambiguation SemEval 2023 A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs IJCAI 2022 Efficient Hyper-parameter Search for Knowledge Graph Embedding ACL 2022 MAPDP: Cooperative Multi-Agent Reinforcement Learning to Solve Pickup and Delivery Problems AAAI 2022 MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters NSDI 2022 Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training EMNLP 2022 Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach ECCV 2022 AttnMove: History Enhanced Trajectory Recovery via Attentional Network AAAI 2021 Automorphic Equivalence-aware Graph Neural Network NeurIPS 2021 Consistent Instance False Positive Improves Fairness in Face Recognition CVPR 2021 Learnable Embedding sizes for Recommender Systems ICLR 2021 Learning Normal Dynamics in Videos With Meta Prototype Network CVPR 2021 Progressive Feature Interaction Search for Deep Sparse Network NeurIPS 2021 Real-Time Image Enhancer via Learnable Spatial-Aware 3D Lookup Tables ICCV 2021 SDD-FIQA: Unsupervised Face Image Quality Assessment With Similarity Distribution Distance CVPR 2021 Synthesizing Good-Enough Strategies for LTLf Specifications IJCAI 2021 AntMan: Dynamic Scaling on GPU Clusters for Deep Learning OSDI 2020 A Sequential Convolution Network for Population Flow Prediction with Explicitly Correlation Modelling IJCAI 2020 Hybrid Compositional Reasoning for Reactive Synthesis from Finite-Horizon Specifications AAAI 2020 Multi-View Joint Graph Representation Learning for Urban Region Embedding IJCAI 2020 Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering NeurIPS 2020 Adaptive Context Network for Scene Parsing ICCV 2019 A Decomposition Approach for Urban Anomaly Detection Across Spatiotemporal Data IJCAI 2019 DeepAPF: Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation IJCAI 2019 DeepDPM: Dynamic Population Mapping via Deep Neural Network AAAI 2019 DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis AAAI 2019 Dual Attention Network for Scene Segmentation CVPR 2019 Reinforced Negative Sampling for Recommendation with Exposure Data IJCAI 2019 Self-Supervised Representation Learning From Videos for Facial Action Unit Detection CVPR 2019 Improving Implicit Recommender Systems with View Data IJCAI 2018 Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching IJCAI 2017 Collaborative Evolution for User Profiling in Recommender Systems IJCAI 2016 Image Feature Learning for Cold Start Problem in Display Advertising IJCAI 2015 Weakly Supervised RBM for Semantic Segmentation IJCAI 2015