Accepted Papers

Please see all of the contributed work at https://openreview.net/group?id=ICML.cc/2025/Workshop/PUT.

papers

ID	Title	Authors	Decision
1	JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models	Eric Tillmann Bill, Enis Simsar, Thomas Hofmann	Accept (Poster)
2	Agentic Adversarial QA for Improving Domain-Specific LLMs	Vincent Grari, ciprian tomoiaga, Sylvain Lamprier, Tatsunori Hashimoto, Marcin Detyniecki	Accept (Poster)
3	Scalable Temporal Domain Generalization via Prompting	Sepidehsadat Hosseini, Mengyao Zhai, Hossein Hajimirsadeghi, Frederick Tung	Accept (Poster)
4	Right Question is Already Half the Answer: Fully Unsupervisedd LLM Reasoning Incentization	Qingyang Zhang, Haitao Wu, Changqing Zhang, Peilin Zhao, Yatao Bian	Accept (Poster)
5	Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting	Heitor Rapela Medeiros, Hossein Sharifi-Noghabi, Gabriel L. Oliveira, Saghar Irandoust	Accept (Poster)
6	AdaptMI: Adaptive Skill-based In-context Math Instructions for Small Language Models	Yinghui He, Abhishek Panigrahi, Yong Lin, Sanjeev Arora	Accept (Poster)
7	UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation	Chaoqun Du, Jiayi Guo, Yulin Wang, Gao Huang	Accept (Poster)
8	SwiTTA: Switching Domain Experts and Aggregating Contextual Features Towards Realistic Test-Time Adaptation	Chaoqun Du, Jiayi Guo, Yulin Wang, Gao Huang	Accept (Poster)
10	Lightweight Online Adaption for Time Series Foundation Model Forecasts	Thomas L Lee, William Toner, Martin Asenov, Artjom Joosen, Rajkarn Singh	Accept (Poster)
11	DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation	Yunbei Zhang, Akshay Mehra, Shuaicheng Niu, Jihun Hamm	Accept (Poster)
13	Language Model Personalization via Reward Factorization	Idan Shenfeld, Felix Faltings, Pulkit Agrawal, Aldo Pacchiano	Accept (Oral)
14	MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation	Eunjin Roh, Yigitcan Kaya, Christopher Kruegel, Giovanni Vigna, Sanghyun Hong	Accept (Poster)
15	Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization	Joschka Braun, Carsten Eickhoff, Seyed Ali Bahrainian	Accept (Poster)
17	Language System: A Lightweight Ranking Framework for Language Models	Chenheng Zhang, Tianqi Du, Jizhe Zhang, Mingqing Xiao, Yifei Wang, Yisen Wang, Zhouchen Lin	Accept (Poster)
18	LIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning	Yansheng Mao, Yufei Xu, Jiaqi Li, Fanxu Meng, Haotong Yang, Zilong Zheng, Xiyuan Wang, Muhan Zhang	Accept (Poster)
19	On Training-Test (Mis)alignment in Unsupervised Combinatorial Optimization: Observation, Empirical Exploration, and Analysis	Fanchen Bu, Kijung Shin	Accept (Poster)
20	Prefix-Tuning+: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention	Haonan Wang, Brian K Chen, Li Siquan, Liang Xinhe, Tianyang Hu, Hwee Kuan Lee, Kenji Kawaguchi	Accept (Poster)
21	Replacing thinking with tool usage enables reasoning in small language models	Corrado Rainone, Tim Bakker, Roland Memisevic	Accept (Poster)
22	Test-time Offline Reinforcement Learning on Goal-related Experience	Marco Bagatella, Mert Albaba, Jonas Hübotter, Georg Martius, Andreas Krause	Accept (Poster)
23	Test-Time Adaptation for Generalizable Task Progress Estimation	Christos Ziakas, Alessandra Russo	Accept (Poster)
25	Causal Fine-Tuning of Pre-trained Language Models for Robust Test Time Adaptation	Jialin Yu, Yuxiang Zhou, Yulan He, Nevin L. Zhang, Junchi Yu, Philip Torr, Ricardo Silva	Accept (Poster)
26	Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks	Vishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian	Accept (Poster)
28	CCC: Enhancing Video Generation via Structured MLLM Feedback	Jing Gu, Ashwin Nagarajan, Tejas Polu, Kaizhi Zheng, Ruijian Zha, Jie Yang, Xin Eric Wang	Accept (Poster)
29	Keep the Alignment, Skip the Overhead: Lightweight Instruction Alignment for Continually Trained LLMs	Ishan Jindal, Badrinath chandana, Pranjal Bharti, Lakkidi Vinay, SACHIN DEV SHARMA	Accept (Poster)
32	OnDistributionalRobustnessofIn-ContextLearningforTextClassification	Carolina Hatanpää, Noah A. Smith, Sachin Kumar	Accept (Poster)
33	Leto: Modeling Multivariate Time Series with Memorizing at Test Time	Ali Behrouz, Daniel Yiming Cao, Ali Parviz, Michele Santacatterina, Ramin Zabih	Accept (Oral)
34	Inference-Time Alignment via Hypothesis Reweighting	Yoonho Lee, Jonathan Williams, Henrik Marklund, Archit Sharma, Eric Mitchell, Anikait Singh, Chelsea Finn	Accept (Poster)
35	e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs	Amrith Setlur, Matthew Y. R. Yang, Charlie Victor Snell, Jeremiah Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar	Accept (Oral)
36	Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning	Shenao Zhang, Yaqing Wang, Yinxiao Liu, Tianqi Liu, Peter Grabowski, Eugene Ie, Zhaoran Wang, Yunxuan Li	Accept (Poster)
37	An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination	Sukanya Patra, Souhaib Ben Taieb	Accept (Poster)
38	Distilling Prompts at Test-Time for Multimodal Few-Shot Learning	Akash Gupta, Amos Storkey, Mirella Lapata	Accept (Poster)
39	Mitigating Forgetting in Low Rank Adaptation	Joanna Sliwa, Frank Schneider, Philipp Hennig, José Miguel Hernández-Lobato	Accept (Poster)
40	Temporal Sampling for Forgotten Reasoning in LLMs	Yuetai Li, Zhangchen Xu, Fengqing Jiang, Bhaskar Ramasubramanian, Luyao Niu, Bill Yuchen Lin, Xiang Yue, Radha Poovendran	Accept (Poster)
43	Adaptive Monocular Depth Estimation with Masked Image Consistency	Damian Sójka, Marc Masana, Bartłomiej Twardowski, Sebastian Cygert	Accept (Poster)
44	Learning to Self-Correct through Chain-of-Thought Verification	Bradley Guo, Jingwen Gu, Jin Peng Zhou, Wen Sun	Accept (Poster)
45	SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation	Jihyun Yu, Yoojin Oh, Wonho Bae, Mingyu Kim, Junhyug Noh	Accept (Poster)
46	Context Tuning for In-Context Optimization	Jack Lu, Ryan Teehan, Zhenbang Yang, Mengye Ren	Accept (Poster)
48	When and How Unlabeled Data Provably Improve In-Context Learning	Yingcong Li, Xiangyu Chang, Muti Kara, Xiaofeng Liu, Amit Roy-Chowdhury, Samet Oymak	Accept (Poster)
49	Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models	Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh	Accept (Poster)
50	The Curious Language Model: Strategic Test-Time Information Acquisition	Michael Cooper, Rohan Wadhawan, John Michael Giorgi, Chenhao Tan, Davis Liang	Accept (Poster)
51	Prune ’n Predict: Optimizing LLM Decision-making with Conformal Prediction	Harit Vishwakarma, Alan Mishler, Thomas Cook, Niccolo Dalmasso, Natraj Raman, Sumitra Ganesh	Accept (Poster)
53	Test-Time Alignment of Discrete Diffusion Models with Sequential Monte Carlo	Chinmay Pani, Zijing Ou, Yingzhen Li	Accept (Poster)
54	Reasoning as an Adaptive Defense for Safety	Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan, Aviral Kumar	Accept (Poster)
57	GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models	Jiarui Feng, Yixin Chen, Muhan Zhang	Accept (Poster)
58	Test Time Adaptation Using Adaptive Quantile Recalibration	Paria Mehrbod, Pedro Vianna, geraldin nanfack, Guy Wolf, Eugene Belilovsky	Accept (Poster)
59	Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion	Frederick Shpilevskiy, Saiyue Lyu, Krishnamurthy Dj Dvijotham, Mathias Lécuyer, Pierre-Andre Noel	Accept (Oral)
60	LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models	Yuto Kojima, Jiarui Xu, Xueyan Zou, Xiaolong Wang	Accept (Poster)
61	Shift-Aware Test Time Adaptation and Benchmarking for Time-Series Forecasting	Shivam Grover, Ali Etemad	Accept (Oral)
63	Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval	Taiye Chen, Zeming Wei, Ang Li, Yisen Wang	Accept (Poster)
64	Scaling Textual Gradients via Sampling-Based Momentum	Zixin Ding, Junyuan Hong, Jiachen T. Wang, Zinan Lin, Zhangyang Wang, Yuxin Chen	Accept (Poster)
65	Rejection Sampling Based Fine Tuning Secretly Performs PPO	Gautham Govind Anil, Dheeraj Mysore Nagaraj, Karthikeyan Shanmugam, Sanjay Shakkottai	Accept (Poster)
66	Value Conditioned Policy Fine Tuning for Test Time Domain Adaptation	Harit Pandya, Ignas Budvytis, Rudra P. K. Poudel, Stephan Liwicki	Accept (Poster)
68	Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics	Maksim Bobrin, Ilya Zisman, Alexander Nikulin, Dmitry V. Dylov, Vladislav Kurenkov	Accept (Poster)
71	N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs	Ilya Zisman, Alexander Nikulin, Viacheslav Sinii, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov	Accept (Poster)
72	Monitoring Risks in Test-Time Adaptation	Mona Schirmer, Metod Jazbec, Christian A. Naesseth, Eric Nalisnick	Accept (Oral)