Cross-Task Knowledge Transfer

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 53

All topics

Platonic Task Arithmetic
Oct 1, 2026Junghwan Park, Woojin ChoCross-Task Knowledge Transfer Efficient Task Adaptation
TelePIX
Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning
Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong Liu +2Class-Incremental Learning Few-Shot Learning
School of Computer Science and Engineering, Beihang University · School of Computer Science, Beijing University of Posts and Telecommunications
Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer
Sep 30, 2026Jiahe Fan, Si Chen, Yinghao Hou +4Cross-Task Knowledge Transfer Continual Model Merging
University of Science and Technology of China
Function beyond Form: Functional Correspondence for Cross-Embodiment Dexterous Grasp Generation
Sep 30, 2026Bolin Zou, Wenlong Dong, Mu Ai +4Robotic Grasping Cross-Embodiment Transfer
Shenzhen Key Laboratory of Robotics and Computer Vision, Southern University of Science and Technology, Shenzhen, China. · Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden. · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China. +1
What Makes High-Magnification Knowledge Transferable? A Study of Cross-Resolution Distillation in Whole-Slide Imaging
Sep 29, 2026Zhiyuan Yang, Jiahao Cheng, Mahdi S. HosseiniWhole-Slide Images Cross-Task Knowledge Transfer
Department of Computer Science and Software Engineering (CSSE) Concordia University Montreal, Canada · Department of Computer Science and Software Engineering (CSSE) Concordia University Montreal, Canada Mila – Quebec AI Institute Montreal, Canada
From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis
Sep 28, 2026Longxiao Fan, Tao Zhang, Han Yan +5Neural Processing Units Cross-Task Knowledge Transfer
Fudan University · University of Science and Technology of China · Huawei Technologies Ltd.
Evo2Team: When Do Evolved Skills Transfer? From Selection to Deployment
Sep 28, 2026Renxiang Wang, Jiaming CuiSkills Cross-Task Knowledge Transfer
Virginia Tech, Blacksburg, VA
Beyond Correctness: Evaluating Semantic Knowledge in Cross-Table Transfer
Sep 28, 2026Seokyong Sheem, Hochang Lee, Suyeong Lee +1Tabular Learning Ablation
Korea University
Layer-wise Curriculum Learning for Efficient LLM Compression
Sep 16, 2026Donggeon Lee, Dooyeon Na, Seungmin Oh +1Large Language Model Compression Adaptive Curriculum
Ajou University, South Korea
Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
Sep 15, 2026Yanick C. Tchenko, Felix Mohr, Hicham Hadj-Abdelkader +1Robotic Perception Cross-Task Knowledge Transfer
Universit´e Paris-Saclay, IBISC Laboratory, France. · Universidad de La Sabana, Colombia.
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
Sep 12, 2026Narcis MarincatLanguage Pairs Language Modeling
Independent researcher.
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Sep 8, 2026Zhou Yu, Bin Bi, Shiva Kumar Pentyala +8Agentic Learning Parameter-Efficient Adaptation
Salesforce AI
Probing Factual Knowledge Transfer with Training Data Interventions
Sep 1, 2026Romina Oji, Marc Braun, Marcel Bollmann +2Multilingual Language Models Large Language Model Pretraining
Department of Computer and Information Science Linköping University
Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
Aug 17, 2026Mingyuan Li, Guangsheng Yu, Xu Wang +1Peak Memory Cross-Encoder
ELLIS Institute Finland · University of Turku · University of Technology Sydney
$\varepsilon$ -MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
Aug 12, 2026Aofan Liu, Shiyuan Song, Yiyan QiEvolutionary Search Cross-Task Knowledge Transfer
Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer
Aug 12, 2026Syed Muhammad Raza, Omer Tariq, Jeongbae SonKnowledge Distillation Symbolic Distillation
Perception AI, Neubility Inc., Seoul, South Korea
Black-Box Knowledge Transfer across Distinct Feature Sets
Aug 10, 2026Oh-Ran Kwon, Daeyoung HamCross-Task Knowledge Transfer Unlabeled Data
Department of Statistics, The Ohio State University · Department of Statistics and Data Science, University of Texas at San Antonio
verdi: retrieval is not transfer for continual world model optimization
Aug 10, 2026Junyu Wu, Shiqin Nie, Youyi Kou +9World Models Cross-Task Knowledge Transfer
* Equal contribution · ‡ Project leader, † Corresponding author · † Corresponding author
SAFE-Merge: Data-Free Continual Model Merging with General Knowledge Preservation
Aug 2, 2026Zihuan Qiu, Zhiyang Liao, Chiyuan He +5Continual Model Merging Replay-Based Continual Learning
University of Electronic Science and Technology of China, Chengdu, China · Dalian University of Technology, Dalian, China
Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
Jul 31, 2026Yi Wang, Jitao Zhao, Di Jin +1Graph Foundation Model Cross-Task Knowledge Transfer
Tianjin University Tianjin, China
Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach
Jul 29, 2026Yinghao Hou, Jiahe Fan, Yuanhao Pu +2Cross-Task Knowledge Transfer Multimodal Benchmarks
University of Science and Technology of China
AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control
Jul 29, 2026Jingbo Cui, Jitao Zhao, Di Jin +1Graph Foundation Model Information-Flow Control
School of Computer Science and Technology, Tianjin University Tianjin, China
UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging
Jul 23, 2026Rafsan Jany, Shadab Tanjeed Ahmad, Ahsan Bulbul +3Cross-Modal Distillation Cross-Modal
Korea Institute of Oriental Medicine, Daejeon, South Korea · Islamic University of Technology, Gazipur, Bangladesh
Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach
Jul 23, 2026Yuhua Wang, Xiaodong Li, Yihao Guo +6Soft Prompt Tuning Heterogeneity
School of Artificial Intelligence, Beihang University Beijing, China · Center for the Applied Statistics, School of Statistics, Renmin University of China Beijing, China · School of Computer Science & Technology, Beijing Jiaotong University Beijing, China +2
Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents
Jul 23, 2026Hu Gao, Yulong Chen, Lizhuang MaImage Restoration Cross-Task Knowledge Transfer
Department of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China · Department of Architecture and Design, Harbin Institute of Technology, Heilongjiang, China
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
Jul 12, 2026Yi Zhao, Jiajun Gao, Chenyang Xu +2Electrocardiogram Classification Wearable Devices
School of Mechano-Electronic Engineering · Xidian University · Xi’an, China +5
Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion
Jul 3, 2026Jiawei Sheng, Taoyu Su, Xixun Lin +2Knowledge Graph Completion Cross-Task Knowledge Transfer
Institute of Information Engineering, Chinese Academy of Sciences Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, UCAS Beijing, China
CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection
Jul 3, 2026Wen Dong, Zhao Wang, Shuangqing Zhang +5Replay-Based Continual Learning Logical Anomalies
Nanjing University, Nanjing, China · China Mobile Zijin Innovation Institute, Nanjing, China · Nanjing University of Science and Technology, Nanjing, China
KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers
Jul 1, 2026Eric Benz, Lennart Stöpler, Nikolai Bolik +1Multimodal Knowledge Editing Cross-Task Knowledge Transfer
Heidelberg University
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
Jun 29, 2026M. K. ArabovMultilingual Language Models Large Language Model Benchmarks
Kazan Federal University, Institute of Computational Mathematics and Information Technologies, Department of Data Analysis, Kazan, Russia
LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
Jun 24, 2026Zhihao Gu, Lin WangRobotic Manipulation Cross-Task Knowledge Transfer
School of EEE, Nanyang Technological University
Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
Jun 14, 2026Yuyang Dai, Yushun DongAttacker Large Language Model Honeypots
Florida State University
Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records
Jun 10, 2026Feiqing Huang, Zongqi Xia, Rong Ma +1Rare Disease Electronic Health Records
Department of Biostatistics, Harvard T.H. Chan School of Public Health · Department of Neurology, University of Pittsburgh · Department of Data Science, Dana-Farber Cancer Institute +1
Hierarchical Projection for Adaptive Knowledge Transfer
Jun 7, 2026Samhita Pal, Tian GuTransfer Learning Domain Adaptation
Vanderbilt University Medical Center · Columbia University
Continual Quadruped Robots Coordination via Semantic Skill Discovery
Jun 6, 2026Daoqing Wang, Yuchen Xiao, Weixuan Huang +5Multi-Robot Systems Legged Robots
National Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China · Polixir Technologies, Nanjing, China
HyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift
Jun 2, 2026Yu-Kai Chan, Wen-Sheng Lien, Dong-Ting Yao +4Multimodal Knowledge Editing Knowledge Graph Embeddings
National Yang Ming Chiao Tung University Hsinchu, Taiwan
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
Jun 1, 2026Haoben Huang, Shuxin Liu, Ou Wu +1Multimodal Knowledge Editing Cross-Task Knowledge Transfer
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China · College of Information Engineering, Zhejiang University of Technology, Hangzhou, China
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
May 31, 2026Anushka Tiwari, Kaiyi JiReplay-Based Continual Learning Cross-Task Knowledge Transfer
Institute for Artificial Intelligence and Data Science, University at Buffalo, Buffalo, NY, USA · Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression
May 31, 2026Wendao Wu, Fangqing Zhang, Haihan Zhang +1Cross-Task Knowledge Transfer Knowledge Distillation
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University, China · School of Mathematical Sciences, Peking University, China
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs
May 30, 2026Subhadip MitraSafety Alignment Red-Teaming
Research Lead, Rota Labs
SLAD : Shared LoRA Adapters for Task Specific Distillation
May 28, 2026Reda Bensaid, Yassir Bendou, Vincent Gripon +1Low-Rank Adaptation Adapters Wireless Foundation Models
IMT Atlantique, Brest, France · Polytechnique Montr´eal, Montr´eal, Canada
Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
May 28, 2026Mengdi Chu, Yang Liu, Ayan Biswas +1Wireless Foundation Models Distribution Shifts
The Ohio State University · Los Alamos National Laboratory
Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning
May 25, 2026Bo Zou, Chao XuLarge Language Model Alignment Chain-of-Thought Reasoning
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
May 22, 2026Anastasiia Sedova, Natalie Schluter, Skyler Seto +1Cross-Lingual Transfer Cross-Task Knowledge Transfer
1Apple
Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling
May 12, 2026Chenran Zhao, Dianxi Shi, Yaowen Zhang +2Offline Reinforcement Learning Cross-Task Knowledge Transfer
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · Institute of Military Transportation, Tianjin, China · Intelligent Game and Decision Lab (IGDL), Beijing, China
Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer
May 12, 2026Nilushika Udayangani, Kishor Nandakishor, Marimuthu PalaniswamiCross-Task Knowledge Transfer Time-Series Classification
Department of Electrical and Electronic Engineering University of Melbourne Parkville, VIC 3052, Australia
Relational Retrieval: Leveraging Known-Novel Interactions for Generalized Category Discovery
May 10, 2026Yulin Xu, Chunqi Guo, Yuanzhen Shuai +1Generalized Category Discovery Multimodal Domain Generalization
University College London London, UK · Juniata College Huntingdon, USA
XPERT: Expert Knowledge Transfer for Effective Training of Language Models
May 9, 2026Chang Liu, Boyu Shi, Xu Yang +1Mixture-Of-Experts Cross-Task Knowledge Transfer
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China.
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
May 9, 2026Zhen-Hao Xie, Yan Wang, Hao Sun +3Class-Incremental Learning Multimodal Domain Generalization
School of Artificial Intelligence and the State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China
MBP-KT: Learning Global Collaborative Information from Meta-Behavioral Pattern for Enhanced Knowledge Tracing
May 9, 2026Yuhao Jia, Duantengchuan Li, Jinsong Chen +4Cross-Task Knowledge Transfer Knowledge Graph Embeddings
Faculty of Artificial Intelligence in Education, Central China Normal University · School of Information Management, Wuhan University · School of Big Data and Artificial Intelligence, Chizhou University
Structure-Centric Graph Foundation Model via Geometric Bases
May 9, 2026Xiaodong He, Haolan He, Ruiyi Fang +2Graph Foundation Model Geometric Machine Learning
University of Electronic Science and Technology of China, Chengdu, Sichuan Province, China · Western University
Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation
May 2, 2026Xitie Zhang, Aming Wu, Yahong HanHuman-To-Robot Transfer Robotic Manipulation
School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University, China · School of Computer Science and Information Engineering, Hefei University of Technology, China
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
Apr 23, 2026Weisi Liu, Guangzeng Han, Xiaolei HuangCross-Task Knowledge Transfer
University of Memphis

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Platonic Task Arithmetic

Junghwan Park, Woojin Cho

TelePIX

Cross-Task Knowledge Transfer Efficient Task Adaptation Weight-Space

Open paper AskPDF arXiv

Models specialized for the same task converge to similar behavior, yet the parameter updates that produce it share no common coordinate system, so weight-space task arithmetic stays confined to a single model and cannot cross architectures without a structural correspondence. Drawing on Plato's allegory of the cave, we hypothesize that these model-specific updates are shadows of one shared, model-agnostic object, which we call the platonic task vector. To make it operational for models that pair an image or audio encoder with a text encoder, we introduce Universal Task Descriptors: matrices whose shape is independent of architecture and embedding dimension, which record a task's functional effect and support addition and negation as matrix operations. Transferring a descriptor into a target means editing the target until it reproduces the descriptor on the task's unlabeled probe images and class-name prompts, requiring no per-image labels. We realize this edit in two ways. First, the descriptor factorizes into a shift field on image embeddings, so a single least-squares solve yields a linear operator that folds into the target's last layer as a weight edit; by linearity, a bank of such operators admits any composition at any strength as a signed sum. Second, a low-rank adapter trained on the same objective reaches every layer and fits compositions jointly, at the cost of one optimization per edit. Heterogeneous models share this object only partially, with a model-specific residual comparable in norm to the shared component, yet cross-model transfer still retains 74-80 percent of the gain of the target's own descriptors. Experiments across six model families, eight classification tasks, and an audio-text setting show that task knowledge transfers and composes across heterogeneous models under both realizations.

Momentum

Related topics

Latest papers 53