Skip to yearly menu bar Skip to main content


Workshop

2nd Workshop on Test-Time Adaptation: Putting Updates to the Test (PUT)

Evan Shelhamer ⋅ Evgenia Rusak ⋅ Steffen Schneider ⋅ Francesco Croce ⋅ Motasem Alfarra ⋅ Teresa Yeo ⋅ Sarthak Kumar Maharana ⋅ Yunhui Guo ⋅ Marc Masana
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: Asia/Seoul
1:00 AM
Opening Remarks
Evan Shelhamer
1:15 AM
Deepak Pathak
2:45 AM
Xiaoxiao Li
→ Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
Heitor Medeiros ⋅ Hossein Sharifi-Noghabi ⋅ Gabriel Oliveira ⋅ Saghar Irandoust
→ Scalable Temporal Domain Generalization via Prompting
Sepidehsadat Hosseini ⋅ Mengyao Zhai ⋅ Hossein Hajimirsadeghi ⋅ Frederick Tung
→ Keep the Alignment, Skip the Overhead: Lightweight Instruction Alignment for Continually Trained LLMs
Ishan Jindal ⋅ Badrinath chandana ⋅ Pranjal Bharti ⋅ Lakkidi Vinay ⋅ SACHIN SHARMA
→ Lightweight Online Adaption for Time Series Foundation Model Forecasts
Thomas Lee ⋅ William Toner ⋅ Martin Asenov ⋅ Artjom Joosen ⋅ Rajkarn Singh
→ Language Model Personalization via Reward Factorization
Idan Shenfeld ⋅ Felix Faltings ⋅ Pulkit Agrawal ⋅ Aldo Pacchiano
→ Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
Shenao Zhang ⋅ Yaqing Wang ⋅ Canoee Liu ⋅ Tianqi Liu ⋅ Peter Grabowski ⋅ Eugene Ie ⋅ Zhaoran Wang ⋅ Yunxuan Li
→ Right Question is Already Half the Answer: Fully Unsupervisedd LLM Reasoning Incentization
Qingyang Zhang ⋅ Haitao Wu ⋅ Changqing Zhang ⋅ Peilin Zhao ⋅ Yatao Bian
→ OnDistributionalRobustnessofIn-ContextLearningforTextClassification
Carolina Hatanpää ⋅ Noah Smith ⋅ Sachin Kumar
→ e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
Amrith Setlur ⋅ Matthew Yang ⋅ Charlie Snell ⋅ Jeremiah Greer ⋅ Ian Wu ⋅ Virginia Smith ⋅ Max Simchowitz ⋅ Aviral Kumar
→ AdaptMI: Adaptive Skill-based In-context Math Instructions for Small Language Models
Yinghui He ⋅ Abhishek Panigrahi ⋅ Yong LIN ⋅ Sanjeev Arora
→ MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation
Eunjin Roh ⋅ Yigitcan Kaya ⋅ Christopher Kruegel ⋅ Giovanni Vigna ⋅ Sanghyun Hong
→ Causal Fine-Tuning of Pre-trained Language Models for Robust Test Time Adaptation
Jialin Yu ⋅ Yuxiang Zhou ⋅ Yulan He ⋅ Nevin Zhang ⋅ Junchi Yu ⋅ Phil Torr ⋅ Ricardo Silva
→ Replacing thinking with tool usage enables reasoning in small language models
Corrado Rainone ⋅ Tim Bakker ⋅ Roland Memisevic
→ Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization
Joschka Braun ⋅ Carsten Eickhoff ⋅ Seyed Ali Bahrainian
→ Language System: A Lightweight Ranking Framework for Language Models
Chenheng Zhang ⋅ Tianqi Du ⋅ Jizhe Zhang ⋅ Mingqing Xiao ⋅ Yifei Wang ⋅ Yisen Wang ⋅ Zhouchen Lin
→ JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models
Eric Tillmann Bill ⋅ Enis Simsar ⋅ Thomas Hofmann
→ Prefix-Tuning+: Modernizing Prefix-Tuning through Attention Independent Prefix Data
Haonan Wang ⋅ Brian Chen ⋅ Li Siquan ⋅ Liang Xinhe ⋅ Tianyang Hu ⋅ Hwee Lee ⋅ Kenji Kawaguchi
→ DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
Yunbei Zhang ⋅ Akshay Mehra ⋅ Shuaicheng Niu ⋅ Jihun Hamm
→ CCC: Enhancing Video Generation via Structured MLLM Feedback
Jing Gu ⋅ Ashwin Nagarajan ⋅ Tejas Polu ⋅ Kaizhi Zheng ⋅ Ruijian Zha ⋅ Jie Yang ⋅ Xin Eric Wang
→ Leto: Modeling Multivariate Time Series with Memorizing at Test Time
Ali Behrouz ⋅ Daniel Cao ⋅ Ali Parviz ⋅ Michele Santacatterina ⋅ Ramin Zabih
→ Agentic Adversarial QA for Improving Domain-Specific LLMs
Vincent Grari ⋅ Ciprian Tomoiaga ⋅ sylvain lamprier ⋅ Tatsunori Hashimoto ⋅ Marcin Detyniecki
→ 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
→ Test-time Offline Reinforcement Learning on Goal-related Experience
Marco Bagatella ⋅ Mert Albaba ⋅ Jonas Hübotter ⋅ Georg Martius ⋅ Andreas Krause
4:00 AM
Lunch
→ Rejection Sampling Based Fine Tuning Secretly Performs PPO
Gautham Govind Anil ⋅ Dheeraj Nagaraj ⋅ Karthikeyan Shanmugam ⋅ Sanjay Shakkottai
→ Test Time Adaptation Using Adaptive Quantile Recalibration
Paria Mehrbod ⋅ Pedro Vianna ⋅ geraldin nanfack ⋅ Guy Wolf ⋅ Eugene Belilovsky
→ Context Tuning for In-Context Optimization
Jack Lu ⋅ Ryan Teehan ⋅ Zhenbang Yang ⋅ Mengye Ren
→ Inference-Time Alignment via Hypothesis Reweighting
Yoonho Lee ⋅ Jonathan Williams ⋅ Henrik Marklund ⋅ Archit Sharma ⋅ Eric Mitchell ⋅ Anikait Singh ⋅ Chelsea Finn
→ Reasoning as an Adaptive Defense for Safety
Taeyoun Kim ⋅ Fahim Tajwar ⋅ Aditi Raghunathan ⋅ Aviral Kumar
→ Adaptive Monocular Depth Estimation with Masked Image Consistency
Damian Sójka ⋅ Marc Masana ⋅ Bartłomiej Twardowski ⋅ Sebastian Cygert
→ Monitoring Risks in Test-Time Adaptation
Mona Schirmer ⋅ Metod Jazbec ⋅ Christian Andersson Naesseth ⋅ Eric Nalisnick
→ SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
Jihyun Yu ⋅ Yoojin Oh ⋅ Won Bae ⋅ Mingyu Kim ⋅ Junhyug Noh
→ Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa ⋅ Frank Schneider ⋅ Philipp Hennig ⋅ Jose Miguel Hernandez-Lobato
→ Theoretical Insights into In-context Learning with Unlabeled Data
Yingcong Li ⋅ Xiangyu Chang ⋅ Muti Kara ⋅ Xiaofeng Liu ⋅ Amit Roy-Chowdhury ⋅ Samet Oymak
→ LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models
Yuto Kojima ⋅ Jiarui Xu ⋅ Xueyan Zou ⋅ Xiaolong Wang
→ Value Conditioned Policy Fine Tuning for Test Time Domain Adaptation
Harit Pandya ⋅ Ignas Budvytis ⋅ Rudra Poudel ⋅ Stephan Liwicki
→ Temporal Sampling for Forgotten Reasoning in LLMs
Yuetai Li ⋅ Zhangchen Xu ⋅ Fengqing Jiang ⋅ Bhaskar Ramasubramanian ⋅ Luyao Niu ⋅ Yuchen Lin ⋅ Xiang Yue ⋅ Radha Poovendran
→ Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
Frederick Shpilevskiy ⋅ Saiyue Lyu ⋅ Krishnamurthy Dvijotham ⋅ Mathias Lécuyer ⋅ Pierre-André Noël
→ Scaling Textual Gradients via Sampling-Based Momentum
Zixin Ding ⋅ Junyuan Hong ⋅ Jiachen (Tianhao) Wang ⋅ Zinan Lin ⋅ Zhangyang “Atlas” Wang ⋅ Yuxin Chen
→ Prune ’n Predict: Optimizing LLM Decision-making with Conformal Prediction
Harit Vishwakarma ⋅ Alan Mishler ⋅ Thomas Cook ⋅ Niccolo Dalmasso ⋅ Natraj Raman ⋅ Sumitra Ganesh
→ Diffusion Tree Sampling: Scalable inference‑time alignment of diffusion models
Vineet Jain ⋅ Kusha Sareen ⋅ Mohammad Pedramfar ⋅ Siamak Ravanbakhsh
→ Learning to Self-Correct through Chain-of-Thought Verification
Bradley Guo ⋅ Jingwen Gu ⋅ Jin Zhou ⋅ Wen Sun
→ Distilling Prompts at Test-Time for Multimodal Few-Shot Learning
Akash Gupta ⋅ Amos Storkey ⋅ Mirella Lapata
→ N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
Ilya Zisman ⋅ Alexander Nikulin ⋅ Viacheslav Sinii ⋅ Denis Tarasov ⋅ Nikita Lyubaykin ⋅ Andrei Polubarov ⋅ Igor Kiselev ⋅ Vladislav Kurenkov
→ Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics
Maksim Bobrin ⋅ Ilya Zisman ⋅ Alexander Nikulin ⋅ Dmitry V. Dylov ⋅ Vladislav Kurenkov
→ The Curious Language Model: Strategic Test-Time Information Acquisition
Michael Cooper ⋅ Rohan Wadhawan ⋅ John Giorgi ⋅ Chenhao Tan ⋅ Davis Liang
7:15 AM
Break
9:00 AM
Best Paper Award
Evan Shelhamer
9:45 AM
Closing Remarks
Evan Shelhamer