Qiang Liu

EarlyTom: Early Token Compression Completes Fast Video Understanding CVPR 2026 From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning ACL 2026 Q Cache: Visual Attention Is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model AAAI 2026 RAPID: Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video Diffusion CVPR 2026 RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation ACL 2026 RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark CVPR 2026 A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization ACL 2025 AMO Sampler: Enhancing Text Rendering with Overshooting CVPR 2025 Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models EMNLP 2025 ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks ICLR 2025 CoRA: Collaborative Information Perception by Large Language Model’s Weights for Recommendation AAAI 2025 Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG ACL 2025 Generate First, Then Sample: Enhancing Fake News Detection with LLM-Augmented Reinforced Sampling ACL 2025 GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation EMNLP 2025 Improving Rectified Flow with Boundary Conditions ICCV 2025 InsightEdit: Towards Better Instruction Following for Image Editing CVPR 2025 Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows ICLR 2025 KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing EMNLP 2025 LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance ICCV 2025 Longhorn: State Space Models are Amortized Online Learners ICLR 2025 Memory-Efficient Optimization with Factorized Hamiltonian Descent AISTATS 2025 Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models ACL 2025 MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra ICLR 2025 PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations ICML 2025 Personalized Text Generation with Contrastive Activation Steering ACL 2025 PIPA: Preference Alignment as Prior-Informed Statistical Estimation ICML 2025 PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations ICLR 2025 REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing EMNLP 2025 SHARP: Steering Hallucination in LVLMs via Representation Engineering EMNLP 2025 SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection ACL 2025 SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization ICML 2025 ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming AAAI 2025 Steepest Descent Density Control for Compact 3D Gaussian Splatting CVPR 2025 SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity AISTATS 2025 Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization EMNLP 2025 Uncovering Overfitting in Large Language Model Editing ICLR 2025 VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation ACL 2025 A Computational Framework for Solving Wasserstein Lagrangian Flows ICML 2024 AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies NeurIPS 2024 Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization NeurIPS 2024 Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting ACL 2024 Communication Efficient Distributed Training with Distributed Lion NeurIPS 2024 Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework NeurIPS 2024 Evolution-Inspired Loss Functions for Protein Representation Learning ICML 2024 EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification ACL 2024 FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames ICML 2024 Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables AAAI 2024 InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation ICLR 2024 Knowledge Graph Enhanced Large Language Model Editing EMNLP 2024 Layer Compression of Deep Networks with Straight Flows AAAI 2024 Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts ICLR 2024 Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models ACL 2024 Memory-Efficient LLM Training with Online Subspace Descent NeurIPS 2024 Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models CVPR 2024 PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator NeurIPS 2024 Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction NeurIPS 2024 Quadratic Quantum Variational Monte Carlo NeurIPS 2024 Rethinking Graph Masked Autoencoders through Alignment and Uniformity AAAI 2024 SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow ECCV 2024 Solving Motion Planning Tasks with a Scalable Generative Model ECCV 2024 Stealthy Attack on Large Language Model based Recommendation ACL 2024 Taming Mode Collapse in Score Distillation for Text-to-3D Generation CVPR 2024 Text-Guided Molecule Generation with Diffusion Language Model AAAI 2024 VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark NeurIPS 2024 Counterfactual Debiasing for Fact Verification ACL 2023 DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design ICML 2023 DUBLIN: Visual Document Understanding By Language-Image Network EMNLP 2023 Efficient Transformer-based 3D Object Detection with Dynamic Token Halting ICCV 2023 FAMO: Fast Adaptive Multitask Optimization NeurIPS 2023 Fast Point Cloud Generation With Straight Flows CVPR 2023 FlowGrad: Controlling the Output of Generative ODEs With Gradients CVPR 2023 Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow ICLR 2023 GSLB: The Graph Structure Learning Benchmark NeurIPS 2023 HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing ICLR 2023 Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks CVPR 2023 Language Is Not All You Need: Aligning Perception with Language Models NeurIPS 2023 Learning Diffusion Bridges on Constrained Domains ICLR 2023 Learning Latent Relations for Temporal Knowledge Graph Reasoning ACL 2023 LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning NeurIPS 2023 Metric Residual Network for Sample Efficient Goal-Conditioned Reinforcement Learning AAAI 2023 MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation ICML 2023 Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction EMNLP 2023 Planning-Oriented Autonomous Driving CVPR 2023 Sampling with Mollified Interaction Energy Descent ICLR 2023 Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures CVPR 2023 Uncovering Neural Scaling Laws in Molecular Representation Learning NeurIPS 2023 Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation NeurIPS 2023 AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds AAAI 2022 A Langevin-like Sampler for Discrete Distributions ICML 2022 Attention and Edge-Label Guided Graph Convolutional Networks for Named Entity Recognition EMNLP 2022 BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach NeurIPS 2022 Bootstrapping a high quality multilingual multimodal dataset for Bletchley ACML 2022 Centroid Approximation for Bootstrap: Improving Particle Quality at Inference ICML 2022 Diffusion-based Molecule Generation with Informative Prior Bridges NeurIPS 2022 Energy-Inspired Molecular Conformation Optimization ICLR 2022 First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data NeurIPS 2022 Future gradient descent for adapting the temporal shifting data distribution in online recommendation systems UAI 2022 GraphDIVE: Graph Classification by Mixture of Diverse Experts IJCAI 2022 Harmless Transfer Learning for Item Embeddings NAACL 2022 How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity ICML 2022 MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning EMNLP 2022 NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training ICLR 2022 Pareto navigation gradient descent: a first-order algorithm for optimization in pareto set UAI 2022 Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent NeurIPS 2022 VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts NeurIPS 2022 A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family JMLR 2021 AlphaMatch: Improving Consistency for Semi-Supervised Learning With Alpha-Divergence CVPR 2021 AlphaNet: Improved Training of Supernets with Alpha-Divergence ICML 2021 argmax centroid NeurIPS 2021 Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach NeurIPS 2021 Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition ICML 2021 Conflict-Averse Gradient Descent for Multi-task learning NeurIPS 2021 KeepAugment: A Simple Information-Preserving Data Augmentation Approach CVPR 2021 MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training CVPR 2021 Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds ICLR 2021 Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision AAAI 2021 Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent NeurIPS 2021 Sampling with Trusthworthy Constraints: A Variational Gradient Framework NeurIPS 2021 VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments ICLR 2021 Accountable Off-Policy Evaluation With Kernel Bellman Statistics ICML 2020 A Chance-Constrained Generative Framework for Sequence Optimization ICML 2020 An efficient representation of chronological events in medical texts EMNLP 2020 Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework NeurIPS 2020 Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning ICLR 2020 Certified Monotonic Neural Networks NeurIPS 2020 Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation ICLR 2020 Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks NeurIPS 2020 Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection ICML 2020 Go Wide, Then Narrow: Efficient Training of Deep Thin Networks ICML 2020 Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough NeurIPS 2020 Implicit Regularization and Convergence for Weight Normalization NeurIPS 2020 Off-Policy Interval Estimation with Lipschitz Value Iteration NeurIPS 2020 SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions ACL 2020 Stein Self-Repulsive Dynamics: Benefits From Past Samples NeurIPS 2020 Stein Variational Inference for Discrete Distributions AISTATS 2020 A Kernel Loss for Solving the Bellman Equation NeurIPS 2019 Exploration via Hindsight Goal Generation NeurIPS 2019 Improving Neural Language Modeling via Adversarial Training ICML 2019 Learning Belief Representations for Imitation Learning in POMDPs UAI 2019 Learning Self-Imitating Diverse Policies ICLR 2019 Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models ICML 2019 Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy ICLR 2019 Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization ICML 2019 Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel NeurIPS 2019 Robustness Can Be Cheap: A Highly Efficient Approach to Discover Outliers under High Outlier Ratios AAAI 2019 Splitting Steepest Descent for Growing Neural Architectures NeurIPS 2019 Stein Variational Gradient Descent With Matrix-Valued Kernels NeurIPS 2019 Action-dependent Control Variates for Policy Optimization via Stein Identity ICLR 2018 Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation NeurIPS 2018 Efficient Localized Inference for Large Graphical Models IJCAI 2018 Energy-efficient Amortized Inference with Cascaded Deep Classifiers IJCAI 2018 Goodness-of-Fit Testing for Discrete Distributions via Stein Discrepancy ICML 2018 Learning to Explore via Meta-Policy Gradient ICML 2018 Multi-agent Epistemic Planning with Common Knowledge IJCAI 2018 On the Discrimination-Generalization Tradeoff in GANs ICLR 2018 Stein Variational Gradient Descent as Moment Matching NeurIPS 2018 Stein Variational Gradient Descent Without Gradient ICML 2018 Stein Variational Message Passing for Continuous Graphical Models ICML 2018 Variational Inference with Tail-adaptive f-Divergence NeurIPS 2018 A Convolutional Approach for Misinformation Identification IJCAI 2017 Black-box Importance Sampling AISTATS 2017 Communication-efficient Sparse Regression JMLR 2017 Local Perturb-and-MAP for Structured Prediction AISTATS 2017 Stein Variational Gradient Descent as Gradient Flow NeurIPS 2017 A Kernelized Stein Discrepancy for Goodness-of-fit Tests ICML 2016 Bootstrap Model Aggregation for Distributed Statistical Learning NeurIPS 2016 Learning Infinite RBMs with Frank-Wolfe NeurIPS 2016 Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm NeurIPS 2016 Decomposition Bounds for Marginal MAP NeurIPS 2015 Probabilistic Variational Bounds for Graphical Models NeurIPS 2015 Aggregating Ordinal Labels from Crowds by Minimax Conditional Entropy ICML 2014 Distributed Estimation, Information Loss and Exponential Families NeurIPS 2014 Marginal Structured SVM with Hidden Variables ICML 2014 Scoring Workers in Crowdsourcing: How Many Control Questions are Enough? NeurIPS 2013 Variational Planning for Graph-based MDPs NeurIPS 2013 Computational Approaches to Sentence Completion ACL 2012 Variational Inference for Crowdsourcing NeurIPS 2012 Learning Scale Free Networks by Reweighted ℓ_1 regularization AISTATS 2011 Learning with Blocks: Composite Likelihood and Contrastive Divergence AISTATS 2010