PPaperPicks

Furong Huang

University of Maryland, College Park, USA

59 papers at tracked venues · 47 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗Google Scholar ↗Homepage ↗

Venues

ICLR ×14NeurIPS ×10ICML ×9ACL ×5NAACL ×5EMNLP ×4AAAI ×3ICCV ×3CVPR ×2AISTATS ×1EACL ×1ICRA ×1SIGIR ×1

Frequent coauthors

Xiyao Wang
DBLP profile ↗ORCID search ↗
×6
Souradip Chakraborty
DBLP profile ↗ORCID search ↗
×5
Yuhang Zhou
DBLP profile ↗ORCID search ↗
×4
Pankayaraj Pathmanathan
DBLP profile ↗ORCID search ↗
×3
Aakriti Agrawal
DBLP profile ↗ORCID search ↗
×3
Mucong Ding
DBLP profile ↗ORCID search ↗
×3
Michael-Andrei Panaitescu-Liess
DBLP profile ↗ORCID search ↗
×3
Yuancheng Xu
DBLP profile ↗ORCID search ↗
×3
Ruijie Zheng
DBLP profile ↗ORCID search ↗
×3
Xiaoyu Liu
DBLP profile ↗ORCID search ↗
×2
Soumya Suvra Ghosal
DBLP profile ↗ORCID search ↗
×2
Dehao Yuan
DBLP profile ↗ORCID search ↗
×2

Papers

  1. AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment
    AAAI 2026 ·
    Pankayaraj Pathmanathan
    DBLP profile ↗ORCID search ↗
  2. EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
    ACL 2026 ·
    Aakriti Agrawal
    DBLP profile ↗ORCID search ↗
  3. Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs
    EACL 2026 ·
    James Beetham
    DBLP profile ↗ORCID search ↗
  4. Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
    ACL 2026 ·
    Pankayaraj Pathmanathan
    DBLP profile ↗ORCID search ↗
  5. Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
    ACL 2026 ·
    Aakriti Agrawal
    DBLP profile ↗ORCID search ↗
  6. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
    NeurIPS 2025 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  7. Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
    ICLR 2025 ·
    Yingzi Ma
    DBLP profile ↗ORCID search ↗
  8. CSRec: Rethinking Sequential Recommendation from A Causal Perspective
    SIGIR 2025 ·
    Xiaoyu Liu
    DBLP profile ↗ORCID search ↗
  9. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
    AAAI 2025 ·
    Michael-Andrei Panaitescu-Liess
    DBLP profile ↗ORCID search ↗
  10. Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
    ICLR 2025 ·
    Souradip Chakraborty
    DBLP profile ↗ORCID search ↗
  11. DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
    EMNLP 2025 ·
    Yuhang Zhou
    DBLP profile ↗ORCID search ↗
  12. Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
    NeurIPS 2025 ·
    Soumya Suvra Ghosal
    DBLP profile ↗ORCID search ↗
  13. Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
    NAACL 2025 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  14. GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
    ICLR 2025 ·
    Yuancheng Xu
    DBLP profile ↗ORCID search ↗
  15. GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
    ICCV 2025 ·
    Kelin Yu
    DBLP profile ↗ORCID search ↗
  16. Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
    CVPR 2025 ·
    Soumya Suvra Ghosal
    DBLP profile ↗ORCID search ↗
  17. Is Poisoning a Real Threat to DPO? Maybe More So Than You Think
    AAAI 2025 ·
    Pankayaraj Pathmanathan
    DBLP profile ↗ORCID search ↗
  18. Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
    NAACL 2025 ·
    Xiaoyu Liu
    DBLP profile ↗ORCID search ↗
  19. MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
    NAACL 2025 ·
    Yuhang Zhou
    DBLP profile ↗ORCID search ↗
  20. PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
    NAACL 2025 ·
    Michael-Andrei Panaitescu-Liess
    DBLP profile ↗ORCID search ↗
  21. Safety Guaranteed Robust Multi-Agent Reinforcement Learning with Hierarchical Control for Connected and Automated Vehicles
    ICRA 2025 ·
    Zhili Zhang
    DBLP profile ↗ORCID search ↗
  22. Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
    ICCV 2025 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  23. SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
    NeurIPS 2025 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  24. Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
    AISTATS 2025 ·
    Zhi Zhang
    DBLP profile ↗ORCID search ↗
  25. TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
    ICLR 2025 ·
    Ruijie Zheng
    DBLP profile ↗ORCID search ↗
  26. Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
    EMNLP 2025 ·
    Aakriti Agrawal
    DBLP profile ↗ORCID search ↗
  27. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
    NeurIPS 2025 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  28. World Models with Hints of Large Language Models for Goal Achieving
    NAACL 2025 ·
    Zeyuan Liu
    DBLP profile ↗ORCID search ↗
  29. Zero-Shot Vision Encoder Grafting via LLM Surrogates
    ICCV 2025 ·
    Kaiyu Yue
    DBLP profile ↗ORCID search ↗
  30. A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
    ICML 2024 ·
    Dehao Yuan
    DBLP profile ↗ORCID search ↗
  31. ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
    ICML 2024 ·
    Tianying Ji
    DBLP profile ↗ORCID search ↗
  32. Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
    ICML 2024 ·
    Yuancheng Xu
    DBLP profile ↗ORCID search ↗
  33. AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
    EMNLP 2024 ·
    Xiyang Wu
    DBLP profile ↗ORCID search ↗
  34. Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
    ICLR 2024 ·
    Xiangyu Liu
    DBLP profile ↗ORCID search ↗
  35. Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
    NeurIPS 2024 ·
    Joshua McClellan
    DBLP profile ↗ORCID search ↗
  36. COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
    ICLR 2024 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  37. Decodable and Sample Invariant Continuous Object Encoder
    ICLR 2024 ·
    Dehao Yuan
    DBLP profile ↗ORCID search ↗
  38. DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
    ICLR 2024 ·
    Guowei Xu
    DBLP profile ↗ORCID search ↗
  39. Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
    NeurIPS 2024 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  40. Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
    ACL 2024 ·
    Yuhang Zhou
    DBLP profile ↗ORCID search ↗
  41. FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
    NeurIPS 2024 ·
    Marco Bornstein
    DBLP profile ↗ORCID search ↗
  42. Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
    ICLR 2024 ·
    Yongyuan Liang
    DBLP profile ↗ORCID search ↗
  43. Hallusionbench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
    CVPR 2024 ·
    Tianrui Guan
    DBLP profile ↗ORCID search ↗
  44. Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
    ICLR 2024 ·
    Michael-Andrei Panaitescu-Liess
    DBLP profile ↗ORCID search ↗
  45. Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
    NeurIPS 2024 ·
    Yongyuan Liang
    DBLP profile ↗ORCID search ↗
  46. MaxMin-RLHF: Alignment with Diverse Human Preferences
    ICML 2024 ·
    Souradip Chakraborty
    DBLP profile ↗ORCID search ↗
  47. Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
    ACL 2024 ·
    Xiyao Wang
    DBLP profile ↗ORCID search ↗
  48. Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
    EMNLP 2024 ·
    Yuhang Zhou
    DBLP profile ↗ORCID search ↗
  49. PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
    ICLR 2024 ·
    Souradip Chakraborty
    DBLP profile ↗ORCID search ↗
  50. PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
    ICML 2024 ·
    Ruijie Zheng
    DBLP profile ↗ORCID search ↗
  51. PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
    ICLR 2024 ·
    Bang An
    DBLP profile ↗ORCID search ↗
  52. Position: On the Possibilities of AI-Generated Text Detection
    ICML 2024 ·
    Souradip Chakraborty
    DBLP profile ↗ORCID search ↗
  53. Position: TrustLLM: Trustworthiness in Large Language Models
    ICML 2024 ·
    Yue Huang
    DBLP profile ↗ORCID search ↗
  54. Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
    ICML 2024 ·
    Ruijie Zheng
    DBLP profile ↗ORCID search ↗
  55. Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
    ICLR 2024 ·
    Xiangyu Liu
    DBLP profile ↗ORCID search ↗
  56. SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
    ICLR 2024 ·
    Mucong Ding
    DBLP profile ↗ORCID search ↗
  57. Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
    NeurIPS 2024 ·
    Yuancheng Xu
    DBLP profile ↗ORCID search ↗
  58. Transfer Q-star : Principled Decoding for LLM Alignment
    NeurIPS 2024 ·
    Souradip Chakraborty
    DBLP profile ↗ORCID search ↗
  59. WAVES: Benchmarking the Robustness of Image Watermarks
    ICML 2024 ·
    Bang An
    DBLP profile ↗ORCID search ↗