论文检索

Deep Learning · Large Language Models

Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges.Caching all Key and Value (KV) states across all attention heads consumes substantial memory.Existing KV cache pruning methods either damage the long-context capabilities of LLMs or offer only limited efficiency improvements.In this paper, we identify that only a fraction of attention heads, a.k.a, Retrieval Heads, are critical for processing long contexts and require full attention across all tokens.In contrast, all other heads, which primarily focus on recent tokens and attention sinks—referred to as Streaming Heads—do not require full attention.Based on this insight, we introduce DuoAttention, a framework that only applies a full KV cache to retrieval heads while using a light-weight, constant-length KV cache for streaming heads, which reduces both LLM's decoding and pre-filling memory and latency without compromising its long-context abilities.DuoAttention uses a lightweight, optimization-based algorithm with synthetic data to identify retrieval heads accurately.Our method significantly reduces long-context inference memory by up to 2.55$\times$ for MHA and 1.67$\times$ for GQA models while speeding up decoding by up to 2.18$\times$ and 1.50$\times$ and accelerating pre-filling by up to 1.73$\times$ and 1.63$\times$ for MHA and GQA models, respectively, with minimal accuracy loss compared to full attention.Notably, combined with quantization, DuoAttention enables Llama-3-8B decoding with 3.33 million context length measured on a single A100 GPU. Code is provided in https://github.com/mit-han-lab/duo-attention.

Deep Learning · Graph Neural Networks

Carlo Abate, Filippo Maria Bianchi

We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach works well on any kind of graph topology and can find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, trainable end-to-end, and particularly suitable for downstream tasks on heterophilic graphs.

Applications · Computer Vision

Xinchen Zhang, Ling Yang, Guohao Li, YaQi Cai, xie jiake, Yong Tang, Yujiu Yang, Mengdi Wang, Bin CUI

Advanced diffusion models like Stable Diffusion 3, Omost, and FLUX have made notable strides in compositional text-to-image generation. However, these methods typically exhibit distinct strengths for compositional generation, with some excelling in handling attribute binding and others in spatial relationships. This disparity highlights the need for an approach that can leverage the complementary strengths of various models to comprehensively improve the composition capability. To this end, we introduce IterComp, a novel framework that aggregates composition-aware model preferences from multiple models and employs an iterative feedback learning approach to enhance compositional generation. Specifically, we curate a gallery of six powerful open-source diffusion models and evaluate their three key compositional metrics: attribute binding, spatial relationships, and non-spatial relationships. Based on these metrics, we develop a composition-aware model preference dataset comprising numerous image-rank pairs to train composition-aware reward models. Then, we propose an iterative feedback learning method to enhance compositionality in a closed-loop manner, enabling the progressive self-refinement of both the base diffusion model and reward models over multiple iterations. Detailed theoretical proof demonstrates the effectiveness of this method. Extensive experiments demonstrate our significant superiority over previous methods, particularly in multi-category object composition and complex semantic alignment. IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation. Code: https://github.com/YangLing0818/IterComp

Applications · Computer Vision

Mingyang Chen, Jiawei Du, Bo Huang, Yi Wang, Xiaobo Zhang, Wei Wang

Dataset distillation aims to streamline the training process by creating a compact yet effective dataset for a much larger original dataset. However, existing methods often struggle with distilling large, high-resolution datasets due to prohibitive resource costs and limited performance, primarily stemming from sample-wise optimizations in the pixel space. Motivated by the remarkable capabilities of diffusion generative models in learning target dataset distributions and controllably sampling high-quality data tailored to user needs, we propose framing dataset distillation as a controlled diffusion generation task aimed at generating data specifically tailored for effective training purposes. By establishing a correlation between the overarching objective of dataset distillation and the trajectory influence function, we introduce the Influence-Guided Diffusion (IGD) sampling framework to generate training-effective data without the need to retrain diffusion models. An efficient guided function is designed by leveraging the trajectory influence function as an indicator to steer diffusions to produce data with influence promotion and diversity enhancement. Extensive experiments show that the training performance of distilled datasets generated by diffusions can be significantly improved by integrating with our IGD method and achieving state-of-the-art performance in distilling ImageNet datasets. Particularly, an exceptional result is achieved on the ImageNet-1K, reaching 60.3\% at IPC=50. Our code is available at https://github.com/mchen725/DD_IGD.

Social Aspects · Trustworthy Machine Learning

Haoyu Wang, Sunhao Dai, Haiyuan Zhao, Liang Pang, Xiao Zhang, Gang Wang, Zhenhua Dong, Jun Xu, Ji-Rong Wen

Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to these documents even when their semantic quality is comparable to human-written ones. This phenomenon, known as source bias, threatens the sustainable development of the information access ecosystem. However, the underlying causes of source bias remain unexplored. In this paper, we explain the process of information retrieval with a causal graph and discover that PLM-based retrievers learn perplexity features for relevance estimation, causing source bias by ranking the documents with low perplexity higher. Theoretical analysis further reveals that the phenomenon stems from the positive correlation between the gradients of the loss functions in language modeling task and retrieval task. Based on the analysis, a causal-inspired inference-time debiasing method is proposed, called **C**ausal **D**iagnosis and **C**orrection (CDC). CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall estimated relevance score. Experimental results across three domains demonstrate the superior debiasing effectiveness of CDC, emphasizing the validity of our proposed explanatory framework. Source codes are available at https://github.com/WhyDwelledOnAi/Perplexity-Trap.

Social Aspects · Accountability, Transparency and Interpretability

Felix Jedidja Binder, James Chua, Tomek Korbak, Henry Sleight, John Hughes, Robert Long, Ethan Perez, Miles Turpin, Owain Evans

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g. thoughts and feelings) that are not accessible to external observers. Do LLMs have this introspective capability of privileged access? If they do, this would show that LLMs can acquire knowledge not contained in or inferable from training data.We investigate LLMs predicting properties of their own behavior in hypothetical situations. If a model M1 has this capability, it should outperform a different model M2 in predicting M1's behavior—even if M2 is trained on M1's ground-truth behavior.The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger).In experiments with GPT-4, GPT-4o, and Llama-3 models, we find that the model M1 outperforms M2 in predicting itself, providing evidence for privileged access. Further experiments and ablations provide additional evidence.Our results show that LLMs can offer reliable self-information independent of external data in certain domains. By demonstrating this, we pave the way for further work on introspection in more practical domains, which would have significant implications for model transparency and explainability. However, while we successfully show introspective capabilities in simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization.

Social Aspects · Trustworthy Machine Learning

Xiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen, Weiming Zhang, Min Lin

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content from LLMs while preserving the overall performance. In this paper, we discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches. To address the issue of inadequate evaluation of model outputs after unlearning, we introduce three additional metrics to evaluate token diversity, sentence semantics, and factual correctness. We then categorize unlearning methods into untargeted and targeted, and discuss their issues respectively. Specifically, the behavior that untargeted unlearning attempts to approximate is unpredictable and may involve hallucinations, and existing regularization is insufficient for targeted unlearning. To alleviate these issues, we propose using the objective of maximizing entropy (ME) for untargeted unlearning and incorporate answer preservation (AP) loss as regularization for targeted unlearning. Experimental results across three scenarios, i.e., fictitious unlearning, continual unlearning, and real-world unlearning, demonstrate the effectiveness of our approaches. The code is available at https://github.com/sail-sg/closer-look-LLM-unlearning.

Deep Learning · Large Language Models

Juntao Dai, Taiye Chen, Yaodong Yang, Qian Zheng, Gang Pan

Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an open challenge leading to discrepancies between the performance of LLMs under the reward model and the true human objectives. A primary contributor to reward over-optimization is the extrapolation error that arises when the reward model evaluates out-of-distribution (OOD) responses. However, current methods still fail to prevent the increasing frequency of OOD response generation during the reinforcement learning (RL) process and are not effective at handling extrapolation errors from OOD responses. In this work, we propose the *Behavior-Supported Policy Optimization* (BSPO) method to mitigate the reward over-optimization issue. Specifically, we define *behavior policy* as the next token distribution of the reward training dataset to model the in-distribution (ID) region of the reward model. Building on this, we introduce the behavior-supported Bellman operator to regularize the value function, penalizing all OOD values without impacting the ID ones. Consequently, BSPO reduces the generation of OOD responses during the RL process, thereby avoiding overestimation caused by the reward model’s extrapolation errors. Theoretically, we prove that BSPO guarantees a monotonic improvement of the supported policy until convergence to the optimal behavior-supported policy. Empirical results from extensive experiments show that BSPO outperforms baselines in preventing reward over-optimization due to OOD evaluation and finding the optimal ID policy.

Applications · Everything Else

Junchao Gong, Siwei Tu, Weidong Yang, Ben Fei, Kun Chen, Wenlong Zhang, Xiaokang Yang, Wanli Ouyang, LEI BAI

Precipitation nowcasting plays a pivotal role in socioeconomic sectors, especially in severe convective weather warnings. Although notable progress has been achieved by approaches mining the spatiotemporal correlations with deep learning, these methods still suffer severe blurriness as the lead time increases, which hampers accurate predictions for extreme precipitation. To alleviate blurriness, researchers explore generative methods conditioned on blurry predictions. However, the pairs of blurry predictions and corresponding ground truth need to be given in advance, making the training pipeline cumbersome and limiting the generality of generative models within blurry modes that appear in training data. By rethinking the blurriness in precipitation nowcasting as a blur kernel acting on predictions, we propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. Specifically, we utilize blurry predictions to guide the generation process of a pre-trained unconditional denoising diffusion probabilistic model (DDPM) to obtain high-fidelity predictions with eliminated blurriness. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional DDPM to any blurriness modes varying from datasets and lead times in precipitation nowcasting. Extensive experiments are conducted on 7 precipitation radar datasets, demonstrating the generality and superiority of our method.

Deep Learning · Other Representation Learning

Renjie Pan, Jihao Dong, Hua Yang

In this paper, we identify a common yet challenging issue in image-text matching, i.e., clone negatives: negative image-text pairs that semantically resemble positive pairs, leading to ambiguous and sub-optimal matching outcomes. To tackle this issue, we propose Adaptive Contrastive Learning (AdaCL), which introduces two margin parameters along with a modulating anchor to dynamically strengthen the compactness between positives and mitigate the influence of clone negatives. The modulating anchor is selected based on the distribution of negative samples without the need for explicit training, allowing for progressive tuning and advanced in-batch supervision. Extensive experiments across several tasks demonstrate the effectiveness of AdaCL in image-text matching. Furthermore, we extend AdaCL to weakly-supervised image-text matching by replacing human-annotated descriptions with automatically generated captions, thereby increasing the number of potential clone negatives. AdaCL maintains robustness in this setting, alleviating the reliance on crowd-sourced annotations and laying a foundation for scalable vision-language contrastive learning.

Social Aspects · Trustworthy Machine Learning

Aya Ismail, Tuomas Oikarinen, Amy Wang, Julius Adebayo, Samuel Stanton, Hector Corrada Bravo, Kyunghyun Cho, Nathan Frey

We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our architecture offers three key benefits: i) Control: We can intervene on concept values to precisely control the properties of generated proteins, achieving a 3$\times$ larger change in desired concept values compared to baselines. ii) Interpretability: A linear mapping between concept values and predicted tokens allows transparent analysis of the model's decision-making process. iii) Debugging: This transparency facilitates easy debugging of trained models. Our models achieve pre-training perplexity and downstream task performance comparable to traditional masked protein language models, demonstrating that interpretability does not compromise performance. While adaptable to any language model, we focus on masked protein language models due to their importance in drug discovery and the ability to validate our model's capabilities through real-world experiments and expert knowledge. We scale our CB-pLM from 24 million to 3 billion parameters, making them the largest Concept Bottleneck Models trained and the first capable of generative language modeling.

Deep Learning · Large Language Models

Christopher Ackerman, Nina Panickssery

It has been reported that LLMs can recognize their own writing. As this has potential implications for AI safety, yet is relatively understudied, we investigate the phenomenon, seeking to establish: whether it robustly occurs at the behavioral level, how the observed behavior is achieved, and whether it can be controlled. First, we find that the Llama3-8b–Instruct chat model - but not the base Llama3-8b model - can reliably distinguish its own outputs from those of humans, and present evidence that the chat model is likely using its experience with its own outputs, acquired during post-training, to succeed at the writing recognition task. Second, we identify a vector in the residual stream of the model that is differentially activated when the model makes a correct self-written-text recognition judgment, show that the vector activates in response to information relevant to self-authorship, present evidence that the vector is related to the concept of ``self'' in the model, and demonstrate that the vector is causally related to the model’s ability to perceive and assert self-authorship. Finally, we show that the vector can be used to control both the model’s behavior and its perception, steering the model to claim or disclaim authorship by applying the vector to the model’s output as it generates it, and steering the model to believe or disbelieve it wrote arbitrary texts by applying the vector to them as the model reads them.

Theory · Optimization

Poojan Shah, Ragesh Jaiswal

$D^2$-sampling is a fundamental component of sampling-based clustering algorithms such as $k$-means++. Given a dataset $V \subset \mathbb{R}^d$ with $N$ points and a center set $C \subset \mathbb{R}^d$, $D^2$-sampling refers to picking a point from $V$ where the sampling probability of a point is proportional to its squared distance from the nearest center in $C$.The popular $k$-means++ algorithm is simply a $k$-round $D^2$-sampling process, which runs in $O(Nkd)$ time and gives $O(\log{k})$-approximation in expectation for the $k$-means problem.In this work, we give a quantum algorithm for (approximate) $D^2$-sampling in the QRAM model that results in a quantum implementation of $k$-means++ with a running time $\tilde{O}(\zeta^2 k^2)$. Here $\zeta$ is the aspect ratio ( i.e., largest to smallest interpoint distance) and $\tilde{O}$ hides polylogarithmic factors in $N, d, k$.It can be shown through a robust approximation analysis of $k$-means++ that the quantum version preserves its $O(\log{k})$ approximation guarantee.Further, we show that our quantum algorithm for $D^2$-sampling can be dequantized using the sample-query access model of Tang (PhD Thesis, Ewin Tang, University of Washington, 2023). This results in a fast quantum-inspired classical implementation of $k$-means++, which we call QI-$k$-means++, with a running time $O(Nd) + \tilde{O}(\zeta^2k^2d)$, where the $O(Nd)$ term is for setting up the sample-query access data structure.Experimental investigations show promising results for QI-$k$-means++ on large datasets with bounded aspect ratio.Finally, we use our quantum $D^2$-sampling with the known $ D^2$-sampling-based classical approximation scheme to obtain the first quantum approximation scheme for the $k$-means problem with polylogarithmic running time dependence on $N$.

Social Aspects · Trustworthy Machine Learning

Yipei Wang, Xiaoqian Wang

Deep ensembles improve the performance of the models by taking the average predictions of a group of ensemble members. However, the origin of these capabilities remains a mystery and deep ensembles are used as a reliable “black box” to improve the performance. Existing studies typically attribute such improvement to Jensen gaps of the deep ensemble method, where the loss of the mean does not exceed the mean of the loss for any convex loss metric. In this work, we demonstrate that Jensen’s inequality is not responsible for the effectiveness of deep ensembles, and convexity is not a necessary condition. Instead, Jensen Gap focuses on the “average loss” of individual models, which provides no practical meaning. Thus it fails to explain the core phenomena of deep ensembles such as the superiority to any single ensemble member, the decreasing loss with the number of ensemble members, etc. Regarding this mystery, we provide theoretical analysis and comprehensive empirical results from a statistical perspective that reveal the true mechanism of deep ensembles. Our results highlight that deep ensembles originate from the homogeneous output distribution across all ensemble members. Specifically, the predictions of homogeneous models (Abe et al., 2022b) have the distributional equivalence property – Although the predictions of independent ensemble members are point-wise different, they form an identical distribution. Such agreement and disagreement contribute to deep ensembles’ “magical power”. Based on this discovery, we provide rigorous proof of the effectiveness of deep ensembles and analytically quantify the extent to which ensembles improve performance. The derivations not only theoretically quantify the effectiveness of deep ensembles for the first time, but also enable estimation schemes that foresee the performance of ensembles with different capacities. Furthermore, different from existing studies, our results also point out that deep ensembles work in a different mechanism from model scaling a single model, even though significant correlations between them have been observed.

Probabilistic Methods · Everything Else

Jonghyeok Lee, Chen Xu, Yao Xie

Conformal prediction has been a popular distribution-free framework for uncertainty quantification. In this work, we present a novel conformal prediction method for time-series, which we call Kernel-based Optimally Weighted Conformal Prediction Intervals ($\texttt{KOWCPI}$). Specifically, $\texttt{KOWCPI}$ adapts the classic Reweighted Nadaraya-Watson (RNW) estimator for quantile regression on dependent data and learns optimal data-adaptive weights. Theoretically, we tackle the challenge of establishing a conditional coverage guarantee for non-exchangeable data under strong mixing conditions on the non-conformity scores. We demonstrate the superior performance of $\texttt{KOWCPI}$ on real time-series against state-of-the-art methods, where $\texttt{KOWCPI}$ achieves narrower confidence intervals without losing coverage.

Miscellaneous Aspects of Machine Learning · Sequential, Network, and Time Series Modeling

Jonathan Y. Zhou, Yao Xie

In the wild, we often encounter collections of sequential data such as electrocardiograms, motion capture, genomes, and natural language, and sequences may be multichannel or symbolic with nonlinear dynamics. We introduce a method to learn low-dimensional representations of nonlinear sequence and time-series data without supervision which has provable recovery guarantees. The learned representation can be used for downstream machine-learning tasks such as clustering and classification. The method assumes that the observed sequences arise from a common domain, with each sequence following its own autoregressive model, and these models are related through low-rank regularization. We cast the problem as a convex matrix parameter recovery problem using monotone variational inequalities (VIs) and encode the common domain assumption via low-rank constraint across the learned representations, which can learn a subspace approximately spanning the entire domain as well as faithful representations for the dynamics of each individual sequence incorporating the domain information in totality. We show the competitive performance of our method on real-world time-series data with baselines and demonstrate its effectiveness for symbolic text modeling and RNA sequence clustering.

Deep Learning · Large Language Models

Qinghao Ye, Xianhan Zeng, Fu Li, Chunyuan Li, Haoqi Fan

Image captioning has long been a pivotal task in visual understanding, with recent advancements in vision-language models (VLMs) significantly enhancing the ability to generate detailed image captions. However, the evaluation of detailed image captioning remains underexplored due to outdated evaluation metrics and coarse annotations. In this paper, we introduce DeCapBench along with a novel metric, DCScore, specifically designed for detailed captioning tasks. DCScore evaluates hallucinations and fine-grained comprehensiveness by deconstructing responses into the smallest self-sufficient units, termed primitive information units, and assessing them individually. Our evaluation shows that DCScore aligns more closely with human judgment than other rule-based or model-based metrics. Concurrently, DeCapBench exhibits a high correlation with VLM arena results on descriptive tasks, surpassing existing benchmarks for vision-language models. Additionally, we present an automatic fine-grained feedback collection method, FeedQuill, for preference optimization based on our advanced metric, demonstrating robust generalization capabilities across auto-generated preference data. Extensive experiments on multiple VLMs demonstrate that our method not only significantly reduces hallucinations but also enhances performance across various benchmarks, achieving superior detail captioning performance while surpassing GPT-4o.

Applications · Robotics

Junliang Chen, Huaiyuan Xu, Yi Wang, Lap-Pui Chau

Predicting variations in complex traffic environments is crucial for the safety of autonomous driving. Recent advancements in occupancy forecasting have enabled forecasting future 3D occupied status in driving environments by observing historical 2D images. However, high computational demands make occupancy forecasting less efficient during training and inference stages, hindering its feasibility for deployment on edge agents. In this paper, we propose a novel framework, \textit{i.e.}, OccProphet, to efficiently and effectively learn occupancy forecasting with significantly lower computational requirements while improving forecasting accuracy. OccProphet comprises three lightweight components: Observer, Forecaster, and Refiner. The Observer extracts spatio-temporal features from 3D multi-frame voxels using the proposed Efficient 4D Aggregation with Tripling-Attention Fusion, while the Forecaster and Refiner conditionally predict and refine future occupancy inferences. Experimental results on nuScenes, Lyft-Level5, and nuScenes-Occupancy datasets demonstrate that OccProphet is both training- and inference-friendly. OccProphet reduces 58\%$\sim$78\% of the computational cost with a 2.6$\times$ speedup compared with the state-of-the-art Cam4DOcc. Moreover, it achieves 4\%$\sim$18\% relatively higher forecasting accuracy. Code and models are publicly available at https://github.com/JLChen-C/OccProphet.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Lu Li, Tianyu Zhang, Zhiqi Bu, Suyuchen Wang, Huan He, Jie Fu, Yonghui Wu, Jiang Bian, Yong Chen, Yoshua Bengio

Model merging has emerged as an effective approach to combining multiple single-task models into a multitask model. This process typically involves computing a weighted average of the model parameters without additional training. Existing model-merging methods focus on improving average task accuracy. However, interference and conflicts between the objectives of different tasks can lead to trade-offs during the merging process. In real-world applications, a set of solutions with various trade-offs can be more informative, helping practitioners make decisions based on diverse preferences. In this paper, we introduce a novel and low-compute algorithm, Model Merging with Amortized Pareto Front (MAP). MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved. It amortizes the substantial computational cost of evaluations needed to estimate the Pareto front by using quadratic approximation surrogate models derived from a preselected set of scaling coefficients. Experimental results on vision and natural language processing tasks demonstrate that MAP can accurately identify the Pareto front, providing practitioners with flexible solutions to balance competing task objectives. We also introduce Bayesian MAP for scenarios with a relatively low number of tasks and Nested MAP for situations with a high number of tasks, further reducing the computational cost of evaluation.

Deep Learning · Large Language Models

Sheng Wang, Liheng Chen, Pengan CHEN, Jingwei DONG, Boyang XUE, Jiyue Jiang, Lingpeng Kong, Chuan Wu

The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served simultaneously.Targeting more parameter-efficient low-rank adaptation (LoRA), parameter sharing presents a promising solution. Empirically, our research into high-level sharing principles highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing.Guided by this finding, we propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies, namely subset selection, pair dissociation, vector sharding, and shard privatization. Briefly, it selects a designated number of shards from global pools with a Mixture-of-Experts (MoE)-like routing mechanism before sequentially concatenating them to low-rank matrices.Hence, it retains all the advantages of LoRA while offering enhanced parameter efficiency, and effectively circumvents the drawbacks of peer parameter-sharing methods.Our empirical experiments demonstrate approximately $8\times$ parameter savings in a standard LoRA setting. The ablation study confirms the significance of each component.Our insights into parameter sharing and MoS method may illuminate future developments of more parameter-efficient finetuning methods.The code is officially available at https://github.com/Forence1999/MoS.