论文检索

General Machine Learning · Unsupervised and Semi-supervised Learning

Zhi Zhou, Ming Yang, Shi-Yu Tian, Kun-Yang Yu, Lan-Zhe Guo, Yu-Feng Li

Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despite its empirical success, the learnability of TTA under distributional non-stationarity remains unexplored. A key challenge is lacking of a principled theoretical framework that simultaneously aligns with the TTA objective and captures both continuously evolving distribution shifts and intrinsic information constraints. To address this gap, we propose the first theoretical framework for characterizing the learnability of TTA, introducing the notions of $(\epsilon,\delta)$-Recovery Complexity and $(\epsilon,\rho)$-TTA Learnability. Recovery complexity quantifies the minimal time required for a TTA algorithm to recover to a target excess risk following a distribution shift, and is further generalized to define $(\epsilon,\rho)$-TTA Learnability, which measures the long-term reliability of TTA algorithms over non-stationary data streams. Within this framework, we introduce a novel temporally dependent discrete surrogate method that models complex non-stationary test streams, enabling a unified and tractable analysis of both gradual and abrupt distribution shifts. We derive order-wise matching lower and upper bounds on recovery complexity through information-theoretic and optimization-based analysis. Our results uncover fundamental limits of TTA, highlight the intrinsic adaptivity-information trade-off of TTA algorithms, and provide the first unified learnability guarantees that go beyond regret-based perspectives.

Computer Vision · Everything Else

Bao Li, Xiaomei Zhang, Miao Xu, Zhaoxin Fan, Xiangyu Zhu, Zhen Lei

Generating 3D human poses from multimodal inputs such as text or images requires models to capture both rich semantic and spatial correspondences. While pose-specific multimodal large language models (MLLMs) have shown promise, their supervised fine-tuning (SFT) paradigm struggles to resolve the task's inherent ambiguity. Its reliance on objectives like SMPL parameter regression creates a critical alignment gap, compromising the model's ability to achieve the required semantic and spatial fidelity. To close the gap, we propose Pose-RFT, a framework that shifts the learning paradigm from supervised imitation to reward-driven reinforcement fine-tuning (RFT). We address the core technical challenge of this task: a hybrid action space requiring joint optimization of discrete language and continuous pose outputs. To this end, we introduce HyGRPO, a hybrid reinforcement learning algorithm that enables stable optimization by performing group-wise reward normalization over sampled responses. Pose-RFT incorporates task-specific reward functions to guide optimization towards spatial alignment in image-to-pose generation and semantic consistency in text-to-pose generation. Extensive experiments on multiple pose generation benchmarks demonstrate that Pose-RFT significantly improves performance over existing pose-specific MLLMs, validating the effectiveness of our approach in closing the alignment gap for 3D pose generation.

Optimization · Everything Else

Jiwan Chung, SAEJIN KIM, Yongrae Jo, Jaewoo Park, Dongjun Min, Youngjae Yu

Large language models (LLMs) operate as autoregressive predictors over discrete token vocabularies, a formulation that has enabled their adaptation far beyond natural language to vision, robotics, and multimodal reasoning. However, training against one-hot targets disregards metric relationships between tokens and limits effectiveness on tasks where distance is meaningful, such as numerical values, spatial coordinates, or quantized embeddings. We introduce DIST2Loss, a distance-aware objective for discrete autoregressive models that replaces one-hot targets with reward-weighted distributions derived from predefined token distances. DIST2Loss can be interpreted as the closed-form solution to entropy-regularized policy optimization with known per-token rewards, retaining the core mechanism of reinforcement learning while avoiding sampling, rollouts, and instability. Our experiments show that DIST2Loss improves data efficiency and downstream performance across diverse domains. It yields tighter bounding boxes in visual grounding, accelerates robotic manipulation by improving action learning, enhances reward modeling for LLM alignment, and strengthens vector-quantized image generation. These results demonstrate that distance-aware supervision offers a simple and general alternative to one-hot supervision for discrete autoregressive models.

Theory · Domain Adaptation and Transfer Learning

Wei Chen, Xingyu Guo, Shuang Li, Yan Zhong, Zhao Zhang, Fuzhen Zhuang, Hongrui Liu, Libang Zhang, Guo Ye, HUIMEI HE

Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by discretizing the adaptation process, typically through the construction of intermediate graphs or stepwise alignment procedures. However, such discrete strategies often fail in real-world scenarios, where graph structures evolve continuously and nonlinearly, making it difficult for fixed-step alignment to approximate the actual transformation process. To address these limitations, we propose \textbf{DiffGDA}, a \textbf{Diff}usion-based \textbf{GDA} method that models the domain adaptation process as a continuous-time generative process. We formulate the evolution from source to target graphs using stochastic differential equations (SDEs), enabling the joint modeling of structural and semantic transitions. To guide this evolution, a domain-aware network is introduced to steer the generative process toward the target domain, encouraging the diffusion trajectory to follow an optimal adaptation path. We theoretically show that the diffusion process converges to the optimal solution bridging the source and target domains in the latent space. Extensive experiments on 14 graph transfer tasks across 8 real-world datasets demonstrate DiffGDA consistently outperforms state-of-the-art baselines.

Ding Qi, Jian Li, Shuguang Dou, Zifan Song, Junyao Gao, Yabiao Wang, Chengjie Wang, Cai Zhao

Multimodal Dataset Distillation (MDD) has emerged as a vital paradigm for enabling efficient training of vision-language models (VLMs) in the era of multimodal data proliferation. Unlike traditional dataset distillation methods that focus on single-modal tasks, MDD presents distinct challenges: (i) the effective distillation of heterogeneous multimodal knowledge, complicated by feature space misalignment and asynchronous optimization dynamics; and (ii) the lack of discrete class guidance, which hinders the distribution coverage and representativeness of synthetic data due to the vastness and continuity of the semantic space. To address these challenges, this paper proposes an Asynchronous Matching with Dynamic sampling (AMD) framework. AMD enables asynchronous trajectory matching by decoupling the selection of starting points for image and text trajectories. Additionally, a Semantics-Aware Prototype Mining module is introduced, which replaces random initialization by leveraging feature-space clustering to identify representative prototypes, enhancing the coverage and representativeness of the distilled samples. Extensive experiments demonstrate that AMD achieves superior distillation performance on Flickr30k and COCO (e.g., IR@1, IR@5, and IR@10 \textbf{gains of 4.5\%, 9.6\%, and 10.9\%}, respectively, on Flickr30k 200 pairs.) with negligible computational overhead.

Theory · Probabilistic Methods

Zijing Ou, Chinmay Pani, Yingzhen Li

Discrete diffusion models have become highly effective across various domains. However, real-world applications often require the generative process to adhere to certain constraints. To this end, we propose a Sequential Monte Carlo (SMC) framework that enables scalable inference-time control of discrete diffusion models through principled importance weighting and optimal proposal construction. Specifically, our approach derives tractable importance weights for a range of intermediate targets and characterises the optimal proposal, for which we develop two practical approximations: a first-order gradient-based approximation and an amortised proposal trained to minimise the log-variance of the importance weights. Empirical results across synthetic tasks, language modelling, biology design, and text-to-image generation demonstrate that our framework enhances controllability and sample quality, highlighting the effectiveness of SMC as a versatile recipe for scaling discrete diffusion models at inference time.

Qian Li, Yuxiao Hu, Juncheng Liu, Yuntian Chen

Symbolic Regression (SR) tries to reveal the hidden equations behind observed data. However, most methods search within a discrete equation space, where the structural modifications of equations rarely align with their numerical behavior, leaving fitting error feedback too noisy to guide exploration. To address this challenge, we propose GenSR, a generative latent space–based SR framework following the "map construction $\rightarrow$ coarse localization $\rightarrow$ fine search" paradigm. Specifically, GenSR first pretrains a dual-branch Conditional Variational Autoencoder (CVAE) to reparameterize symbolic equations into a generative latent space with symbolic continuity and local numerical smoothness. This space can be regarded as a well-structured "map" of the equation space, providing directional signals for search. At inference, the CVAE coarsely localizes the input data to promising regions in the latent space. Then, a modified CMA-ES refines the candidate region, leveraging smooth latent gradients. From a Bayesian perspective, GenSR reframes SR task as maximizing the conditional distribution $p({\rm Equ.}|{\rm Num.})$, with CVAE training achieving this objective through the Evidence Lower Bound (ELBO). This new perspective provides a theoretical guarantee for the effectiveness of GenSR. Extensive experiments show that GenSR jointly optimizes predictive accuracy, expression simplicity, and computational efficiency, while remaining robust under noise.

Computer Vision · Vision Models & Multimodal

Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye

Optimizing discrete diffusion model (DDM) with rewards remains a challenge—the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce **MaskGRPO**, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify the theoretical foundation for DDMs, which facilitates building an importance estimator that captures valuable token fluctuation for gradient updates. We then delicately tailored the rollout method for visual sequences, which yields diverse completions and reliable optimization gradients. Across math reasoning, coding, and visual generation benchmarks, MaskGRPO brings more stable and efficient updates, **doubling** reinforcement learning gains while speeding up training by up to **30%**. This study establishes MaskGRPO as a systematic policy optimization approach and the first practical way for discretized visual diffusion. The code is available at https://github.com/martian422/MaskGRPO.

Applications · Neuroscience, Cognitive Science

Zijie Xu, Xinyu Shi, Yiting Dong, Zihan Huang, Zhaofei Yu

Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However, the discrete and non-differentiable nature of spikes leads to unstable gradient propagation in directly trained SNNs, making Batch Normalization (BN) an important component for stabilizing training. In online Reinforcement Learning (RL), imprecise BN statistics hinder exploitation, resulting in slower convergence and suboptimal policies. While Artificial Neural Networks (ANNs) can often omit BN, SNNs critically depend on it, limiting the adoption of SNNs for energy-efficient control on resource-constrained devices. To overcome this, we propose Confidence-adaptive and Re-calibration Batch Normalization (CaRe-BN), which introduces (i) a confidence-guided adaptive update strategy for BN statistics and (ii) a re-calibration mechanism to align distributions. By providing more accurate normalization, CaRe-BN stabilizes SNN optimization without disrupting the RL training process. Importantly, CaRe-BN does not alter inference, thus preserving the energy efficiency of SNNs in deployment. Extensive experiments on both discrete and continuous control benchmarks demonstrate that CaRe-BN improves SNN performance by up to $22.6$% across different spiking neuron models and RL algorithms. Remarkably, SNNs equipped with CaRe-BN even surpass their ANN counterparts by $5.9$%. These results highlight a new direction for BN techniques tailored to RL, paving the way for neuromorphic agents that are both efficient and high-performing. Code is available at https://github.com/xuzijie32/CaRe-BN.

Computer Vision · Image and Video Generation

Denis Zavadski, Nikita Tatsch, Carsten Rother

Product quantisation (PQ) is a classical method for scalable vector encoding, yet it has seen limited usage for latent representations in high-fidelity image generation. In this work, we introduce \textit{PQGAN}, a quantised image autoencoder that integrates PQ into the well-known vector quantisation (VQ) framework of VQGAN and adapts it to the regime of large-scale latent generative models. PQGAN achieves a noticeable improvement over state-of-the-art methods in terms of reconstruction performance, including both quantisation methods and their continuous counterparts. We achieve a PSNR score of 37dB, where prior work achieves 27dB, and are able to reduce the FID, LPIPS, and CMMD score by up to 96\%. Our key to success is a thorough analysis of the interaction between codebook size, embedding dimensionality, and subspace factorisation, with vector and scalar quantisation as special cases. We obtain novel findings, such that the performance of VQ and PQ behaves in opposite ways when scaling the embedding dimension. Furthermore, our analysis shows performance trends for PQ that help guide optimal hyperparameter selection. Finally, we demonstrate that PQGAN can be seamlessly integrated into pre-trained diffusion models. This enables either a significantly faster and more compute-efficient generation, or a doubling of the output resolution at no additional cost, positioning PQ as a strong extension for discrete latent representations in image synthesis.

Deep Learning · Graph Neural Networks

Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Jimin Cao, Aleksandar Bojchevski

Even a slight perturbation in the graph structure can cause a significant drop in the accuracy of graph neural networks (GNNs). Most existing attacks leverage gradient information to perturb edges. This relaxes the attack's optimization problem from a discrete to a continuous space, resulting in solutions far from optimal. It also prevents the adaptability of the attack to non-differentiable objectives. Instead, we introduce a few simple, yet effective, enhancements of an evolutionary-based algorithm to solve the discrete optimization problem directly. Our Evolutionary Attack EvA works with any black-box model and objective, eliminating the need for a differentiable proxy loss. This allows us to design two novel attacks that reduce the effectiveness of robustness certificates and break conformal sets. EvA uses sparse representations to significantly reduce memory requirements and scale to larger graphs. We also introduce a divide and conquer strategy that improves both EvA and existing gradient-based attacks. Among our experiments, EvA shows $\sim$11\% additional drop in accuracy on average compared to the best previous attack, revealing significant untapped potential in designing attacks.

Computer Vision · Everything Else

Bingfan Zhu, Biao Jiang, Sunyi Wang, SHIXIANG TANG, Tao Chen, Linjie Luo, Youyi Zheng, Xin Chen

With the rapid progress of large language models (LLMs), multimodal frameworks that unify understanding and generation have become promising, yet they face increasing complexity as the number of modalities and tasks grows. We observe that motion quantization introduces approximation errors that cap motion quality, and that unifying discrete text and continuous motion within a single-stream backbone amplifies cross-modal interference. Motivated by recent multi-branch Transformer designs that separate signals from different modalities, we propose MotionGPT3, a bimodal motion–language model for both understanding and generation. MotionGPT3 encodes raw motion into a continuous latent space using a variational autoencoder (VAE), thereby avoiding quantization-induced artifacts, while leveraging the semantic prior of pretrained language models. A dual-stream Transformer with shared attention preserves modality-specific routes while enabling controlled, bidirectional information flow, which reduces interference, stabilizing optimization, and empirically accelerates convergence without degrading fidelity. For multimodal joint training, a generate-then-align three-stage schedule further improves stability and limits cross-task interference. Experiments show that MotionGPT3 achieves 2× faster convergence in training loss and up to 4× faster convergence in validation, while maintaining state-of-the-art performance on standard motion understanding and motion generation benchmarks.

Computer Vision · Image and Video Generation

Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li, Jiaojiao Fan, Zekun Hao, Fitsum Reda, Yogesh Balaji, Huayu Chen, Sheng Liu 等

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces \alg, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving $20\%$ tokens without influence on performance, and achieving $2.3\times$ compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, \alg enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research.

Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li, Jiaojiao Fan, Zekun Hao, Fitsum Reda, Yogesh Balaji, Huayu Chen, Sheng Liu 等

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces \alg, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving $20\%$ tokens without influence on performance, and achieving $2.3\times$ compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, \alg enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research.

Reinforcement Learning · Deep RL

Haoran Xu, Kaiwen Hu, Somayeh Sojoudi, Amy Zhang

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by erroneous out-of-distribution extrapolation. Existing methods either rely on reparameterized policy gradient, which are difficult to scale to large generative models, or on reject sampling, which can be overly conservative when attempting to move beyond the behavior support. In this paper, we propose Value Gradient Flow (VGF), a scalable new paradigm for behavior-regularized RL. VGF casts behavior-regularized RL as an optimal transport problem that maps the reference distribution to the value-induced optimal policy distribution. We solve this transport problem via discrete gradient flow, where value gradients guide particles initialized from the reference distribution. Our analysis shows that VGF imposes regularization implicitly by controlling the transport budget. VGF eliminates explicit policy parameterization while remaining expressive and flexible, this enables adaptive test-time scaling by adjusting the transport budget. Extensive experiments demonstrate that VGF significantly outperforms prior methods, achieving state-of-the-art results on offline RL benchmarks (D4RL, OGBench) and LLM RL tasks.

General Machine Learning · Representation Learning

Haolin Pan, Dong Jinyuan, Hongbin Zhang, Hongyu Lin, Mingjie Xing, Yanjun WU

Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization. Prevailing paradigms, however, present a dilemma. Static representations, derived from source code or intermediate representation (IR), are efficient and deterministic but offer limited insight into how a program will behave or evolve under complex code transformations. Conversely, dynamic representations, which rely on runtime profiling, provide profound insights into performance bottlenecks but are often impractical for large-scale tasks due to prohibitive overhead and inherent non-determinism. This paper transcends this trade-off by proposing a novel quasi-dynamic framework for program representation. The core insight is to model a program's optimization sensitivity. We introduce the Program Behavior Spectrum, a new representation generated by probing a program's IR with a diverse set of optimization sequences and quantifying the resulting changes in its static features. To effectively encode this high-dimensional, continuous spectrum, we pioneer a compositional learning approach. Product Quantization is employed to discretize the continuous reaction vectors into structured, compositional sub-words. Subsequently, a multi-task Transformer model, termed PQ-BERT, is pre-trained to learn the deep contextual grammar of these behavioral codes. Comprehensive experiments on two representative compiler optimization tasks---Best Pass Prediction and -Oz Benefit Prediction---demonstrate that our method outperforms strong static baselines. Our code is publicly available at https://github.com/Panhaolin2001/PREP/.

Optimization · Sampling and Optimization

Konstantinos Emmanouilidis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Rene Vidal

From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min–max optimization or, more generally, as variational inequality problems (VIPs). Owing to their simplicity and scalability, stochastic gradient methods with constant step size are widely used, despite the fact that they converge only up to a constant term. Among the many heuristics adopted in practice, two classical techniques have recently attracted attention to mitigate this issue: *Random Reshuffling* of data and *Richardson–Romberg extrapolation* across iterates. Random Reshuffling sharpens the mean-squared error (MSE) of the estimated solution, while Richardson-Romberg extrapolation acts orthogonally, providing a second order reduction in its bias. In this work, we show that their composition is strictly better than both, not only maintaining the enhanced MSE guarantees but also yielding an even greater cubic refinement in the bias. To the best of our knowledge, our work provides the first theoretical guarantees for such a synergy in structured non-monotone VIPs. Our analysis proceeds in two steps: (i) we smooth the discrete noise induced by reshuffling and leverage tools from continuous-state Markov chain theory to establish a novel law of large numbers and a central limit theorem for its iterates; and (ii) we employ spectral tensor techniques to prove that extrapolation debiases and sharpens the asymptotic behavior even under the biased gradient oracle induced by reshuffling. Finally, extensive experiments validate our theory, consistently demonstrating substantial speedups in practice.

Optimization · Non-Convex

Jiawei Xu, Yi Zheng, Chenghe Sun, Taiyu Zhou, Zuqi Zhang, Jie Li, Lirong Zheng, Zhuo Zou

Efficient deployment of deep neural networks increasingly relies on Post-Training Quantization (PTQ). Logarithmic PTQ, in particular, promises multiplier-free hardware efficiency, but its performance is often limited by the nonlinear and symmetric quantization grid and standard rounding-to-nearest (RTN) approach. While learnable rounding has significantly advanced linear PTQ, its application to the non-linear and often discrete nature of logarithmic domain remains unexplored. This paper introduces learnable Logarithmic Adaptive Rounding Techniques (LogART) that pioneer task-aware learnable rounding specifically for the logarithmic domain. LogART further extends the learnable rounding strategy to flexibly support outlier-aware, asymmetric, and hardware-friendly dynamic logarithmic bases, determined in a distribution-aware manner using an efficient search strategy. Extensive experiments demonstrate that LogART achieves state-of-the-art accuracy while maintaining efficiency in quantizing models across various architectures and ultra-low bitwidths, outperforming existing logarithmic PTQ methods and paving the way for more effective hardware deployment. The code is available at https://github.com/logart-lab/logart.

Kaiwen Zheng, Huayu Chen, Haotian Ye, Haoxiang Wang, Qinsheng Zhang, Kai Jiang, Hang Su, Stefano Ermon, Jun Zhu, Ming-Yu Liu

Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Recent works discretize the reverse sampling process to enable GRPO-style training, yet they inherit fundamental drawbacks, including solver restrictions, forward–reverse inconsistency, and complicated integration with classifier-free guidance (CFG). We introduce Diffusion Negative-aware FineTuning (DiffusionNFT), a new online RL paradigm that optimizes diffusion models directly on the forward process via flow matching. DiffusionNFT contrasts positive and negative generations to define an implicit policy improvement direction, naturally incorporating reinforcement signals into the supervised learning objective. This formulation enables training with arbitrary black-box solvers, eliminates the need for likelihood estimation, and requires only clean images rather than sampling trajectories for policy optimization. DiffusionNFT is up to $25\times$ more efficient than FlowGRPO in head-to-head comparisons, while being CFG-free. For instance, DiffusionNFT improves the GenEval score from 0.24 to 0.98 within 1k steps, while FlowGRPO achieves 0.95 with over 5k steps and additional CFG employment. By leveraging multiple reward models, DiffusionNFT significantly boosts the performance of SD3.5-Medium in every benchmark tested.

Applications · Language, Speech and Dialog

Xiaohe Bo, Rui Li, Zexu Sun, Quanyu Dai, Zeyu Zhang, Zihang Tian, Xu Chen, Zhenhua Dong

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language, and the latter through implicit parameter updates. However, prior work has typically studied them in isolation, leaving their synergistic potential largely underexplored. To bridge this gap, in this paper, we introduce MetaTuner, a novel framework that jointly integrates prompt optimization and fine-tuning for LLM training. Specifically, we introduce two neural networks to generate prompts and parameters, respectively, while allowing them to share a common bottom encoding layer to enable knowledge sharing. By the guidance of the final supervised signals, our framework is optimized to discover the optimal combinations between the prompts and parameters. Given that prompt learning involves discrete optimization while fine-tuning operates in a continuous parameter space, we design a supervised regularization loss to train our framework effectively. Extensive experiments across diverse benchmarks show that our method consistently outperforms the baselines. To benefit the research community, we have released our project at https://github.com/BoXiaohe/MetaTuner.