Skip to yearly menu bar Skip to main content


Workshop Thu, Jul 9, 2026 • 4:00 PM – 1:00 AM PDT ROOM 327

Continual Adaptation at Scale: Towards Sustainable AI

Ghada Sokar ⋅ Gintare Karolina Dziugaite ⋅ Mohammad Emtiyaz Khan ⋅ Rupam Mahmood ⋅ Martin Mundt ⋅ Daniel Marczak
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
4:00 PM
Opening Remarks
4:25 PM
Fast adaptation: a CL perspective
Razvan Pascanu
5:05 PM
Coffee Break
6:10 PM
The Geometry of Forgetting: A Fisher-Information Framework for Alignment-Preserving Continual Adaptation
Soham Batra ⋅ Siddharth Karuturi ⋅ Kaustubh Bukkapatnam ⋅ Laksh Patel
6:20 PM
Aligning Language Models from User Interactions
Thomas Kleine Buening ⋅ Jonas Hübotter ⋅ Barna Pasztor ⋅ Idan Shenfeld ⋅ Giorgia Ramponi ⋅ Andreas Krause
6:30 PM
Fast-weight Product Key Memory
Tianyu Zhao ⋅ Llion Jones
8:00 PM
Lunch
9:40 PM
Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
Van-Tuan Tran ⋅ Shruthi Gowda ⋅ Merim Dzaferagic ⋅ Marco Ruffini
9:50 PM
Merging Adapted Models via Data-Free Covariance Estimation
Marawan Gamal ⋅ Derek Tam ⋅ Pascal Jr Tikeng Notsawo ⋅ Colin Raffel ⋅ Guillaume Rabusseau
10:00 PM
On the Importance of Trivial Baselines: Re-evaluating LoRA Adapter Transfer for Generative Tasks
Andreas Hochlehnert ⋅ Danni Liu ⋅ Jan Niehues ⋅ Shankar Kumar ⋅ Felix Stahlberg
11:00 PM
Coffee Break
11:30 PM
Poster Session
Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio
AVI GUPTA ⋅ Nilotpal Sinha ⋅ Vishnu Raj ⋅ Sambuddha Saha ⋅ Pratik Joshi ⋅ Koteswar Rao Jerripothula ⋅ Tammam Tillo
Semantic Grouping with Dual-Strategy Distributional Rehearsal for Continual Learning
Khoa Le Nho ⋅ Hồ Xuân Hùng ⋅ Thanh Hai Dang ⋅ Duc-Trong Le ⋅ Quynh-Trang Pham Thi
SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
Kexian Tang ⋅ Jiani Wang ⋅ Shaowen Wang ⋅ Kaifeng Lyu
REPO: Detoxifying LLMs via Representation Erasure-based Preference Optimization
Naz Sepahvand ⋅ Eleni Triantafillou ⋅ Hugo Larochelle ⋅ Doina Precup ⋅ Daniel Roy ⋅ Gintare Karolina Dziugaite
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
Damian Sójka ⋅ Sebastian Cygert ⋅ Marc Masana
Functional Task Networks: Cortex-Inspired Spatial Parameter Isolation for Continual Learning
Kevin L McKee ⋅ Yicong Zheng ⋅ Zacharie Bugaud ⋅ Thomas Miconi
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Jiyeon Kim ⋅ Hyunji Lee ⋅ Dylan Zhou ⋅ Sue H Park ⋅ Seunghyun Yoon ⋅ Trung Bui ⋅ Franck Dernoncourt ⋅ Sungmin Cha ⋅ Minjoon Seo
Mitigating Catastrophic Forgetting in Continual RL via Certified Alignment
Maksim Anisimov ⋅ Matthew Wicker ⋅ Francesco Belardinelli
DECAF: De-Clustering for Adaptive Representational Unlearning
Anjie Le ⋅ Can Peng ⋅ Hongcheng Guo ⋅ J. A Noble
Test-Time Training for Visual Foresight Vision-Language-Action Models
Sangwu Park ⋅ Wonjoong Kim ⋅ Yeonjun In ⋅ Sein Kim ⋅ HongSeok Kang ⋅ Chanyoung Park
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
Jeanmely Rojas Nunez ⋅ Viraj V Sawant ⋅ Nathan Allen ⋅ Nomgondalai Amgalanbaatar ⋅ Yannis Zongo ⋅ Kevin Zhu ⋅ Maheep Chaudhary
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
Lawrence Feng ⋅ Gaurav Ghosal ⋅ Jacob Mitchell Springer ⋅ Ziqian Zhong ⋅ Aditi Raghunathan
Rotation-Preserving Supervised Fine-Tuning
Hangzhan Jin ⋅ Tianwei Ni ⋅ Lu Li ⋅ Pierre-Luc Bacon ⋅ Mohammad Hamdaqa ⋅ Doina Precup
Characterizing Plastic Regions in Neural Networks
Gwyneth Liu ⋅ Nir Shavit ⋅ Linghao Kong
Continual Learning of Physical Systems via Derivative Distillation
Claudia Gentili ⋅ Alessandro Trenta ⋅ Andrea Cossu ⋅ Davide Bacciu
MeMo: Memory as a Model
Ryan Wei Heng Quek ⋅ Sanghyuk Lee ⋅ Alfred Leong ⋅ Arun Verma ⋅ Alok Prakash ⋅ Nancy Chen ⋅ Bryan Kian Hsiang Low ⋅ Daniela Rus ⋅ Armando Solar-Lezama
Orthogonal Mixture-of-Expert Low-Rank Adapter for Continual Learning
Zhuoran Xie ⋅ Shichun Yang ⋅ Xu Mohan ⋅ Qingyun Ye ⋅ Jiong Ding ⋅ Chen rui ⋅ Fan Zhou
AV-CTTA: Audio-Visual Continual Test-Time Adaptation without Forgetting
Sarthak Kumar Maharana ⋅ Akshay Mehra ⋅ Bhavya Ramakrishna ⋅ Yunhui Guo ⋅ Guan-Ming Su
Route, Reuse, Repurpose: Continual Adaptation of LLMs with Bounded Adapter Pools
Bilge Celik ⋅ Anna Vettoruzzo ⋅ Joaquin Vanschoren
A loss curvature account of fine-tuning fragility
Ivaylo Dimitrov ⋅ Leo Karoubi ⋅ Sunny Howard ⋅ Dmitrii Krasheninnikov
Organized Plasticity for Cost-Bounded Continual Adaptation
Yourim Choi ⋅ Subeom Park ⋅ Reeahn Kim ⋅ Hyung-Sin Kim
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
Abhijit Chakraborty ⋅ Suddhasvatta Das ⋅ Yash Shah ⋅ Vivek Gupta ⋅ Kevin A Gary
Calibrated Target-Aware Data Selection for Continual Mid-Training in Streams
Ke Wan ⋅ Tianyi Zhao ⋅ Tianhao Huang ⋅ Guanghui Min ⋅ Chen Chen
Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation
Uwe König ⋅ Hamza Kazmi ⋅ Ruizhe Li ⋅ Maheep Chaudhary
Experience-Guided Behavior Adaptation for Large Language Models
Iknoor Singh ⋅ Harjot Singh ⋅ Abhishek Tripathi ⋅ Niresh Agarwal ⋅ Murat Sensoy
Measurement Plasticity: Sensor-Level Adaptation for Vision–Language Models
Boyeong Im ⋅ Wooseok Lee ⋅ Yoojin Kwon ⋅ Hyung-Sin Kim
Provable Forgetting Bounds Drive Capacity Savings: Spectral Thresholding in Continual LoRA
Louis Barinka ⋅ Giulia Lanzillotta ⋅ Enis Simsar ⋅ Tanguy Dieudonné ⋅ Thomas Hofmann
RepSelect: Robust LLM Unlearning via Representational Selectivity
Filip Sondej ⋅ Yushi Yang ⋅ Adam Mahdi
Beyond Classification: Continual Learning for Multimodal Retrieval
Alicja Dobrzeniecka ⋅ Filip Szatkowski ⋅ Sebastian Cygert ⋅ Szymon Lukasik ⋅ Bartłomiej Twardowski