Pin-Yu Chen

Venues

Frequent coauthors

Papers

1. Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness
   WACV 2026 ·

   Erh-Chung Chen

   DBLP profile ↗ORCID search ↗
2. GRE Score: Generative Risk Evaluation for Large Language Models
   ACL 2026 ·

   Zaitang Li

   DBLP profile ↗ORCID search ↗
3. Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
   ACL 2026 ·

   Yue Huang

   DBLP profile ↗ORCID search ↗
4. Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
   ACL 2026 ·

   Chen Xiong

   DBLP profile ↗ORCID search ↗
5. ImReasoner: Improving Memory-based Language Models for Reasoning-in-a-Haystack Tasks
   ACL 2026 ·

   Ching-Yun Ko

   DBLP profile ↗ORCID search ↗
6. MegaCoin: Enhancing Medium-Grained Color Perception for Vision-Language Models
   AAAI 2026 ·

   Ming-Chang Chiu

   DBLP profile ↗ORCID search ↗
7. OjaKV: Context-Aware Online Low-Rank KV Cache Compression
   ACL 2026 ·

   Yuxuan Zhu

   DBLP profile ↗ORCID search ↗
8. RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems
   ACL 2026 ·

   Yu Jiang

   DBLP profile ↗ORCID search ↗
9. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
   ACL 2026 ·

   Lei Hsiung

   DBLP profile ↗ORCID search ↗
10. ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
    ACL 2026 ·

    David H. Yang

    DBLP profile ↗ORCID search ↗
11. Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search
    NeurIPS 2025 ·

    Yanbo Wang

    DBLP profile ↗ORCID search ↗
12. Attention Tracker: Detecting Prompt Injection Attacks in LLMs
    NAACL 2025 ·

    Kuo-Han Hung

    DBLP profile ↗ORCID search ↗
13. CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
    NeurIPS 2025 ·

    Chen Xiong

    DBLP profile ↗ORCID search ↗
14. Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
    ACL 2025 ·

    Megh Thakkar

    DBLP profile ↗ORCID search ↗
15. Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks
    ACL 2025 ·

    Chen Xiong

    DBLP profile ↗ORCID search ↗
16. Differentiable Prompt Learning for Vision Language Models
    IJCAI 2025 ·

    Zhenhan Huang

    DBLP profile ↗ORCID search ↗
17. DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
    WACV 2025 ·

    Shyam Marjit

    DBLP profile ↗ORCID search ↗
18. From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers
    AAAI 2025 ·

    Bharat Runwal

    DBLP profile ↗ORCID search ↗
19. Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
    ICLR 2025 ·

    Jiayi Ye

    DBLP profile ↗ORCID search ↗
20. Large Language Models can Become Strong Self-Detoxifiers
    ICLR 2025 ·

    Ching-Yun Ko

    DBLP profile ↗ORCID search ↗
21. PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
    CVPR 2025 ·

    Wei Li

    DBLP profile ↗ORCID search ↗
22. REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
    ICLR 2025 ·

    Yukun Chen

    DBLP profile ↗ORCID search ↗
23. Retention Score: Quantifying Jailbreak Risks for Vision Language Models
    AAAI 2025 ·

    Zaitang Li

    DBLP profile ↗ORCID search ↗
24. Revisiting Mode Connectivity in Neural Networks with Bezier Surface
    ICLR 2025 ·

    Jie Ren

    DBLP profile ↗ORCID search ↗
25. SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
    ICLR 2025 ·

    Han Shen

    DBLP profile ↗ORCID search ↗
26. SPARC: An AI-Based Speech Processing and Real-Time Correction System
    IJCAI 2025 ·

    TingRay Chung

    DBLP profile ↗ORCID search ↗
27. STAR: Spectral Truncation and Rescale for Model Merging
    NAACL 2025 ·

    Yu-Ang Lee

    DBLP profile ↗ORCID search ↗
28. Shape it Up! Restoring LLM Safety during Finetuning
    NeurIPS 2025 ·

    Shengyun Peng

    DBLP profile ↗ORCID search ↗
29. TabWak: A Watermark for Tabular Diffusion Models
    ICLR 2025 ·

    Chaoyi Zhu

    DBLP profile ↗ORCID search ↗
30. Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
    AAAI 2025 ·

    Xiaomeng Hu

    DBLP profile ↗ORCID search ↗
31. Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
    ICLR 2025 ·

    Hongkang Li

    DBLP profile ↗ORCID search ↗
32. When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
    ICLR 2025 ·

    Hongkang Li

    DBLP profile ↗ORCID search ↗
33. A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
    ACL 2024 ·

    Megh Thakkar

    DBLP profile ↗ORCID search ↗
34. A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
    ICML 2024 ·

    Mohammed Nowaz Rabbani Chowdhury

    DBLP profile ↗ORCID search ↗
35. AutoVP: An Automated Visual Prompting Framework and Benchmark
    ICLR 2024 ·

    Hsi-Ai Tsao

    DBLP profile ↗ORCID search ↗
36. Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning
    ICML 2024 ·

    Zhiyuan He

    DBLP profile ↗ORCID search ↗
37. Computational Complexity of Verifying the Group No-show Paradox
    IJCAI 2024 ·

    Farhad Mohsin

    DBLP profile ↗ORCID search ↗
38. Duwak: Dual Watermarks in Large Language Models
    ACL 2024 ·

    Chaoyi Zhu

    DBLP profile ↗ORCID search ↗
39. Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
    AAAI 2024 ·

    Shengwei An

    DBLP profile ↗ORCID search ↗
40. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
    ICLR 2024 ·

    Xiangyu Qi

    DBLP profile ↗ORCID search ↗
41. GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
    NeurIPS 2024 ·

    Zaitang Li

    DBLP profile ↗ORCID search ↗
42. Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
    NeurIPS 2024 ·

    Xiaomeng Hu

    DBLP profile ↗ORCID search ↗
43. How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
    ICML 2024 ·

    Hongkang Li

    DBLP profile ↗ORCID search ↗
44. It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
    ICLR 2024 ·

    Chen Chen

    DBLP profile ↗ORCID search ↗
45. Language Agnostic Code Embeddings
    NAACL 2024 ·

    Saiteja Utpala

    DBLP profile ↗ORCID search ↗
46. Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
    ICLR 2024 ·

    Yuchen Hu

    DBLP profile ↗ORCID search ↗
47. Larimar: Large Language Models with Episodic Memory Control
    ICML 2024 ·

    Payel Das

    DBLP profile ↗ORCID search ↗
48. Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series
    ICML 2024 ·

    Asterios Tsiourvas

    DBLP profile ↗ORCID search ↗
49. Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning
    AAAI 2024 · Pin-Yu Chen
50. Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
    NeurIPS 2024 ·

    Shengyun Peng

    DBLP profile ↗ORCID search ↗
51. NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
    NeurIPS 2024 ·

    Hao-Lun Sun

    DBLP profile ↗ORCID search ↗
52. Overload: Latency Attacks on Object Detection for Edge Devices
    CVPR 2024 ·

    Erh-Chung Chen

    DBLP profile ↗ORCID search ↗
53. Position: TrustLLM: Trustworthiness in Large Language Models
    ICML 2024 ·

    Yue Huang

    DBLP profile ↗ORCID search ↗
54. Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
    ICML 2024 ·

    Zhi-Yi Chin

    DBLP profile ↗ORCID search ↗
55. Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
    ICLR 2024 ·

    Ming-Yu Chung

    DBLP profile ↗ORCID search ↗
56. Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
    ICML 2024 ·

    Yihua Zhang

    DBLP profile ↗ORCID search ↗
57. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
    ICLR 2024 ·

    Yu-Lin Tsai

    DBLP profile ↗ORCID search ↗
58. SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
    ICML 2024 ·

    Shuai Zhang

    DBLP profile ↗ORCID search ↗
59. Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
    NeurIPS 2024 ·

    Chia-Yi Hsu

    DBLP profile ↗ORCID search ↗
60. Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
    NeurIPS 2024 ·

    Yuchen Hu

    DBLP profile ↗ORCID search ↗
61. SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing
    SIGKDD 2024 ·

    Changchang Yin

    DBLP profile ↗ORCID search ↗
62. The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
    ICLR 2024 ·

    Yan Liu

    DBLP profile ↗ORCID search ↗
63. Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
    ICLR 2024 ·

    Ming Jin

    DBLP profile ↗ORCID search ↗
64. Uncovering the Hidden Cost of Model Compression
    CVPR 2024 ·

    Diganta Misra

    DBLP profile ↗ORCID search ↗
65. What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
    ICML 2024 ·

    Hongkang Li

    DBLP profile ↗ORCID search ↗
66. What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
    ICML 2024 ·

    Ching-Yun Ko

    DBLP profile ↗ORCID search ↗