论文检索

General Machine Learning · Transfer, Multitask and Meta-learning

Shaocong Ma, Peiran Yu, Heng Huang

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have inherent limitations: full fine-tuning is computationally expensive, while PEFT often struggles to learn new knowledge and exhibits suboptimal performance. To overcome these issues, we propose a novel *hybrid fine-tuning* approach that jointly updates both LLMs and PEFT modules using a combination of zeroth-order and first-order optimization methods. To analyze our new algorithm, we develop a theoretical framework centered on the concept of *hybrid smoothness condition*, which accounts for the heterogeneous nature of the optimization landscape in joint LLM and PEFT training. We derive a rigorous convergence analysis for the convergence of reshuffling-type SGD algorithm under multiple learning rates and demonstrate its effectiveness through extensive empirical studies across various downstream tasks and model architectures. On the practical side, our results demonstrate consistent performance improvement, making the approach a viable solution for large-scale language model fine-tuning.

General Machine Learning · Transfer, Multitask and Meta-learning

Lukas Gruber, Markus Holzleitner, Sepp Hochreiter, Werner Zellinger

Density ratio estimation (DRE) is fundamental in machine learning and statistics, with applications in domain adaptation and two-sample testing. However, DRE methods are highly sensitive to hyperparameter selection, with suboptimal choices often resulting in poor convergence rates and empirical performance. To address this issue, we propose a novel model aggregation algorithm for DRE that trains multiple models with different hyperparameter settings and aggregates them. Our aggregation provably achieves minimax-optimal error convergence without requiring prior knowledge of the smoothness of the unknown density ratio. Our method surpasses cross-validation-based model selection and model averaging baselines for DRE on standard benchmarks for DRE and large-scale domain adaptation tasks, setting a new state of the art on image and text data.

General Machine Learning · Transfer, Multitask and Meta-learning

Tao Tao, Maissam Barkeshli

We study the ability of Transformer models to learn sequences generated by Permuted Congruential Generators (PCGs), a widely used family of pseudo-random number generators (PRNGs). PCGs introduce substantial additional difficulty over linear congruential generators (LCGs) by applying a series of bit-wise shifts, XORs, rotations and truncations to the hidden state. We show that Transformers can nevertheless successfully perform in-context prediction on unseen sequences from diverse PCG variants, in tasks that are beyond published classical attacks. In our experiments we scale moduli up to $2^{22}$ using up to $50$ million model parameters and datasets with up to $5$ billion tokens. Surprisingly, we find even when the output is truncated to a single bit, it can be reliably predicted by the model. When multiple distinct PRNGs are presented together during training, the model can jointly learn them, identifying structures from different permutations. We demonstrate a scaling law with modulus $m$: the number of in-context sequence elements required for near-perfect prediction grows as $\sqrt{m}$. For larger moduli, optimization enters extended stagnation phases; in our experiments, learning moduli $m \geq 2^{20}$ requires incorporating training data from smaller moduli, demonstrating a critical necessity for curriculum learning. Finally, we analyze embedding layers and uncover a novel clustering phenomenon: the top principal components spontaneously group the integers into bitwise rotationally-invariant clusters, revealing how representations can transfer from smaller to larger moduli.

General Machine Learning · Transfer, Multitask and Meta-learning

Yichi Zhang, Fangzheng Xie, Shu Yang, Chong Wu

In language tasks requiring extensive human-model interaction, the inference cost of large language models (LLMs) can be substantial. To reduce expenses while preserving the quality of the responses, an LLM router selects among candidate models to balance between the expected response quality and the inference cost. A central challenge in router training is the accuracy and accessibility of reliable supervision. Gold-standard data, obtained from domain experts or benchmark labels, provide accurate quality evaluations of LLM responses but are costly and difficult to scale. In contrast, preference-based data, collected via crowdsourcing or LLM-as-a-judge systems, are cheaper and more scalable, yet often biased in reflecting the true quality of responses. We cast the problem of LLM router training with combined Gold-standard and preference-based data into a causal inference framework by viewing the response evaluation mechanism as the treatment assignment. This perspective further reveals that the bias in preference-based data corresponds to the well-known causal estimand: the conditional average treatment effect (CATE). Based on this new perspective, we develop an integrative causal router training framework that corrects preference-data bias, addresses imbalances between two data sources, and improves routing robustness and efficiency. Numerical experiments demonstrate that our approach delivers more accurate routing and improves the trade-off between cost and quality. Illustrative code to reproduce our main experiment is available at https://github.com/yichistat/Meta-router.

General Machine Learning · Transfer, Multitask and Meta-learning

Jiangrong Shen, Liang Zhao, Qi Xu, Yuqi Yang, Liangjun Chen, Gang Pan, Badong Chen

The human brain exhibits remarkable efficiency in processing sequential information, a capability deeply rooted in the temporal selectivity and stochastic competition of neuronal activation. Current continual learning in spiking neural networks (SNNs) faces a critical challenge: balancing task-specific selectivity with adaptive resource allocation and enhancing the robustness with perturbations to mitigate catastrophic forgetting. Considering the intrinsic temporal dynamics of spiking neurons instead of traditional K-winner-take-all (K-WTA) based on firing rate, we explore how to leave networks robust to temporal perturbations in SNNs on lifelong learning tasks. In this paper, we propose Randomized Temporal K-winner-take-all (RTK-WTA) SNNs for lifelong learning, a biologically grounded approach that integrates trace-dependent neuronal activation with probabilistic top-k selection. By dynamically prioritizing neurons based on their spatiotemporal relevance, RTK-WTA SNNs emulate the brain’s ability to modulate neural resources in spatial and temporal dimensions while introducing controlled randomness to prevent overlapping task representations. The proposed RTK-WTA SNNs enhance inter-class margins and robustness through expanded feature space utilization theoretically. The experimental results show that RTK-WTA surpasses deterministic K-WTA by 3.07–5.0\% accuracy on splitMNIST and splitCIFAR100 with elastic weight consolidation. Controlled stochasticity balances temporal coherence and adaptability, offering a scalable framework for lifelong learning in neuromorphic systems.

General Machine Learning · Transfer, Multitask and Meta-learning

Wenhao Li, Yudong Xu, Elias Khalil, Scott Sanner

We study the neural program synthesis of $\textit{parameterized}$ function families through the lens of meta-learning with hypernetworks. Given a user intent $U$, a meta-learner $M_{\phi}$ produces a full weight set $\hat{\theta}=M_{\phi}(U)$ for a target neural network with fixed architecture $S$, and the instantiated network $m_{S,\hat{\theta}}(X)\to Y$ realizes the behavior intended for $U$. Classical hypernetworks typically $\textit{ignore the target network’s structure}$ and emit a flat list of weights; as a consequence, they fail to account for $\textit{neuron-permutation symmetry}$—many distinct parameterizations of $S$ implement the same function—so equivalent solutions are treated as different targets, fragmenting supervision and hurting out-of-distribution generalization. To address this, we propose $\textit{Meta-GNN}$, a hypernetwork that constructs a $\textit{neural graph}$ from the target architecture $S$ and applies $\textbf{structure-aware}$ message passing with parameter-tied encoders and decoders. This design reduces the search space during learning by collapsing equivalent classes of target networks, without loss of expressivity. Empirically, across modular arithmetic ($\textit{AddMod}$-$p$), array operations ($\textit{SumFirst}$-$n$), and inverse-rule tasks from 1D-ARC, $\textit{Meta-GNN}$ substantially improves learning and $\textbf{out-of-distribution generalization}$ compared to classic hypernetworks and direct $(U,X)\to Y$ baselines. Mechanistic analyses reveal $\textit{what is learned}$: on $\textit{AddMod}$-$p$ the synthesized Transformers recover the canonical clock representation and admit a compact closed-form map $U\mapsto\theta$. These results demonstrate that structure-aware Meta-GNNs enable reliable generalization to $\textit{unseen program parameterizations}$, providing a critical advance for the nascent field of neural program synthesis.

General Machine Learning · Transfer, Multitask and Meta-learning

Guodong DU, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi, Wanyu LIN, Ho-Kin Tang, Xiucheng Li, Fangming Liu, Wenya Wang 等

Cross-capability transfer represents a key challenge in large language model (LLM) research, particularly in multi-task integration, model compression, and knowledge fusion. Recent works such as FuseLLM and FuseChat have shown the potential of transferring multiple model capabilities to lightweight models, thereby enhancing adaptability and efficiency. This motivates our investigation into more efficient methods for cross-capability transfer. However, existing merging approaches primarily focus on small, homogeneous models, limiting their applicability. For large, heterogeneous models, knowledge distillation with full-parameter fine-tuning often overlooks the student model’s inherent capability and risks catastrophic forgetting, while PEFT methods struggle to effectively absorb knowledge from source LLMs. To address these issues, we introduce **GraftLLM**, a novel grafting-based method that stores source model capabilities in a target model + SkillPack format. This approach preserves general capabilities, reduces parameter conflicts, and supports forget-free continual learning and model fusion. We employ a module-aware adaptive compression strategy for parameter updates, ensuring efficient storage while **preserving task-specific knowledge**. The resulting SkillPack serves as a compact and transferable knowledge carrier, ideal for **heterogeneous LLM fusion**. Experiments across various scenarios demonstrate that GraftLLM outperforms existing techniques in knowledge transfer, knowledge fusion, and forget-free learning, providing a scalable and efficient solution for cross-capability transfer.

General Machine Learning · Transfer, Multitask and Meta-learning

Angelo Porrello, Pietro Buzzega, Felix Dangel, Thomas Sommariva, Riccardo Salami, Lorenzo Bonicelli, Simone Calderara

Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors; however, existing approaches typically require external task data, conflicting with modularity and data availability constraints (e.g., privacy requirements). We propose a dataless approach by framing regularization against representation drift as a curvature matrix approximation problem. This allows us to leverage well-established techniques; in particular, we adopt Kronecker-Factored Approximate Curvature and obtain a practical regularizer that achieves state-of-the-art results in task addition and negation. Our method has constant complexity in the number of tasks and promotes robustness to task vector rescaling, eliminating the need for held-out tuning.

General Machine Learning · Transfer, Multitask and Meta-learning

Dengming Zhang, Xiaowen Ma, Zhenliang Ni, Zhenkai Wu, Han Shu, Xin Jiang, Xinghao Chen

Model merging, which combines multiple domain-specialized experts into a single model, offers a practical path to endow Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) with broad capabilities without the cost of joint training or serving many models. However, training-free methods rely on hand-tuned coefficients, whereas training-based methods primarily align parameters rather than downstream task behavior and typically treat all layers uniformly, ignoring inter-layer heterogeneity. We introduce Expert Merging, a training-light method that learns a small set of layer-wise coefficients using only unlabeled calibration data. The coefficients are optimized to explicitly align the merged model’s hidden states and logits with those of the corresponding experts, with a coefficient regularizer for stability and task-weighted losses for controllable trade-offs. To capture inter-layer variation, Expert Merging++ augments this design with importance-guided chunking: a normalized layer-importance metric, derived from learned coefficients, task-vector magnitudes, and parameter counts, allocates more chunk-wise coefficients to high-importance layers while keeping low-importance layers lightweight. The result is a label-free, parameter-efficient, and scalable approach to multi-expert model merging across LLMs and MLLMs. Across MLLM backbones (InternVL and Qwen2-VL) and the LLM backbone (Mistral), our method surpasses strong training-free and training-based merging baselines, with Expert Merging++ delivering further gains and, in some cases, even exceeding supervised Mixture Training. Our code is available at https://github.com/Littleor/ExpertMerging.

General Machine Learning · Transfer, Multitask and Meta-learning

Pei Yang, Yuhang Zhuang, Qi Tan

The classical optimal transport such as Kantorovich's optimal transport and partial optimal transport could be too restrictive in applications due to the full-mass or fixed-mass preservation constraints. To remedy this limitation, we propose elastic optimal transport (ELOT) which is distinctive from the classical optimal transport in its ability of adaptive-mass preserving. It aims to answer the problem of how to transport the probability mass adaptively between probability distributions, which is a fundamental topic in various areas of artificial intelligence. The strength of elastic optimal transport is its capability to transport adaptive-mass in the light of the geometry structure of the problem itself. As an application example in machine learning, we apply elastic optimal transport to both unsupervised domain adaptation and partial domain adaptation tasks. It adaptively transports masses from source domain to target domain by taking domain shift into consideration and respecting the ubiquity of noises or outliers in the data, in order to improve the generalization performance. The experiment results on the benchmarks show that ELOT significantly outperforms the state-of-the-art methods. As a powerful distribution matching tool, elastic optimal transport might be of interests to the broad areas such as artificial intelligence, healthcare, physics, operations research, urban science, etc. The source code is available in the supplementary material.

General Machine Learning · Transfer, Multitask and Meta-learning

Barry Wang, Avi Schwarzschild, Alexander Robey, Ali Payani, Charles Fleming, Mingjie Sun, Daphne Ippolito

Retrofitting large language models (LLMs) with new behaviors typically requires full finetuning or distillation—costly steps that must be repeated for every architecture. In this work, we introduce ⌘V (Command-V), a backpropagation-free behavior transfer method that copies an existing residual representation adapter from a donor model and pastes its effect into an architecturally different recipient model. ⌘V profiles layer activations on a small prompt set, derives linear converters between corresponding layers, and applies the donor intervention in the recipient’s activation space. This process does not require access to the original training data and needs minimal compute. In three case studies—safety-refusal enhancement, jailbreak facilitation, and automatic chain-of-thought reasoning—⌘V matches the performance of direct finetuning while using orders of magnitude less resources.

General Machine Learning · Transfer, Multitask and Meta-learning

Dongjun Kim, Seohyeon Cha, Huancheng Chen, Chaining Wang, Haris Vikalo

Real-world deployment of machine learning models requires the ability to continually learn from non-stationary data while preserving prior knowledge and user privacy. Therefore, storing knowledge acquired from past data in a resource- and privacy-friendly manner is a crucial consideration in determining their viability. We introduce Quantized Gradient Projection Memory (QGPM), a systematic framework for continual learning that compresses and preserves the previous gradient subspace. QGPM integrates three key components: (i) distribution-aware, basis-wise quantization to minimize storage overhead, (ii) a Quantization Error-Aware (QEA) gradient projection that selectively relaxes orthogonality to mitigate gradient drift caused by accumulated quantization noise, and (iii) an on-the-fly sparse sketching strategy that improves runtime memory and computational efficiency. Experiments across multiple benchmarks demonstrate that QGPM achieves state-of-the-art performance under fixed memory budgets, highlighting its effectiveness in scalable, privacy-preserving continual learning.

General Machine Learning · Transfer, Multitask and Meta-learning

Ruihan Jin, Pengpeng Shao, Zhengqi Wen, Jinyang Wu, Mingkuan Feng, Shuo Yang, Chu Yuan Zhang, Jianhua Tao

Knowledge distillation has emerged as a pivotal technique for transferring knowledge from stronger large language models (LLMs) to smaller, more efficient models. However, traditional distillation approaches face challenges related to knowledge conflicts and high resource demands, particularly when leveraging multiple teacher models. In this paper, we introduce the concept of **Knowledge Purification**, which consolidates the rationales from multiple teacher LLMs into a single rationale, thereby mitigating conflicts and enhancing efficiency. To investigate the effectiveness of knowledge purification, we further propose five purification methods from various perspectives. Our experiments demonstrate that these methods not only improve the performance of the distilled model but also effectively alleviate knowledge conflicts. Moreover, router-based methods exhibit robust generalization capabilities, underscoring the potential of innovative purification techniques in optimizing multi-teacher distillation and facilitating the practical deployment of powerful yet lightweight models.

General Machine Learning · Transfer, Multitask and Meta-learning

Kunal Pratap Singh, Ali Garjani, Rishubh Singh, Muhammad Uzair Khattak, Jason Toskov, Efe Tarhan, Andrei Atanov, Oğuzhan Kar, Amir Zamir

The common approach for developing a vision model is generalism, which involves training on a large diverse dataset to cover the varied deployment environments and leads to a model that is expected to solve the problem everywhere. However, many practical applications need to operate in a specific test space, e.g., a robot deployed in a single house, and do not necessarily need to generalize to novel environments. In this work, we explore whether we can use rich multimodal data only from the test environment to pre-train a representation in a self-supervised way, without access to any external data. We find that this approach can match and, in most cases, outperform generalists pre-trained on large-scale Internet datasets, including popular off-the-shelf models, CLIP and DINOv2. We study the effectiveness of this approach by evaluating the models on various datasets and downstream tasks, such as semantic segmentation, captioning, and object detection, as well as a set of ablations and analyses to extract insights. This approach raises intriguing points on substituting data with (multi)modality, enabling an alternative scenario where the need for external Internet-scale datasets for pre-training models is reduced. It also shows that merely benefiting from test-space data was insufficient for achieving competitive results, and multimodality was essential for that purpose.

General Machine Learning · Transfer, Multitask and Meta-learning

Zixuan Duan, Fengyuan Lu, Xunzhi Xiang, Wenbin Li, Yang Gao, Qi Fan

Recent advances in Open Vocabulary Object Detection (OVOD) have shown strong performance on standard benchmarks, but performance drops sharply under out-of-distribution (OOD) shifts. Continual learning offers a potential remedy by sequentially integrating new tasks, yet existing methods often struggle to balance retaining the pre-trained model capabilities with adapting to new tasks, and usually require retraining under specific task orders. To address these limitations, we observe that model editing naturally lends itself to this setting, as it enables efficient knowledge injection while retaining prior capabilities. Building on this insight, we introduce $\textbf{A}$utomatically $\textbf{B}$alanced $\textbf{M}$odel $\textbf{E}$diting ($\textbf{ABME}$), which injects new task knowledge into the powerful OVOD models while preserving the model’s original abilities. We first stores compact key–value representations with storage cost independent of task volume. Then we leverage the stored KV matrices to automatically balance the new and old knowledge for varying learning scenarios, supporting order-agnostic task insertion or removal without additional retraining. Experiments show that ABME consistently achieves a better trade-off between maintaining pre-trained performance and adapting to diverse OOD tasks compared to existing continual learning approaches for open-vocabulary object detection, and generalizes seamlessly across different models and task scales.

General Machine Learning · Transfer, Multitask and Meta-learning

Van Cuong Pham, Anh Hoang, Cuong Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do

Post-training quantization (PTQ) is an attractive approach for compressing diffusion models to speed up the sampling process and reduce memory footprint. Most existing PTQ methods uniformly sample data from various time steps in denoising process to construct a calibration set for quantization and consider calibration samples equally important during the quantization process. However, treating all calibration samples equally may not be optimal. One notable property in the denoising process of diffusion models is that low-frequency features are primarily recovered in early stages, while high-frequency features are recovered in later stages of the denoising process. However, none of the previous works on quantization for diffusion models consider this property to enhance the effectiveness of quantized models. In this paper, we propose a novel meta-learning approach for PTQ of diffusion models that jointly optimizes the contributions of calibration samples and the weighting of frequency components at each time step for quantizing noise estimation networks. Specifically, our approach automatically learns to assign optimal weights to calibration samples while selectively focusing on mimicking specific frequency components of data generated by the full-precision noise estimation network at each denoising time step. Extensive experiments on CIFAR-10, LSUN-Bedrooms, FFHQ, and ImageNet datasets demonstrate that our approach consistently outperforms the compared PTQ methods for diffusion models.

General Machine Learning · Transfer, Multitask and Meta-learning

Nilushika Udayangani Hewa Dehigahawattage, Nandakishor Desai, Marimuthu Palaniswami

While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial prefixes. The absence of class-discriminative patterns in partial data can significantly hinder a classifier’s ability to generalize. This work uses knowledge distillation (KD) to equip partial time series classifiers with the generalization ability of their full-sequence counterparts. In KD, high-capacity teacher transfers supervision to aid student learning on the target task. Matching with teacher features has shown promise in closing the generalization gap due to limited parameter capacity. However, when the generalization gap arises from training-data differences (full versus partial), the teacher’s full-context features can be an overwhelming target signal for the student’s short-context features. To provide progressive, diverse, and collective teacher supervision, we propose Generative Diffusion Prior Distillation (GDPD), a novel KD framework that treats short-context student features as degraded observations of the target full-context features. Inspired by the iterative restoration capability of diffusion models, we learn a diffusion-based generative prior over teacher features. Leveraging this prior, we posterior-sample target teacher representations that could best explain the missing long-range information in the student features and optimize the student features to be minimally degraded relative to these targets. GDPD provides each student feature with a distribution of task-relevant long-context knowledge, which benefits learning on the partial classification task. Extensive experiments across earliness settings, datasets, and architectures demonstrate GDPD’s effectiveness for full-to-partial distillation.

General Machine Learning · Transfer, Multitask and Meta-learning

Bangguo Ye, Yuanwei Zhang, Xiaoqun Zhang

Fine-tuning large pre-trained models under resource constraints remains challenging due to the massive number of parameters involved. Existing parameter-efficient tuning methods, such as low-rank adaptation (LoRA) and its variants, rely heavily on matrix factorization and often struggle in extremely low-parameter regimes. In this work, we propose TRAC, a novel fine-tuning framework that leverages Tensor-Train decomposition with Across-layer Compression. Specifically, TRAC represents each adaptation module as a compact sequence of tensor-train cores and allows certain cores to be frozen or shared across layers, thereby exploiting the inherent similarity and redundancy among layer weight matrices. To retain layer-specific flexibility, lightweight controllers are introduced, enabling shared tensor cores to adaptively modulate representations. We evaluate TRAC on diverse architectures, including Qwen, LLaMA, GPT, BERT, and ViT, across benchmarks covering text classification, text generation, and image classification. Experimental results demonstrate that TRAC achieves performance comparable to or better than LoRA and its variants, while substantially reducing trainable parameters and storage requirements.

General Machine Learning · Transfer, Multitask and Meta-learning

Matthew Macfarlane, Clem Bonnet, Herke van Hoof, Levi Lelis

A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency, yet their scalability is constrained by formalisms such as domain-specific languages (DSLs), which are labor-intensive to create and may not transfer to new domains. In contrast, neural networks flexibly learn from data but fail to generalise systematically. We bridge this divide with the Neural Language Interpreter (NLI), an architecture that learns its own discrete, symbolic-like programming language end-to-end. NLI autonomously discovers a vocabulary of subsymbolic primitive operations and uses a novel differentiable neural executor to interpret variable-length sequences of these primitives. This allows NLI to represent programs that are not bound to a constant number of computation steps, enabling it to solve more complex problems than those seen during training. To make these discrete, compositional program structures amenable to gradient-based optimisation, we employ the Gumbel-Softmax relaxation, enabling the entire model to be trained end-to-end. Crucially, this same differentiability enables powerful test-time adaptation. At inference, NLI's program inductor provides an initial program guess. This guess is then refined via gradient descent through the neural executor, enabling efficient search for the neural program that best explains the given data. We demonstrate that NLI outperforms in-context learning, test-time training, and continuous latent program networks (LPNs) on tasks that require combinatorial generalisation and rapid adaptation to unseen tasks. Our results establish a new path toward models that combine the compositionality of discrete languages with the gradient-based search and end-to-end learning of neural networks.

General Machine Learning · Transfer, Multitask and Meta-learning

Zijun Wu, Yongchang Hao, Lili Mou

Large language models are typically controlled via prompts, which must be repeatedly re-processed for every new query and are difficult to reuse modularly. We introduce TokMem, a procedural memory framework that compiles each reusable task procedure into a single trainable memory token. Each token serves as both a procedure index and a generation control signal that steers generation, enabling targeted behaviors with constant-size overhead. TokMem keeps the backbone LLM frozen and stores procedural knowledge entirely in these dedicated units, so new procedures can be added continually without interfering with existing ones. We evaluate TokMem on two settings: atomic recall over 1,000 Super-Natural Instructions tasks and compositional recall on multi-step function-calling. Our results show that TokMem consistently outperforms retrieval-augmented prompting while avoiding repeated context overhead. Moreover, it matches or exceeds parameter-efficient fine-tuning with substantially fewer trainable parameters.