Transfer Learning

Ask about this topic

Overview

Transfer learning asks how a model trained on one task or domain can help with another, reducing the need for target-specific data and computation. Common approaches include pretraining followed by fine-tuning or parameter-efficient adapters, feature alignment for domain shifts, and knowledge transfer through distillation, model merging, or shared representations. Evaluations span zero-shot and few-shot transfer, cross-domain benchmarks in vision and language, and adaptation in settings such as clinical data, robotics, and scientific modeling. A central tension is that transferred knowledge can improve accuracy and sample efficiency or cause negative transfer; predicting when it will help, and separating reusable knowledge from dataset or architecture effects, remains difficult.

Latest papers

CardsList

422 papers62 papers in the last four weeks, up 29% on the four weeks before. 0.4% of all new papers.

Aug 26, 2026

Cross-simulator transfer with foundation model summaries: Towards robust SKA-era reionization inference

Simulation-based inference (SBI) for parameter estimation is vulnerable to model misspecification: neural summaries and density estimators trained on a specific forward model typically fail when applied to data drawn from another model, or from real observations, and no training simulator can capture the full observational pipeline of a real measurement exactly. We show that a self-supervised Vision Transformer (ViT), pretrained label-free on a fast approximate simulator, produces transferable data summaries that generalize across simulators. Without retraining, it can be reused as a frozen encoder to infer astrophysical parameters from a completely different simulator that resolves the radiative transfer explicitly, on which it has never seen either data or parameters. As a concrete use case in 21cm cosmology, SKATR, a ViT pretrained with a Joint Embedding Predictive Architecture (JEPA), serves as a foundation model for reionization inference from upcoming SKA measurements: SKATR is pretrained once on 67k low-cost, noiseless semi-numerical 21cmFAST lightcones, then frozen and applied to hydrodynamical Loreli II lightcones, where a lightweight conditional flow matching head infers five astrophysical parameters; the encoder is never shown Loreli data, its parameters, or any noise. In our comparison, SKATR yields the most precise and best-calibrated posteriors across all five parameters, matching the accuracy of the fully-supervised in-domain baseline while requiring 2.6x fewer radiative-transfer simulations. Under realistic SKA AA* noise, only SKATR remains simultaneously accurate, informative, and calibrated, outperforming even a supervised baseline retrained from scratch on noisy data. Self-supervised pretraining on computationally efficient semi-numerical simulations is therefore a viable route to calibrated, simulator- and noise-agnostic reionization inference for the SKA-era.

Yannic Pietschke, Caroline Heneka, Ayodele Ore +1

Institut für Theoretische Physik, Universität Heidelberg, Philosophenweg 16, 69120 Heidelberg, Germany · Max Planck Institute for Radioastronomy, Auf dem Hügel 69, Bonn, 53121, Germany

Simulation-Based InferenceTransfer LearningSelf-Supervised Pre-TrainingVision Transformer
AskPDF
Aug 26, 2026

A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks

Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems. We investigate this question by fine-tuning Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluating the resulting model, without additional deep-learning training, on four complementary downstream settings: cross-dataset odor descriptor prediction, odorous-versus-odorless classification, enantiomer evaluation, and odor mixture discriminability. The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations. The enantiomer analysis further shows that three-dimensional molecular representations distinguish mirror-image molecules in a way that two-dimensional graph models fundamentally cannot, although accurately predicting the perceptual consequences of stereochemistry remains an open challenge. Together, these results support a train-once, transfer-across-tasks paradigm for machine olfaction and suggest that chemically pretrained molecular representations provide a strong foundation for transferable olfactory prediction.

Yikun Han, Yi Wang, Neil Mankodi +2

Department of Statistics, University of Michigan, Ann Arbor, Michigan, USA · Computer Science and Engineering Division, University of Michigan, Ann Arbor, Michigan, USA

Molecular Foundation ModelsTransfer LearningMolecular Representation LearningMolecular Property Prediction
AskPDF
Aug 25, 2026

DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning

Digital mobility outcomes (DMOs) derived from wearable sensors characterise mobility in daily life and offer a promising means of monitoring disease progression. However, existing DMO studies have typically focused on either a single disease or a single visit. To the best of our knowledge, we are the first to define and study the practical problem of cross-disease longitudinal DMO modelling. We argue that this problem should satisfy at least two requirements. First, the temporal progression of DMOs should be modelled within each disease, as mobility-limiting diseases evolve over time. Second, multiple mobility-limiting diseases should be modelled jointly, as different diseases affect different aspects of human mobility. To address this problem, we propose DeMMO, an interpretable framework for longitudinal, multi-disease, and multi-outcome learning. Its central technical contribution is an interpretable cross-disease and cross-outcome relation-learning mechanism that infers signed relations directly from learned longitudinal DMO-outcome mappings, thereby enabling selective information sharing across cohorts without requiring paired participants. We evaluate DeMMO on the recently released, large-scale, multicentre Mobilise-D dataset, which presents a challenging modelling setting involving longitudinal observations, multiple clinical outcomes, and four participant-disjoint cohorts representing distinct mobility-limiting diseases. Compared with eight strong structural longitudinal and deep-regression baselines, DeMMO achieves the best overall predictive performance and outperforms the baselines for most individual outcomes. Stability selection further identifies reliable longitudinal DMO patterns that can inform subsequent clinical validation and disease monitoring. The implementation code is available at https://github.com/menghui-zhou/DeMMO.

Menghui Zhou, Zhipeng Yuan, Vitaveska Lanfranchi +1

School of Computer Science, University of Sheffield, Sheffield, United Kingdom

Clinical Outcome PredictionMulti-Task LearningTransfer LearningWearable Health Monitoring
AskPDF
Aug 24, 2026

UHI-Bench: Benchmarking Dual-Source Urban Heat Island Modeling Across Cities in Diverse Climate Regimes

Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface temperature UHI (LST-UHI) and near-surface air temperature UHI (AirT-UHI), capture physically distinct aspects of urban heat. However, most studies rely on a single source, and substituting one for the other can substantially bias the magnitude and spatial variability of human heat exposure. Accurate UHI modeling also requires dynamic meteorological drivers and static urban morphology features, but spatiotemporal incompatibilities hinder their alignment. Cloud gaps in LST observations and sparse AirT station networks further limit dual-source UHI modeling, motivating cross-city transfer across diverse climates. To bridge these gaps, we introduce UHI-Bench, the first UHI benchmark for dual-source UHI modeling that integrates dynamic and static environmental context. Following a unified signal, mechanism, and transfer framework, it evaluates over 20 baselines from four model families on five tasks across 20 cities and nine Köppen climate classes. Results show that no model is uniformly best, although foundation models remain consistently competitive and stable. Environmental covariates generally improve performance, but their utility varies across sources and tasks. Cross-city transferability is better explained by overlap in UHI regimes than by climate-zone similarity. With the dataset and standardized pipeline, our work provides practical guidance for urban heat modeling, promotes climate data equity, and supports future advances in climate research.

Wanyun Ling, Chenxi Liu, Yi Xie +3

Department of Operations and Technology Technical University of Munich Heilbronn, Germany · Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences Hong Kong SAR, China · Faculty of Computer Science RWTH Aachen University Aachen, Germany +2

Benchmark DesignClimate ScienceTransfer Learning
AskPDF
Aug 23, 2026

From Symmetry to Invariance: Learning Galois Equivalent Representations in Finite Fields

Neural networks can learn algebraic operations from finite examples, but it remains unclear whether this ability transfers across mathematically equivalent representations of the same operation. We study this question through multiplication in finite fields under changes of basis. The Galois action organizes basis representations into orbits, and bases in the same orbit induce the same coordinate multiplication map. This structure allows us to separate learning multiplication from transferring it to basis representations that are not used for training. We examine several ways of providing or recovering the relevant orbit structure, including invariant labels, basis matrices, orbit recognition, and algebraic decomposition. Our main approach trains a model to predict the Galois action between basis representations. Repeated applications of the learned transformation are then used to construct a canonical representative for each orbit, which supports multiplication on held-out bases through exact canonical matching. This provides a concrete mechanism for converting a learned algebraic symmetry into an invariant representation that can be used for transfer.

Zheng Zhang, Na Zhang

Department of Mathematics, Towson University, 7800 York Rd, Towson, MD 21204, USA

Invariant Representation LearningEquivariant Representation LearningTransfer Learning
AskPDF
Aug 23, 2026

Tracing the Unlabeled Storm: Cross-Variable Transfer in a Lagrangian Atmospheric JEPA Framework

Deep atmospheric convection governs South Asian monsoon variability, yet attempting to learn its latent world model directly from zero-inflated, heavy-tailed precipitation yields suboptimal predictive representations. Continuous atmospheric proxies, such as outgoing longwave radiation (OLR), express this convective organization far more coherently. We address this mismatch with cross-variable proxy learning: M-JEPA, a multiscale Monsoon Joint-Embedding Predictive Architecture, is pretrained on five continuous proxy fields over Lagrangian patches tracking moving convective systems---without rainfall supervision at any point. The resulting frozen representation is transferred to daily precipitation forecasts through a shared decoder trunk featuring parallel probabilistic and deterministic branches. Because rainfall is strictly unobserved during pretraining, downstream skill directly measures the predictive information captured in the latent rollout. A frozen-backbone probing framework with two controls (an identical architecture trained on rainfall alone, and a randomly initialized backbone) attributes the transfer specifically to proxy pretraining: direct rainfall training exhibits 36%36\% higher CRPS error (7.527.52 vs.\ 5.545.54,mm/day). Against the 51-member operational ECMWF ensemble, the transferred model attains a statistically resolved CRPS advantage (6.816.81 vs.\ 6.896.89,mm/day) and higher Brier skill (+0.05+0.05 vs.\ −0.04-0.04) using 15.415.4M parameters on a single consumer GPU, concentrated at heavy-rain thresholds and fine spatial scales, while the ensemble retains an advantage in neighborhood skill and deterministic references on point metrics. The result provides a competitive monsoon precipitation forecast grounded in intraseasonal dynamics and a diagnostic framework for evaluating transferred atmospheric representations.

K M Anirudh, S Sandeep, Hariprasad Kodamana

Centre for Atmospheric Sciences, IIT Delhi, New Delhi, India · Yardi School of Artificial Intelligence, IIT Delhi, New Delhi, India · Department of Chemical Engineering, IIT Delhi, New Delhi, India

Precipitation ForecastingSpatiotemporal ForecastingJoint-Embedding Predictive ArchitectureTransfer LearningProbabilistic Forecasting
AskPDF
Aug 23, 2026

TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders

Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand datasets, in contrast to the abundance of human body motion data. We address this limitation by transferring motion representations learned from large body pose corpora to the hand domain. We introduce TransHands, a backbone-agnostic transfer learning framework that enables pre-trained human motion encoders to be effectively adapted for 3D hand pose estimation from 2D pose inputs. Rather than training hand-specific biomechanical models from scratch, TransHands combines a two-stage training and fine-tuning strategy with a lightweight hand-specific input adaptation module that aligns hand kinematics with the representation space learned for full-body motion. We evaluate TransHands across four state-of-the-art motion modeling architectures, including transformer-based, graph-based, and frequency- domain models. Results demonstrate that motion priors learned from body pose data transfer consistently across architectures, yielding consistent accuracy gains, strong cross-domain generalization, particularly in challenging egocentric settings, and applicability for downstream tasks in real-world contexts.

Milo Piccioli, Gianluca Amprimo, Claudia Ferraris +1

Politecnico di Torino, Torino, Italy · Consiglio Nazionale delle Ricerche, Torino, Italy

3D Hand Pose EstimationTransfer LearningCross-Domain Transfer LearningMotion Representation Learning
AskPDF
Aug 22, 2026

How Architecture and Training Affect TPC Representations Across Experiments

Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representations to be reused beyond the experiments in which they were developed. This work evaluates the reusability of representations across experiments and detector systems using probes on frozen encoders. These probes reveal task-relevant structure before downstream adaptation, complementing fine-tuning. Together with random-weight controls, they distinguish contributions from architecture and encoder training that downstream performance alone cannot resolve. Time projection chamber (TPC) data provide a useful testbed because events from TPC systems can be represented as variable-length sparse tensors, while detector geometries, event topologies, and scientific tasks can differ substantially. We investigate whether fixed-dimensional TPC event representations can be reused across classification tasks, experiments, and detector systems. Sparse ResNet and PointNet-style encoders produce 512-dimensional embeddings for four datasets from the GADGET II TPC and AT-TPC. Randomly initialized encoders isolate the contribution from architecture before supervised training. We then train each encoder on a classification task, freeze its parameters, and train a linear or nonlinear probe for each downstream task. We find that this architecture-induced structure remains useful across experiments and detector systems. The randomly initialized PointNet-style representation is highly informative on several tasks. The two architectures organize their embedding spaces differently, but neither exhibits a large, systematic loss of utility cross-detector. These results show that architecture is a major source of task-relevant structure in TPC embeddings and should be treated explicitly when assessing representation learning and developing reusable detector models.

Tyler Wheeler, Michelle P. Kuchera, Raghuram Ramanujan +12

Department of Computational Math, Science, and Engineering, Michigan State University, East Lansing, MI, USA · Department of Physics, Grand Valley State University, Allendale, Michigan, USA · Department of Physics, Davidson College, Davidson, NC, USA +5

Representation LearningTransfer LearningPoint Cloud Learning
AskPDF
Aug 21, 2026

When does fusing hand-crafted knowledge with learned representations pay? A cost-normalized benchmark of stacking, substitution, and interference

Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or harms. We benchmark one fixed hand-crafted knowledge source, a pinned bank of Gabor targets injected only during training at ∼\sim2% overhead, against data-driven alternatives (SimCLR, SimSiam, DINO, ImageNet transfer, augmentation, learned teachers) under one frozen recipe with fixed subsets: 13 datasets, 9 backbones, 150 to 1.28M images, 32--224,px, 2.5M--86M parameters (\computeCells\computeCells classification configurations over \computeRuns\computeRuns runs, plus segmentation and detection transplants). Across the training-time combinations we measure, three outcomes recur (decision-level fusion differs). Different-currency sources can stack: the prior composes with DeiT augmentation on attention backbones and is worth +26+26 points to ViT-B/16 at 224224,px, +6.7+6.7 at twice that budget. Same-currency sources substitute: against effective self-supervised pretraining, the combination never usefully exceeds the better single source. Fusing at full strength into an already-informed initialization interferes in proportion to what it carries: ImageNet transfer, −15-15 to −17-17 points, removed by a weaker auxiliary weight. Frozen-feature diagnostics measured on each source alone separate these outcomes retrospectively but do not predict them: a rule built on them calls one of nine unseen pairs. At a practitioner's own label budget, the frozen-feature gain predicts the end-to-end gain to within 0.170.17 points across 30 cells and seven datasets; the underlying decomposition, Δ=G+\readout(base)Δ= G + \readout(\mathrm{base}), holds in sign on \auditRate%\auditRate\% of testable cells and is called an unseen backbone family's feature gain in advance. The project page is https://amughrabi.github.io/MomentAux.

Ahmad AlMughrabi, Albert Clop, Benjamin Busam +2

Universitat de Barcelona, Barcelona, Spain · Technical University of Munich, Munich, Germany · Universitat Pompeu Fabra, Barcelona, Spain

Representation LearningImage ClassificationTransfer LearningSelf-Supervised Pre-Training
AskPDF
Aug 21, 2026

Lift, Associate, and Fuse: A Decision-Centric Framework for 2D-to-3D Foundation Model Transfer

Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representation. Those groupings obscure the decisions that determine whether a system remains coherent across views: where image evidence is grounded, when observations become one identity, how semantic and granularity conflicts are handled, which information is fused, and what state survives for later queries. We introduce Lift, Associate, and Fuse (LAF), a decision-centric framework that represents a transfer system as five operators: Generate, Associate, Reconcile, Fuse, and Persist/Query. LAF defines an explicit contract for the persistent carrier---its spatial support, semantic state, identity state, uncertainty, provenance, and supported operations---and identifies the first stage at which discarded evidence becomes unrecoverable. We operationalize the framework as a structured audit protocol and apply it to 161 systems available through 7 August 2026, spanning point-, field-, Gaussian-, object-, graph-, and memory-based carriers. Representation, temporal, relational, and feed-forward stress tests required no additional analytical stage after the final confirmation pass. The resulting decision traces expose four recurring properties: association does not establish identity; carrier design fixes both the query interface and correction boundary; rendered-view, native-3D, and proposal-level evaluations are not interchangeable; and qualifiers such as training-free, real-time, open-vocabulary, and generalizable are meaningful only when attached to a stage and a complete cost ledger. LAF therefore supplies a representation-neutral method for comparing existing systems, diagnosing irreversible failures, and specifying revisable 3D perception for future agents.

Wentao Sun, Yiping Chen, John S. Zelek +1

Department of Systems Design Engineering, University of Waterloo, N2L 3G1 Waterloo, Canada · School of Geospatial Engineering and Science, Sun Yat-sen University, 519082 Zhuhai, China

Transfer Learning3D Semantic Segmentation3D Foundation ModelsData Association
AskPDF
Aug 20, 2026

Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents

Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may transfer unreliably and can even harm the agent that retrieves them. When agent-induced skills transfer reliably across tasks remains an open question. We conduct a comprehensive and controlled study of how the way skills are induced shapes their transfer across tasks. Specifically, we compare task-level with subtask-level skill induction and text with code skill formats, the two axes along which existing methods differ. Task-level skills mostly reduce the agent's performance below its no-memory baseline while subtask-level skills raise it above on average, and text skills transfer better than code skills. To further understand our findings, we examine two complementary properties of the induced skills: specificity, which measures how closely a skill matches real tasks, and abstractness, which measures how evenly its relevance spreads across tasks. Neither property alone predicts task success, but their combined effect does, which we propose as a skill utility score. The score correlates consistently with task success when skills are transferred, and subtask-level and text skills score higher. Computing skill utility only needs the skills and task descriptions, so our score serves as a lightweight diagnostic of a skill memory for practitioners.

Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian +1

Computer Science Department, Stony Brook University, Stony Brook, USA

LLM Agent Skill LearningLLM Agent Skill EvaluationMemory-Augmented Language Model AgentsTransfer LearningNegative Transfer
AskPDF
Aug 20, 2026

Transfer Learning in Nonparametric Regression with Deep ReLU Networks

This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a common structure along with group-specific deviations in additive form, the proposed method employs a two-stage offset learning procedure: the first stage pools data from all groups to estimate an overall mean function, and the second stage estimates offsets for each group, yielding final group-level estimators through additive combination. Upper bounds on the L2\mathcal L_2 error are established for the proposed framework, covering a broad class of nonparametric estimators under mild complexity and noise conditions. When instantiated with deep ReLU networks, explicit convergence rates are derived under hierarchical composition models, demonstrating the ability to overcome the curse of dimensionality. Conditions that enable positive transfer with faster rates are considered, including learning with simpler functions and data augmentation through pooling samples across groups. Various simulations and real-data experiments further validate the effectiveness of the proposed method.

Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen +1

Department of Statistics and Data Science, University of California, Los Angeles, California, USA · Department of Statistics and Data Science, Washington University in St. Louis, Missouri, USA · Department of Information Systems, Business Statistics and Operations Management, Hong Kong University of Science and Technology, Hong Kong, China.

Transfer LearningNonparametric RegressionStatistical Learning TheoryMulti-Task Learning
AskPDF
Aug 19, 2026

SceneGTMM: A Conformal Mapping-based Scene-Aware Transferable GNN-Transformer Dual-Graph Interaction Framework for Map Matching

Map matching is a key technology connecting positioning data with high precision road networks, but it faces challenges in noise robustness, cross regional transfer, and interpretability. To addr ess the limitations of existing methods in local global fusion, dynamic road network adaptation, and reliance on black box mod els, this paper proposes SceneGTMM, a transferable GNN Transformer dual graph interaction map matching framework based on a conformal mapping based scene relative strategy. 1) Conformal mapping based scene relative strategy: constructs trajectory centric local coordinate systems to reduce dependence on the training road network, supporting cross regional transfer and dynamic road network updates; 2) GNN Transformer dual graph interaction architecture: a GNN modeled road graph captures local topological constraints, while a Transformer modeled trajectory graph captures global temporal dependencies, and cross graph attention achieves noise suppression and semantic alignment; 3) CRF enhanced structured prediction: combines the global context of the Transformer with the topological transition constraints of CRF to improve path connectivity and robustness. Experiments show that SceneGTM achieves over 80% accuracy on multi source trajectories with positioning errors of 16 50 meters, representing a 5.3% improvement over HMM. In cross city transfer scenarios, it outperforms MTrajRec, GraphMM, and TMM, and enhances interpretability through attention and relative coordinate visualization. This study provides a new paradigm for high precision, transferable map matching for real time traffic perception and autonomous driving path planning.

Yongliang Zhang, Feng Song, Ji Chen +6

Amap, Alibaba Group,beijing,china

Intelligent Transportation SystemsSpatiotemporal GNNsTransfer Learning
AskPDF
Aug 19, 2026

Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR

Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes capability expansion costly. We therefore study continual RLVR, which updates the existing model as each task arrives. The central question is whether a model updated this way can perform as well as a jointly trained model. To answer this question, we introduce Continual Reasoning Gym, a continual-RLVR environment that organizes text and visual reasoning tasks into five task sequences. In this setting, we identify two key observations: Sequential RLVR exhibits modest forgetting, yet its final performance remains below that of MTRL. To understand the latter, we decompose final performance and show that forgetting accounts for only part of the gap. To explain the former, we identify shared reasoning: transferable reasoning structure allows training on one task to support others on average. We therefore introduce Continual Prompt Replay (CPR), which harnesses shared reasoning to improve learning on the arriving and future tasks by replaying previous-task prompts and regenerating their responses with the current policy. On average, only CPR reaches MTRL-level performance.

Lirui Luo, Guoxi Zhang, Hongming Xu +3

State Key Lab of General AI, School of Intelligence Science and Technology, Peking University · State Key Laboratory of General Artificial Intelligence, BIGAI · Beijing Institute of Technology +1

RL for Language Model ReasoningReplay-Based Continual LearningTransfer LearningReinforcement Learning with Verifiable RewardsContinual RL
AskPDF
Aug 19, 2026

What Does Attention Transfer Transfer? Attention Structure and Robustness in Vision Transformers

Vision transformers (ViTs) trained to copy a pretrained teacher's attention maps recover most of fine-tuning's in-distribution accuracy yet fall measurably short of it under distribution shift, as recent work has shown. What the copy delivers has never been measured directly in the attention structure and tied to robustness. We build that instrumentation for ViT-S students of a self-supervised teacher on ImageNet-100, and report three findings that triangulate one conclusion. First, the transfer is essentially perfect and permanently so: the distilled student's attention ends up roughly two orders of magnitude closer to the teacher's than fine-tuning does, and does not drift with additional training. Second, the gap is real at 14×\times fewer parameters and 10×\times less data than previously studied, but it has a time axis. It tracks training maturity, and completing the schedules that the stopping rule interrupted closes it below our pre-registered threshold in two of three seeds, with comparisons at equal accuracy giving the same result. The endpoint gap at this scale is substantially a training-maturity artifact: robustness matures later than accuracy, and stopping rules tuned to accuracy undersample it. Third, forcing cross-row redundancy down by half the structural separation between the distilled and fine-tuned conditions produces no detectable robustness response under two registered ways of matching accuracy. Verified transfer, a gap that closes while the structure never moves, and a null under direct intervention are together consistent with the deficit residing in features, not in the visible attention structure. This is elimination plus intervention, and its scope is the regime we measured. In this regime, attention overlays show where a model looks, not what it knows.

Jesse Ponnock

Johns Hopkins University

Vision TransformerTransformer AttentionTransfer LearningKnowledge Distillation
AskPDF
Aug 18, 2026

Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models

Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly find that adding a generation objective leaves understanding flat. Joint-training studies cannot settle the disagreement: with overlapping supervision, a gain cannot be attributed to the architecture rather than the data. To further investigate the relationship between the two directions in UMMs, we separate them by construction. A novel visual entity, a rendered 3D asset paired with a pseudo-word screened for absence from the frozen model's behavior, is bound through exactly one task direction, and the untrained direction is then measured. We find that the channel is real in both directions, but the directions differ in kind: generation training installs a name the model can only match among candidates; understanding training installs one it can also produce. What governs cross-task usability is where the binding enters the shared computation. An alignment probe predicts export across 36 configurations (Spearman ρ=+0.68ρ= +0.68). That objective's alignment term, maximized in closed form over activations with every weight frozen, makes a concept drawable when injected at layer 7 of 28 and is indistinguishable from the base model from layer 14 on, while the weight-based version of the same edit peaks at layers 10-14. In an observational series of four models, this window appears only where the understanding pathway is a semantic vision encoder, suggesting that unified weights are not enough: the two directions must share a semantic format at the entry point. Exploiting the rule, a mid-stack alignment objective acquires the concept for a 0.1%0.1\% relative loss of the model's general text-to-image ability, against 41%41\% for the standard generative route. Our code is at https://github.com/Zane-ZYQiu/entry-point-umm.

Zongyang Qiu, Yihan Wu, Kaixuan Fan +2

The Hong Kong University of Science and Technology (Guangzhou) · Columbia University · MMLab, CUHK +1

Unified Multimodal ModelsMultimodal GenerationCross-Modal AlignmentTransfer Learning
AskPDF
Aug 18, 2026

Understanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics

Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting that no single curriculum is universally optimal and raising a fundamental question: what determines when curriculum learning works? In this paper, we answer this question by analyzing the optimization dynamics induced by different curriculum schedules. We show that the transfer relationship between different difficulty levels characterizes the optimization dynamics induced by curriculum learning, which in turn explains the effectiveness of different curriculum schedules, and formalize this relationship as Relative Transfer, a principled measure of cross-difficulty knowledge transfer. Based on this measurement, we derive Transfer-aware Dynamic Curriculum Sampling (TDCS), which dynamically adjusts the sampling distribution according to the estimated transfer relationship throughout training. Extensive experiments on multiple reasoning benchmarks demonstrate that TDCS consistently outperforms representative scheduling strategies across different tasks, model scales, and training paradigms. More importantly, our work provides a unified optimization-based explanation of curriculum learning through cross-difficulty transfer.

Zhikai Ding, Ziyi Ye

Fudan University

Curriculum LearningLLM TrainingTransfer Learning
AskPDF
Aug 16, 2026

CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications

Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representation learned in one deployment can fail when viewpoint, traffic, illumination, and propagation geometry change. This paper presents CM-MAE, a self-supervised vision--wireless pretraining framework for cross-scenario representation transfer. The evaluated real-data model uses only RGB frames and the measured 64-beam received-power vector available in DeepSense 6G; it does not use ray-traced paths, calibrated depth, or beam-index labels during pretraining. Its central pretraining term is a soft contrastive alignment loss. Instead of making the synchronized image--wireless pair the only positive pair, this loss builds a target distribution from similarities between measured beam-power profiles, so nonidentical samples with similar directional responses are not forced apart as false negatives. A masked joint decoder provides the complementary local objective by reconstructing hidden visual patches and wireless angular clusters under modality dropout. After pretraining, a differential-rate fine-tuning rule lets a new fusion head adapt quickly while the encoders move slowly. Under a sequence-disjoint DeepSense 6G protocol, adding the soft alignment loss improves a matched linear-probe transfer average from 24.88% to 29.49%. Mild fusion fine-tuning reaches 77.38% Top-1 accuracy on unseen Scenarios 6--8, and optional transductive normalization adaptation reaches 78.69%. Since the fusion setting uses the contemporaneous 64-beam power vector at inference, these results should be read as representation-transfer diagnostics, not as proactive beam-prediction or reduced-sweeping claims.

Yubo Zhang, Yiyao Liu

Cross-Modal Representation LearningSelf-Supervised Pre-TrainingMultimodal LearningTransfer LearningMultimodal Contrastive Learning
AskPDF
Aug 16, 2026

TransfHAR: Self-Supervised Wrist Representations for On-Demand Activity Recognition

Fine-grained wrist activity recognition can support applications such as procedural step guidance and context-aware assistance, yet acquiring labeled data for every new task, user, and activity granularity remains a bottleneck. We present TransfHAR, a self-supervised wrist IMU framework for on-demand, fine-grained activity recognition by learning transferable motion priors from global, unlabeled activities. We show that self-supervised pretraining on coarse wrist IMU activities (e.g., sitting, walking, exercise) learns motion structure rich enough to transfer to fine-grained manipulative, gestural, and procedural activities (e.g., snapping, stirring, waving) that are absent from pretraining. We implement TransfHAR as a real-time smartwatch application that lets users define and expand their own activity set for personalized recognition from only a few demonstrations. Across three offline cross-dataset evaluations, TransfHAR matches or exceeds fully supervised baselines that use complete label sets with equal or additional sensor channels, by 6.2 balanced-accuracy points on average. In an in-lab study with 10 participants each performing seven novel wrist activities, TransfHAR reaches 86.7% balanced accuracy across participants with five examples per class and 90.4% when updated from a single one-minute recording per class. These results indicate that broad self-supervised wrist pretraining provides an effective foundation for on-demand fine-grained activity recognition.

Aidan Bradshaw, Riku Arakawa, Xin Liu +1

Northwestern University Evanston, Illinois, USA · Carnegie Mellon University Pittsburgh, Pennsylvania, USA · Google Seattle, Washington, USA

Human Activity RecognitionWearable SensingTransfer LearningSelf-Supervised Learning
AskPDF
Aug 14, 2026

Small Models Scout Bottleneck Order for Large-Model Data Control

Small proxy models are commonly used to identify data mixtures for larger-scale training. We ask whether their training trajectories reveal another transferable structure: the order in which larger models should resolve skill bottlenecks. We formulate first-passage skill training, where each monitored skill has a target floor and the objective is to minimize the tokens required to reach all floors. We introduce LogFloor, a closed-loop controller that directs each round toward current bottlenecks, producing phase-ordered resolution trajectories. Across five bAbI skill slices on Qwen2.5-1.5B, LogFloor reduces token cost by 56.2% on average. In 70M-to-12B transfer, three-round replay of a 70M scout path reaches every floor in all eight target runs, saving 30.9% by pair mean, 39.4% in pooled training tokens, and 37.6% under source-cost accounting. On MMLU-control, a frozen scout path succeeds across all eight 12B runs. Collapsing a path to its static marginal mixture or reversing its phase order removes most benefits, while bottleneck labels alone remain partially useful. These results identify phase-ordered bottleneck resolution as a transferable curriculum structure for monitored skill-targeted training.

Seungmin Choi, Jiwon Sung, Muhammad Umer +4

Stanford University · Seoul National University

LLM TrainingEfficient Language Model TrainingCurriculum LearningTransfer LearningData Mixture Optimization
AskPDF
Aug 14, 2026

CytoBERT: A Foundation Model for Cytometry Data

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke +7

University of Rostock, Rostock, Germany · Marburg University, Marburg, Germany · Hessian Center for Artificial Intelligence, Darmstadt, Germany

Representation LearningTransfer Learning
AskPDF
Aug 14, 2026

Attributing Preprocessing Invariance in Spectral Foundation Models

A spectral foundation model should remain useful when laboratories preprocess spectra differently. The standard test trains a classifier under one pipeline and evaluates under another, taking preserved accuracy as evidence of learned invariance. However, these models normalize each input before any learned parameter is applied. When normalization maps differently preprocessed spectra to the same vector, the encoder receives identical inputs and the measured invariance cannot be attributed to learning. We propose a normalization-only attribution control: compare the encoder against its normalization before interpreting transfer as learned invariance. On six Raman datasets the encoder does not measurably improve transfer over its normalization. A controlled experiment confirms invariance develops only when variation reaches the encoder past normalization. Across three systems, no encoder improves relative retention over its normalization. An audit of eighteen configurations across five modalities confirms the issue is widespread: the normalization-only control should be reported before crediting transfer to the encoder.

Dongjun Wei, Hongyi Wu

ESCP Business School, Paris · OpluxCare Tech Group Ltd. · The University of Hong Kong, Hong Kong

Transfer LearningRaman SpectroscopySpectral MethodsInvariant Representation Learning
AskPDF
Aug 14, 2026

From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics

Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian representation. However, Lagrangian trajectories are less commonly available than Eulerian fields, while most neural operators are trained and evaluated primarily in the Eulerian representation. This mismatch motivates a new learning problem: can a model trained solely on Eulerian observations generalize zero-shot from Eulerian field prediction to Lagrangian particle rollout, without Lagrangian supervision or task-specific adaptation? To address this problem, we propose the Transferable Latent Operator (TLO), which learns a unified flow representation shared by Eulerian field prediction and Lagrangian particle rollout. TLO decouples latent flow evolution from coordinate-dependent decoding: querying the evolving latent representation at fixed spatial coordinates yields Eulerian fields, whereas querying velocities at particle positions and recursively updating these positions enables Lagrangian rollout. Across five fluid-dynamics benchmarks, TLO consistently outperforms existing neural operators in both Eulerian field prediction and zero-shot Lagrangian rollout, with further gains from limited Lagrangian fine-tuning.

Meng Li, Chuqi Chen, Zhengqing Gao +4

Shanghai Artificial Intelligence Laboratory · The Hong Kong University of Science and Technology · University of Michigan +2

Neural OperatorsComputational Fluid DynamicsPhysics-Based SimulationTransfer LearningFlow Map Learning
AskPDF
Aug 13, 2026

Emergence of Transfer Learning towards Specific Identification of Alzheimer's Disease A Prospective Approach

Worldwide, millions of senior citizens are suffering from Alzheimer disease abbreviated as AD, a well- versed form of dementia. AD is featured by amnesia, intellectual disability, and difficulty with consciousness. DL and ML models are undoubtedly explored to identify AD related patterns on large dimensional neuroimaging data but they need global optimization and are suffering from overfitting issue that might yield dissatisfactory result in testing data set. DL overcomes the issue by convolution of input image with kernel but any sudden change in the MRI image or human manipulation, limited pre- processing of the images can mislead CNN in achieving highly accurate detection. Transfer Learning (TL) has proved itself in AD diagnosis by utilizing pre-trained models on large data sets to guide novice model in a new neuroimaging dataset. This review provides an inclusive glimpse of TL implication in classification, identification including the conversion of AD. Keeping in view, we have assessed the strengths and limitations of TL in improvising diagnostic accuracy even with limited data. The uniqueness of the present review is the incorporation of explainable AI in TL based AD diagnosis system. Finally, it can be claimed that the review will guide the new re-searchers in the area of TL induced neurodegenerative disease detection.

Soumik Podder, Chandramouli Haldar

Department of Basic Science and Humanities Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata Kolkata, India · Department of Computer Science and Engineering Guru Nanak Institute of Technology Kolkata, India

Alzheimer's Disease ClassificationTransfer LearningMedical Image Classification
AskPDF
Aug 12, 2026

ε\varepsilon-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discarding search experience after completion. We introduce ε\varepsilon-MemEvo, a framework for cross-task knowledge transfer in LLM program evolution. ε\varepsilon-MemEvo stores prior experience as task-agnostic tactic memories: compact natural-language summaries of successful algorithmic strategies rather than raw code, enabling transfer across tasks with different APIs and evaluators. To avoid negative transfer from semantically mismatched memories, ε\varepsilon-MemEvo uses an adaptive injection gate that decides whether retrieved memories should be injected, and at what intensity. We evaluate ε\varepsilon-MemEvo on 8 diverse optimization benchmarks spanning mathematical optimization and systems engineering, using a content-level Leave-One-Out protocol that excludes target-task memory entries. On the primary GPT-5 backbone, ε\varepsilon-MemEvo improves AUCC over AdaEvolve on all 8 tasks, with a mean relative gain of +8.7%, and improves early-stage convergence by +9.4% on average. Ablations show that naive memory injection can fail catastrophically, while adaptive gating remains safe across all five ablation tasks. The data-updated posterior is interpretable in observed states: it favors skip during improving search and shifts from skip to hint across early and late plateaus. These gains incur less than 1% computational overhead.

Aofan Liu, Shiyuan Song, Yiyan Qi

Evolutionary OptimizationLarge Language Model-Guided OptimizationLLM-Based Program SynthesisTransfer LearningMemory-Augmented Agents
AskPDF
Aug 12, 2026

XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer. We identify the entity grounding problem in cross-architecture communication: cross-attention bridges that transfer continuous representations across different LLM families suffer from rare-token compression collapse, where entity identity is lost in the continuous bottleneck (bridge-only F1 ~30%). We propose XBRIDGE, a decode-free communication protocol that addresses this through two mechanisms. Lexical Anchor Mapping (LAM) maps the sender's original context tokens to the receiver's vocabulary, providing discrete entity anchors. A Latent Enrichment Bridge (LEB) lets the receiver query the sender's hidden states for contextual enrichment. The entity anchors ground the bridge's contextual signals to specific entities through the receiver's own self-attention. Across three model families (Llama, Qwen, and Mistral), seven benchmarks, and both communication directions, XBRIDGE outperforms text-based communication on all seven tasks for each model pair while achieving 11x lower latency, and in a same-architecture setting it also exceeds a KV-sharing baseline on six of seven tasks. LEB requires only 264M trainable parameters (3.8% of the receiver), is trained on a small balanced sample set, and adds negligible inference overhead.

Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang +3

University of Illinois Chicago · Capital One AI Foundations · Hankuk University of Foreign Studies +1

LLM GroundingTransfer LearningMulti-Agent Communication
AskPDF
Aug 11, 2026

Market-Information-Aware Gated-LoRA of Foundation Models for Transferable Day-Ahead Electricity Price Forecasting

Electricity price forecasting is crucial for market participants but remains difficult because prices are volatile, market-specific, and closely tied to anticipated system conditions. Existing supervised methods depend largely on market-specific historical data, limiting their use in newly established or data-scarce markets. This paper proposes a market-information-aware adaptation framework that transfers the Chronos-2 time-series foundation model to day-ahead electricity price forecasting. It first constructs a multi-source market information (MSMI) interface aligning 7-day price context with pre-clearing supply--demand, reserve, maintenance, generator-capacity, and intertie variables, and then trains a source-domain gated low-rank adapter (LoRA), updating about 1%1\% of model parameters without target-market labels. The gate scales the frozen source adapter according to reserve-tightness and operating-state signals. A leave-one-market-out protocol is adopted for evaluating cross-market transferability. Experiments on four Chinese provincial day-ahead spot markets show that the proposed framework reduces the average MAE/RMSE by 6.24%/7.99%6.24\%/7.99\% relative to market-information-aware zero-shot Chronos-2 and by 3.05%/3.52%3.05\%/3.52\% relative to vanilla Source-LoRA. Experiments show that the gain is not reproduced by a learned global scalar or by random gate initialization, while the additional improvement over Source-LoRA is limited. These results suggest that market-structured inputs and state-dependent gated LoRA can provide a practical transfer path for data-scarce electricity markets.

Hang Fan, Wei Wei, Shengwei Mei

Electricity Price ForecastingTime Series ForecastingLow-Rank AdaptationTransfer LearningTime-Series Foundation Models
AskPDF
Aug 10, 2026

Black-Box Knowledge Transfer across Distinct Feature Sets

Pre-trained black-box predictive functions encode knowledge distilled from massive datasets and extensive computation. However, when the available input features differ from those the black box expects, direct use is infeasible. We introduce a method for transferring predictive knowledge from the black box to a new, heterogeneous input space. Our approach decomposes the target regression function into a transferable component, which the black box can inform, and a non-transferable component, which captures information unique to the new space. We propose a two-step neural network procedure, estimating the transferable component from abundant unlabeled feature pairs that bridge the two input spaces and the non-transferable component from limited labels. We derive prediction risk bounds that improve on those of a non-transfer alternative when the non-transferable component is small or smooth, and the procedure adapts to either case. Under additional conditions, the worst-case risk of our estimator is of strictly smaller polynomial order than the minimax risk of estimation from the labeled data alone. We extend the framework to multiple black boxes, each on its own input space, and show that aggregation can reduce prediction error relative to the best single black box. Simulated and real data demonstrate the practical value of the method.

Oh-Ran Kwon, Daeyoung Ham

Department of Statistics, The Ohio State University · Department of Statistics and Data Science, University of Texas at San Antonio

Transfer LearningKnowledge Distillation
AskPDF
Aug 10, 2026

VERDI:Verified Contradictions for Continual World-Model Optimization

Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research agents automate the optimization loop but treat successful strategies as directly reusable recipes, without principled safeguards for when transfer is appropriate. We argue instead that retrieval is not transfer: a strategy validated on one model is at best an optimization hypothesis for another, and becomes transferable knowledge only after target-side experimental valida- tion. Guided by this principle, we propose VERDI , a continual framework for evidence-licensed world model optimization. VERDI characterizes each world model through shared inference-time probes to construct an Optimization Fin- gerprint, retrieves relevant prior experience as ranked hypotheses, and validates every candidate under a frozen target-side verifier before admitting it as reusable evidence; contradictions among nearby fingerprints further trigger probe evolution, continually refining the diagnostic representation itself. Experiments on Ctrl-World, the Cosmos family, and RoboCoin show that VERDI reduces search cost by 68%, GPU cost by 69%, and negative transfer from 0.34 to 0.06, while predicting transfer outcomes with 83% sign accuracy.

Junyu Wu, Shiqin Nie, Youyi Kou +10

* Equal contribution

World Model LearningWorld ModelsTransfer LearningNegative Transfer
AskPDF
Aug 10, 2026

TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset

Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO . Qualitatively, it seems a transfer learning dataset should have both more classes and more examples per class than the fine tuning dataset; however, a quantitative method to choose the best transfer learning dataset does not currently exist. In this paper, we design TLDChoiceNet, a model to choose the best transfer learning dataset given a fine tuning dataset by predicting the test-set accuracy after fine-tuning. A simple version 1 achieves 0.154 MSE on the test dataset, while a version 2 leveraging an ImageNet pre-trained ResNet50 v2 embedding with per-class information attains a 5X lower MSE of 0.031. We further design two metrics that enable an unsupervised method of choosing an optimal transfer learning dataset: distribution distance (DD), which linearly regresses against fine-tune accuracy with an R2 of 0.89, and average class correlation (ACC), which improves the R2 to 0.97. Our results underscore that a dataset's low-level statistics can explain the transfer learning effect, and that using a pre-trained ImageNet can embed different classes further apart in latent feature space.

Jing Ning, James D. Braza

Department of Computer Science, Stanford University

Fine-TuningTransfer LearningCross-Dataset GeneralizationImage Classification
AskPDF