Furong Huang

AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment AAAI 2026 Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026 Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling ACL 2026 TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos CVPR 2026 Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset ICLR 2025 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI 2025 Collab: Controlled Decoding using Mixture of Agents for LLM Alignment ICLR 2025 DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data EMNLP 2025 Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement NAACL 2025 FLARE: Robot Learning with Implicit World Modeling CoRL 2025 GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment ICLR 2025 GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning ICCV 2025 Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models CoRL 2025 Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment CVPR 2025 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey NAACL 2025 MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs NAACL 2025 PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models NAACL 2025 Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension ICCV 2025 Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory AISTATS 2025 TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies ICLR 2025 Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems EMNLP 2025 World Models with Hints of Large Language Models for Goal Achieving NAACL 2025 Zero-Shot Vision Encoder Grafting via LLM Surrogates ICCV 2025 ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization ICML 2024 Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate ICML 2024 A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) ICML 2024 AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models EMNLP 2024 Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies ICLR 2024 Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance NeurIPS 2024 COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL ICLR 2024 Decodable and Sample Invariant Continuous Object Encoder ICLR 2024 DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization ICLR 2024 Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization NeurIPS 2024 Explore Spurious Correlations at the Concept Level in Language Models for Text Classification ACL 2024 FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding? NeurIPS 2024 Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations ICLR 2024 HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models CVPR 2024 Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds ICLR 2024 Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion NeurIPS 2024 MaxMin-RLHF: Alignment with Diverse Human Preferences ICML 2024 Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences ACL 2024 Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation EMNLP 2024 PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024 PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts ICLR 2024 Position: On the Possibilities of AI-Generated Text Detection ICML 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss ICML 2024 PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control ICML 2024 Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL ICLR 2024 SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation ICLR 2024 Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NeurIPS 2024 Transfer Q-star : Principled Decoding for LLM Alignment NeurIPS 2024 WAVES: Benchmarking the Robustness of Image Watermarks ICML 2024 TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning NeurIPS 2023 C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder NeurIPS 2023 Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication ICLR 2023 Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise NeurIPS 2023 Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness ICLR 2023 Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function ICLR 2023 Large-Scale Distributed Learning via Private On-Device LSH NeurIPS 2023 Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator ICML 2023 Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy ICML 2023 Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning AAAI 2023 SMART: Self-supervised Multi-task pretrAining with contRol Transformers ICLR 2023 STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning ICML 2023 SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication ICLR 2023 Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach NeurIPS 2022 Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning NeurIPS 2022 End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking NeurIPS 2022 Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory ICLR 2022 Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework ICML 2022 Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity NeurIPS 2022 Transferring Fairness under Distribution Shifts via Fair Consistency Regularization NeurIPS 2022 Transfer RL across Observation Feature Spaces via Model-Based Regularization ICLR 2022 Tuformer: Data-driven Design of Transformers for Improved Generalization or Efficiency ICLR 2022 Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NeurIPS 2022 Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL ICLR 2022 Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks AAAI 2021 Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks NeurIPS 2021 TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL AAAI 2021 Understanding the Generalization Benefit of Model Invariance from a Data Perspective NeurIPS 2021 VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization NeurIPS 2021 Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics ICLR 2021 An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm ICML 2020 ARMA Nets: Expanding Receptive Field for Dense Prediction NeurIPS 2020 Convolutional Tensor-Train LSTM for Spatio-Temporal Learning NeurIPS 2020 Sampling-Free Learning of Bayesian Quantized Neural Networks ICLR 2020 Understanding Generalization in Deep Learning via Tensor Methods AISTATS 2020 Guaranteed Scalable Learning of Latent Tree Models UAI 2019 Learning Deep ResNet Blocks Sequentially using Boosting Theory ICML 2018 Escaping From Saddle Points — Online Stochastic Gradient for Tensor Decomposition COLT 2015 Online Tensor Methods for Learning Latent Variable Models JMLR 2015 High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion JMLR 2012 Learning Mixtures of Tree Graphical Models NeurIPS 2012