Publications

Underline: lab members · * Equal contribution · ^† Co-correspondence

Preprints Conference papers Workshop papers Journal papers Thesis

Preprints

[P4] Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs
Moongyu Jeon*, Dongjae Jeon*, Bumjun Kim, Mingyu Kim^†, and Albert No^†
submitted
[P3] JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models
Yeachan Jun and Albert No
submitted
[P2] The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
Dueun Kim and Albert No
submitted
[P1] Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
Soeun Kim and Albert No
submitted

Conference papers

[C39] VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
Hyesoo Hong, Minsoo Kim, Wonje Jeung, Sangyeon Yoon, Dongjae Jeon, and Albert No
Neural Information Processing Systems (NeurIPS2026)
[C38] Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
Shin So, Kyelim Lee, and Albert No
Neural Information Processing Systems (NeurIPS2026)
[C37] Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
Sangyeon Yoon*, Wonje Jeung*, Yoonjun Cho, Dongjae Jeon, and Albert No
Neural Information Processing Systems (NeurIPS2026)
[C36] A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
Moongyu Jeon*, Sangwoo Shin*, Bumjun Kim, Kyelim Lee, and Albert No
Neural Information Processing Systems (NeurIPS2026)
[C35] Same Trajectory, Contradictory Rewards (RoboRMBench): Paraphrase Fragility in Vision Language Reward Models
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Yoonjun Cho, Dongjae Jeon, Bumjun Kim, Jean Oh^†, Youngjae Yu^†, and Albert No^†
Conference on Empirical Methods in Natural Language Processing (EMNLP2026 Oral Presentation)
[C34] BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
Sangyeon Yoon, Hyesoo Hong, Wonje Jeung, Yongil Kim, Wooseok Seo, Heuiyeen Yeen, Albert No, and Sunkyoung Kim
Conference on Empirical Methods in Natural Language Processing (EMNLP2026 Oral Presentation)
[C33] Position: The Term “Machine Unlearning” Is Overused in LLMs
Sangyeon Yoon*, Yeachan Jun*, and Albert No
International Conference on Machine Learning (ICML2026 Position)
[C32] dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
Pyo Min Hong and Albert No
International Conference on Machine Learning (ICML2026)
[Project Page]
[C31] Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
Yoonjun Cho*, Dongjae Jeon*, Soeun Kim, Moongyu Jeon, and Albert No
International Conference on Machine Learning (ICML2026)
[Project Page]
[C30] Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
Bumjun Kim*, Dongjae Jeon*, Moongyu Jeon*, and Albert No
International Conference on Machine Learning (ICML2026)
[C29] DUSK: Do Not Unlearn Shared Knowledge
Wonje Jeung*, Sangyeon Yoon*, Hyesoo Hong*, Soeun Kim, Seungju Han, Youngjae Yu, and Albert No
Annual Meeting of the Association for Computational Linguistics (ACL2026 Findings)
[Project Page]
[C28] Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
Bumjun Kim and Albert No
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2026 Findings)
[C27] Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
Sangyeon Yoon, Hyesoo Hong, Wonje Jeung, and Albert No
International Conference on Learning Representations (ICLR2026)
[C26] A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
Wonje Jeung*, Sangyeon Yoon*, Yoonjun Cho, Dongjae Jeon, Sangwoo Shin, Hyesoo Hong, and Albert No
International Conference on Learning Representations (ICLR2026)
[Project Page]
[C25] Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
Bumjun Kim*, Dongjae Jeon*, Dueun Kim*, Wonje Jeung, and Albert No
International Conference on Learning Representations (ICLR2026)
[Project Page]
[C24] Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
Pura Peetathawatchai, Wei-Ning Chen, Berivan Isik, Sanmi Koyejo, and Albert No
IEEE Secure and Trustworthy Machine Learning Conference (SaTML2026)
[C23] An Information Theoretic Evaluation Metric For Strong Unlearning
Dongjae Jeon*, Wonje Jeung*, Taeheon Kim, Albert No^†, and Jonghyun Choi^†
Association for the Advancement of Artificial Intelligence (AAAI2026)
[C22] Information-Theoretic Discrete Diffusion
Moongyu Jeon, Sangwoo Shin, Dongjae Jeon, and Albert No
Neural Information Processing Systems (NeurIPS2025)
[C21] SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
Wonje Jeung, Sangyeon Yoon, Minsuk Kahng^†, and Albert No^†
Neural Information Processing Systems (NeurIPS2025)
[C20] SEPS: A Separability Measure for Robust Unlearning in LLMs
Wonje Jeung*, Sangyeon Yoon*, and Albert No
Conference on Empirical Methods in Natural Language Processing (EMNLP2025 Main)
[C19] R-TOFU: Unlearning in Large Reasoning Models
Sangyeon Yoon, Wonje Jeung, and Albert No
Conference on Empirical Methods in Natural Language Processing (EMNLP2025 Main)
[C18] Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition
Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, and Albert No
Annual Meeting of the Association for Computational Linguistics (ACL2025 Findings)
[C17] Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
Dongjae Jeon*, Dueun Kim*, and Albert No
International Conference on Machine Learning (ICML2025 Spotlight, top 2.6%)
[C16] Improved Communication-Privacy Trade-offs in L2 Mean Estimation under Streaming Differential Privacy
Wei-Ning Chen, Berivan Isik, Peter Kairouz, Albert No, Sewoong Oh, and Zheng Xu
International Conference on Machine Learning (ICML2024)
[C15] Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
TaeHo Yoon, Kibeom Myoung, Keon Lee, Jaewoong Cho, Albert No, and Ernest K. Ryu
Neural Information Processing Systems (NeurIPS2023)
[C14] Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
Berivan Isik, Wei-Ning Chen, Ayfer Ozgur, Tsachy Weissman, and Albert No
Neural Information Processing Systems (NeurIPS2023)
[C13] Prune Your Model Before Distill It
Jinhyuk Park and Albert No
European Conference on Computer Vision (ECCV2022)
[C12] Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Jongmin Lee, Joo Young Choi, Ernest K. Ryu^†, and Albert No^†
International Conference on Machine Learning (ICML2022)
[C11] An Information-Theoretic Justification for Model Pruning
Berivan Isik, Tsachy Weissman, and Albert No
International Conference on Artificial Intelligence and Statistics (AISTATS2022)
[C10] WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Albert No, Taeho Yoon, Se-Hyeon Kwon, and Ernest K. Ryu
International Conference on Machine Learning (ICML2021)
[C9] CROMqs: Rateless Lossy Compression of Quality Scores
Idoia Ochoa, Albert No, Mikel Hernaez, and Tsachy Weissman
Information Theory Workshop (ITW2016)
[C8] Universality of Logarithmic Loss in Lossy Compression
Albert No and Tsachy Weissman
International Symposium on Information Theory (ISIT2015)
[C7] Rateless Lossy Compression via the Extremes
Albert No and Tsachy Weissman
Annual Allerton Conference on Communication, Control, and Computing (2014)
[C6] Information Divergences and the Curious Case of the Binary Alphabet
Jiantao Jiao, Thomas Courtade, Albert No, Kartik Venkat, and Tsachy Weissman
International Symposium on Information Theory (ISIT2014)
[C5] Strong Successive Refinability: Sufficient Conditions
Albert No, Amir Ingber, and Tsachy Weissman
International Symposium on Information Theory (ISIT2014)
[C4] Complexity and Rate-Distortion Tradeoff via Successive Refinement
Albert No, Amir Ingber, and Tsachy Weissman
Annual Allerton Conference on Communication, Control, and Computing (2013)
[C3] Minimax Filtering via Relations between Information and Estimation
Albert No and Tsachy Weissman
International Symposium on Information Theory (ISIT2013)
[C2] Reference Based Genome Compression
Bobbie G. Chern, Idoia Ochoa, Alexandros Manolakos, Albert No, Kartik Venkat, and Tsachy Weissman
Information Theory Workshop (ITW2012)
[C1] Joint Source-Channel Coding of one Random Variable over the Poisson Channel
Albert No, Kartik Venkat, and Tsachy Weissman
International Symposium on Information Theory (ISIT2012)

Workshop papers

[W3] Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
Sangyeon Yoon*, Wonje Jeung*, and Albert No
Neural Information Processing Systems Workshop (Statistical Frontiers in LLMs and Foundation Models @ NeurIPS2024)
[W2] Fully Quantized Always-on Face Detector Considering Mobile Image Sensors
Haechang Lee, Wongi Jeong, Dongil Ryu, Hyunwoo Je, Albert No, Kijeong Kim, and Se Young Chun
International Conference on Computer Vision Workshop (LBQNN @ ICCV2023, Oral)
[W1] Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Andrey Ignatov, Radu Timofte, Shuai Liu, Chaoyu Feng, Furui Bai, Xiaotao Wang, Lei Lei, Ziyao Yi, Yan Xiang, Zibin Liu, Shaoqing Li, Keming Shi, Dehui Kong, Ke Xu, Minsu Kwon, Yaqi Wu, Jiesi Zheng, Zhihao Fan, Xun Wu, Feng Zhang, Albert No, Minhyeok Cho, Zewen Chen, Xiaze Zhang, Ran Li, Juan Wang, Zhiming Wang, Marcos V. Conde, Ui-Jin Choi, Georgy Perevozchikov, Egor Ershov, Zheng Hui, Mengchuan Dong, Xin Lou, Wei Zhou, Cong Pang, Haina Qin, and Mingxuan Cai
European Conference on Computer Vision Workshop (AIM @ ECCV2022)

Journal papers

[J24] A Simple Extension of Bayer Demosaicing For Lightweight Non-Bayer Demosaicing
Ki-Wook Hong*, Minhyeok Jo*, Haechang Lee*, Se Young Chun, and Albert No
IEEE Access, July 2025
[J23] Efficient and Low-Complexity Variable-to-VariableLength Coding for DNA Storage
Yunfei Gao and Albert No
BMC Bioinformatics, October 2024
[J22] Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
Joo Young Choi, Jaesung R. Park, Inkyu Park, Jaewoong Cho, Albert No, and Ernest K. Ryu
Transactions on Machine Learning Research (TMLR), October 2024
[J21] Needleman-Wunsch Attention: A Framework for Enhancing DNA Sequence Embedding
Kyelim Lee and Albert No
IEEE Access, May 2024
[J20] Adaptable DNA Storage Coding: An Efficient Framework for Homopolymer Constraint Transitions
Yunfei Gao and Albert No
IEEE Access, January 2024
[J19] How Does a Transformer Learn Compression? An Attention Study on Huffman and LZ4
Beomseok Seo and Albert No
IEEE Access, December 2023
[J18] Reducing cost in DNA-based data storage by sequence analysis-aided soft information decoding of variable-length reads
Seong-Joon Park, Sunghwan Kim, Jaeho Jeong, Albert No, Jong-Seon No, and Hosung Park
Bioinformatics, September 2023
[J17] PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
Minhyeok Cho, Haechang Lee, Hyunwoo Je, Kijeong Kim, Dongil Ryu, and Albert No
IEEE Access, May 2023
[J16] Generative Adversarial Networks for DNA Storage Channel Simulator
Sanghoon Kang*, Yunfei Gao*, Jaeho Jeong, Seong-Joon Park, Jae-Won Kim, Jong-Seon No, Ha Hyeon Jeon, Jeong Wook Lee, Sunghwan Kim, Hosung Park, and Albert No
IEEE Access, January 2023
[J15] Age Estimation from fMRI Data Using Recurrent Neural Network
Yunfei Gao and Albert No
Applied Science, January 2022
[J14] FCLQC: Fast and Concurrent Lossless Quality Scores Compressor
Minhyeok Cho and Albert No
BMC Bioinformatics, December 2021
[J13] Cooperative Sequence Clustering and Decoding for DNA Storage System with Fountain Codes
Jaeho Jeong, Seong-Joon Park, Jae-Won Kim, Jong-Seon No, Ha Hyeon Jeon, Jeong Wook Lee, Albert No, Sunghwan Kim, and Hosung Park
Bioinformatics, April 2021
[J12] Error Rate-Based Log-Likelihood Ratio Processing for Low-Density Parity-Check Codes in DNA Storage
Xiaozhou Lu, Jaeho Jeong, Jae-Won Kim, Jong-Seon No, Hosung Park, Albert No, and Sunghwan Kim
IEEE Access, September 2020
[J11] CROMqs: Rateless Lossy Compression of Quality Scores
Albert No, Mikel Hernaez, and Idoia Ochoa
Journal of Bioinformatics and Computational Biology, September 2020
[J10] Nonasymptotic Upper Bounds on Binary Single Deletion Codes via Mixed Integer Linear Programming
Albert No
Entropy, December 2019
[J9] Markov Decision Policies for Dynamic Video Delivery in Wireless Caching Networks
Minseok Choi, Albert No^†, Mingyue Ji, and Joongheon Kim^†
IEEE Transactions on Wireless Communications, December 2019
[J8] Universality of Logarithmic Loss in Fixed-Length Lossy Compression
Albert No
Entropy, June 2019
[J7] Universality of Logarithmic Loss in Successive Refinement
Albert No
Entropy, February 2019
[J6] SPIHT Algorithm with Adaptive Selection of Compression Ratio Depending on DWT Coefficients
Hyun Kim, Albert No, and Hyuk-jae Lee
IEEE Transactions on Multimedia, December 2018
[J5] Information Geometric Approach on Most Informative Boolean Function Conjecture
Albert No
Entropy, September 2018
[J4] Rateless Lossy Compression via the Extremes
Albert No and Tsachy Weissman
IEEE Transactions on Information Theory, October 2016
[J3] Strong Successive Refinability and Rate-Distortion-Complexity Tradeoff
Albert No, Amir Ingber, and Tsachy Weissman
IEEE Transactions on Information Theory, June 2016
[J2] Information Measures: The Curious Case of the Binary Alphabet
Jiantao Jiao, Thomas A. Courtade, Albert No, Katik Venkat, and Tsachy Weissman
IEEE Transactions on Information Theory, December 2014
[J1] Minimax Filtering via Relations between Information and Estimation
Albert No and Tsachy Weissman
IEEE Transactions on Information Theory, August 2014

Thesis

Rateless Lossy Compression via the Extremes
PhD Thesis, Stanford University, 2015
Advisor: Tsachy Weissman