论文检索

Amitava Das, Suranjana Trivedy, Danush Khanna, Yaswanth Narsupalli, Basab Ghosh, Rajarshi Roy, Gurpreet Singh, Vinija Jain, Vasu Sharma, Aishwarya Naresh Reganti 等

The rapid advancement of large language models (LLMs) has revolutionized numerous applications, but presents significant challenges in aligning these models with diverse human values, ethical standards, and specific user preferences. Direct Preference Optimization (DPO) has become a cornerstone for preference alignment but is constrained by reliance on fixed divergence measures and limited feature transformations. We introduce DPO-Kernels, an innovative enhancement of DPO that integrates kernel methods to overcome these challenges through four key contributions: (i) Kernelized Representations: These representations enhance divergence measures by using polynomial, RBF, Mahalanobis, and spectral kernels for richer feature transformations. Additionally, we introduce a hybrid loss that combines embedding-based loss with probability-based loss; (ii) Divergence Alternatives: Beyond Kullback–Leibler (KL), we incorporate Jensen-Shannon, Hellinger, Rényi, Bhattacharyya, Wasserstein, and other f-divergences to boost stability and robustness; (iii) Data-Driven Selection: Choosing the optimal kernel-divergence pair among 28 combinations (4 kernels \times 7 divergences) is challenging. We introduce automatic metrics that analyze the data to select the best kernel-divergence pair, eliminating the need for manual tuning; (iv) Hierarchical Mixture of Kernels (HMK): Combining local and global kernels for precise and large-scale semantic modeling. This approach automatically selects the optimal kernel mixture during training, enhancing modeling flexibility. DPO-Kernels achieve state-of-the-art generalization in factuality, safety, reasoning, and instruction following across 12 datasets. While alignment risks overfitting, Heavy-Tailed Self-Regularization (HT-SR) theory confirms that DPO-Kernels ensure robust generalization in LLMs. Comprehensive resources are available to facilitate further research and application of DPO-Kernels.

Akshat Sharma, Hangliang Ding, Jianping Li, Neel Dani, Minjia Zhang

State-of-the-art 2-bit KV cache quantization techniques achieve excellent results in accelerating LLM inference while retaining accuracy on long context tasks. However, further pushing the compression ratio fails to deliver performance gains. In this work, we revisit these approaches by considering, additionally, adaptive KV methods that retain LLM accuracy with only a subset of KV states. This leads us to propose a method based on 2-bit KV cache quantization with adaptive KV policies. In addition, we take an algorithm and system co-design approach by developing hardware-friendly kernels to accelerate LLM inference while making MiniKV compatible with existing memory-efficient attention techniques such as FlashAttention, effectively translating algorithmic improvements into system performance gains. Experiments on a wide range of long context tasks show that MiniKV effectively achieves >80% KV cache compression while retaining accuracy, outperforming state-of-the-art methods while achieving excellent latency, throughput, and memory consumption improvements in long context inference.

Mingxu Chai, Ziyu Shen, Chong Zhang, Yue Zhang, Xiao Wang, Shihan Dou, Jihua Kang, Jiazheng Zhang, Qi Zhang

Document parsing involves layout element detection and recognition, essential for extracting information. However, existing methods often employ multiple models for these tasks, leading to increased system complexity and maintenance overhead. While some models attempt to unify detection and recognition, they often fail to address the intrinsic differences in data representations, thereby limiting performance in document processing. Our research reveals that recognition relies on discrete tokens, whereas detection relies on continuous coordinates, leading to challenges in gradient updates and optimization. To bridge this gap, we propose the Gaussian-Kernel Cross-Entropy Loss (GK-CEL), enabling generative frameworks to handle both tasks simultaneously. Building upon GK-CEL, we propose DocFusion, a unified document parsing model with only 0.28B parameters. Additionally, we construct the DocLatex-1.6M dataset to provide high-quality training support. Experimental results show that DocFusion, equipped with GK-CEL, performs competitively across four core document parsing tasks, validating the effectiveness of our unified approach.

Hayden Helm, Aranyak Acharyya, Youngser Park, Brandon Duderstadt, Carey Priebe

Generative models are capable of producing human-expert level content across a variety of topics and domains. As the impact of generative models grows, it is necessary to develop statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model’s pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks.

Coleman Richard Charles Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, Sebastian Zhao, June Paik, Michael W. Mahoney, Kurt Keutzer, Amir Gholami

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation.For these long context length applications, the length of the input prompt poses a significant challenge in terms of inference efficiency since the inference costs increase linearly with sequence length.However, for many of these applications, much of the context in the prompt is fixed across different user inputs, thereby providing the opportunity to perform offline optimizations in order to process user inputs quickly, as they are received. We propose Squeezed Attention to accelerate LLM applications where a large portion of the input context is fixed.We first leverage K-means clustering offline to group the keys for the fixed context based on semantic similarity and represent each cluster with a single centroid value.During inference, we compare query tokens from the user input with the centroids to predict which keys from the fixed context are semantically relevant, and then compute exact attention using only the important keys, thereby reducing bandwidth and computational costs. We also present a hierarchical version of our algorithm which can reduce the complexity of attention from linear to logarithmic with respect to the fixed context length.We evaluate our method on various long-context benchmarks including LongBench, where it achieves a 3.1\times reduction in KV budget with no noticeable accuracy loss and up to an 8\times reduction with only a 0.5 point accuracy gap for the LLaMA-2-7B-32K, LWM-Text-Chat-1M, and Longchat-7B-v1.5-32K models.Futhermore, we implement kernels for centroid comparison and sparse FlashAttention with important keys, achieving more than 4\times speedups during both the prefill and generation phases for long-context inference.Our code is available at https://github.com/SqueezeAILab/SqueezedAttention.

Md Kowsher, Tara Esmaeilbeig, Chun-Nam Yu, Chen Chen, Mojtaba Soltanalian, Niloofar Yousefi

We propose Row-Column Fine-Tuning(RoCoFT), a parameter-efficient fine-tuning method for large language models based on updating only a few rows and columns of the weight matrices in transformers. Through extensive experiments with medium-sized LMs like RoBERTa and DeBERTa, and larger LMs like Bloom-7B, Llama2-7B, and Llama2-13B, we show that our method gives comparable or better accuracies than state-of-the-art Parameter-Efficient Finetuning methods while also being more memory and computation-efficient. We also study the reason behind the effectiveness of our method with tools from neural tangent kernel theory. We empirically demonstrate that our kernel, constructed using a restricted set of row and column parameters, is numerically close to the full-parameter kernel and gives comparable classification performance. Ablation studies are conducted to investigate the impact of different algorithmic choices, including the robustness of RoCoFT to any selection of rows and columns, as well as the optimal rank for the effective implementation of our method.

Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu

Instruction tuning is widely used to enhance a pre-trained Multimodal Large Language Model (MLLM) to understand and follow human instructions by training it on a curated set of task-specific dataset. However, it is infeasible to collect all possible instruction datasets simultaneously in real-world scenarios. Thus, enabling MLLM with continual instruction tuning is essential for maintaining their adaptability. However, existing methods often trade off memory efficiency for performance gains, significantly compromising overall efficiency. In this paper, we propose a task-specific expansion and task-general fusion framework based on the variations in Centered Kernel Alignment (CKA) similarity across different model layers when trained on diverse datasets. Furthermore, we analyze the information leakage present in the existing benchmark and propose a new and more challenging benchmark to rationally evaluate the performance of different methods. Comprehensive experiments showcase a significant performance improvement of our method compared to existing state-of-the-art methods. Our code will be public available.

Jihao Zhao, Zhiyuan Ji, Zhaoxin Fan, Hanyu Wang, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the inherent trade-off between computational efficiency and chunking precision in LLM-based approaches, we devise the granularity-aware Mixture-of-Chunkers (MoC) framework, which consists of a three-stage processing mechanism. Notably, our objective is to guide the chunker towards generating a structured list of chunking regular expressions, which are subsequently employed to extract chunks from the original text. Extensive experiments demonstrate that both our proposed metrics and the MoC framework effectively settle challenges of the chunking task, revealing the chunking kernel while enhancing the performance of the RAG system.

Reinforcement Learning · Batch/Offline

Brahma Pavse, Yudong Chen, Qiaomin Xie, Josiah Hanna

In reinforcement learning, offline value function learning is the procedure of using an offline dataset to estimate the expected discounted return from each state when taking actions according to a fixed target policy. The stability of this procedure, i.e., whether it converges to its fixed-point, critically depends on the representations of the state-action pairs. Poorly learned representations can make value function learning unstable, or even divergent. Therefore, it is critical to stabilize value function learning by explicitly shaping the state-action representations. Recently, the class of bisimulation-based algorithms have shown promise in shaping representations for control. However, it is still unclear if this class of methods can \emph{stabilize} value function learning. In this work, we investigate this question and answer it affirmatively. We introduce a bisimulation-based algorithm called kernel representations for offline policy evaluation (\textsc{krope}). \textsc{krope} uses a kernel to shape state-action representations such that state-action pairs that have similar immediate rewards and lead to similar next state-action pairs under the target policy also have similar representations. We show that \textsc{krope}: 1) learns stable representations and 2) leads to lower value error than baselines. Our analysis provides new theoretical insight into the stability properties of bisimulation-based methods and suggests that practitioners can use these methods to improve the stability and accuracy of offline evaluation of reinforcement learning agents.

Deep Learning · Other Representation Learning

YinFeng Chen, Jin Liu, Rui Qiu

The normal vectors obtained from the support vector machine (SVM) method offer the potential to achieve sufficient dimension reduction in both classification and regression scenarios. Motivated by it, we in this paper introduce a unified framework for nonlinear sufficient dimension reduction based on classification ensemble. Kernel principal SVM, which leverages the reproducing kernel Hilbert space, can almost be regarded as a special case of this framework, and we generalize it by using a neural network function class for more flexible deep nonlinear reduction. We theoretically prove its unbiasedness with respect to the central $\sigma$-field and provide a nonasymptotic upper bound for the estimation error. Simulations and real data analysis demonstrate the considerable competitiveness of the proposed method, especially under heavy data contamination, large sample sizes, and complex inputs.

Deep Learning · Large Language Models

Haojie Duanmu, Xiuhong Li, Zhihang Yuan, Size Zheng, Jiangfei Duan, Xingcheng ZHANG, Dahua Lin

Mixture-of-Experts (MoE) models face deployment challenges due to their large parameter counts and computational demands. We explore quantization for MoE models and highlight two key insights: 1) linear blocks exhibit varying quantization sensitivity, and 2) divergent expert activation frequencies create heterogeneous computational characteristics. Based on these observations, we introduce MxMoE, a mixed-precision optimization framework for MoE models that considers both algorithmic and system perspectives. MxMoE navigates the design space defined by parameter sensitivity, expert activation dynamics, and hardware resources to derive efficient mixed-precision configurations. Additionally, MxMoE automatically generates optimized mixed-precision GroupGEMM kernels, enabling parallel execution of GEMMs with different precisions. Evaluations show that MxMoE outperforms existing methods, achieving 2.4 lower Wikitext-2 perplexity than GPTQ at 2.25-bit and delivering up to 3.4x speedup over full precision, as well as up to 29.4% speedup over uniform quantization at equivalent accuracy with 5-bit weight-activation quantization. Our code is available at https://github.com/cat538/MxMoE.

Theory · Probabilistic Methods

Annabelle Carrell, Albert Gong, Abhishek Shetty, Raaz Dwivedi, Lester Mackey

The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of uniform subsampling while substantially reducing the number of summary points. However, existing guarantees cover only a restricted range of distributions and kernel-based quality measures and suffer from pessimistic dimension dependence. To address these deficiencies, we introduce a new low-rank analysis of sub-Gaussian thinning that applies to any distribution and any kernel, guaranteeing high-quality compression whenever the kernel or data matrix is approximately low-rank. To demonstrate the broad applicability of the techniques, we design practical sub-Gaussian thinning approaches that improve upon the best known guarantees for approximating attention in transformers, accelerating stochastic gradient training through reordering, and distinguishing distributions in near-linear time.

General Machine Learning · Kernel methods

Junhong Zhang, Zhihui Lai

Kernel methods are powerful tools for nonlinear learning with well-established theory. The scalability issue has been their long-standing challenge. Despite the existing success, there are two limitations in large-scale kernel methods: (i) The memory overhead is too high for users to afford; (ii) existing efforts mainly focus on kernel ridge regression (KRR), while other models lack study. In this paper, we propose **Joker**, a joint optimization framework for diverse kernel models, including KRR, logistic regression, and support vector machines. We design a dual block coordinate descent method with trust region (DBCD-TR) and adopt kernel approximation with randomized features, leading to low memory costs and high efficiency in large-scale learning. Experiments show that **Joker** saves up to 90% memory but achieves comparable training time and performance (or even better) than the state-of-the-art methods.

Reinforcement Learning

Yuhui Wang, Qingyuan Wu, Dylan Ashley, Francesco Faccio, Weida Li, Chao Huang, Jürgen Schmidhuber

The Value Iteration Network (VIN) is an end-to-end differentiable neural network architecture for planning. It exhibits strong generalization to unseen domains by incorporating a differentiable planning module that operates on a latent Markov Decision Process (MDP). However, VINs struggle to scale to long-term and large-scale planning tasks, such as navigating a $100\times 100$ maze---a task that typically requires thousands of planning steps to solve. We observe that this deficiency is due to two issues: the representation capacity of the latent MDP and the planning module's depth. We address these by augmenting the latent MDP with a dynamic transition kernel, dramatically improving its representational capacity, and, to mitigate the vanishing gradient problem, introduce an "adaptive highway loss" that constructs skip connections to improve gradient flow. We evaluate our method on 2D/3D maze navigation environments, continuous control, and the real-world Lunar rover navigation task. We find that our new method, named Dynamic Transition VIN (DT-VIN), scales to 5000 layers and solves challenging versions of the above tasks. Altogether, we believe that DT-VIN represents a concrete step forward in performing long-term large-scale planning in complex environments.

General Machine Learning · Clustering

Qianqian Wang, Mengping Jiang, Zhengming Ding, Quanxue Gao

K-Means clustering is a classical and effective unsupervised learning method attributed to its simplicity and efficiency. However, it faces notable challenges, including sensitivity to random initial centroid selection, a limited ability to discover the intrinsic manifold structures within nonlinear datasets, and difficulty in achieving balanced clustering in practical scenarios. To overcome these weaknesses, we introduce a novel framework for K-Means that leverages manifold learning. This approach eliminates the need for centroid calculation and utilizes a cluster indicator matrix to align the manifold structures, thereby enhancing clustering accuracy. Beyond the traditional Euclidean distance, our model incorporates Gaussian kernel distance, K-nearest neighbor distance, and low-pass filtering distance to effectively manage data that is not linearly separable. Furthermore, we introduce a balanced regularizer to achieve balanced clustering results. The detailed experimental results demonstrate the efficacy of our proposed methodology.

Optimization · Stochastic

Haihan Zhang, Weicheng Lin, Yuanshi Liu, Cong Fang

This paper considers a canonical problem in kernel regression: how good are the model performances when it is trained by the popular online first-order algorithms, compared to the offline ones, such as ridge and ridgeless regression? In this paper, we analyze the foundational single-pass Stochastic Gradient Descent (SGD) in kernel regression under source condition where the optimal predictor can even not belong to the RKHS, i.e. the model is misspecified. Specifically, we focus on the inner product kernel over the sphere and characterize the exact orders of the excess risk curves under different scales of sample sizes $n$ concerning the input dimension $d$. Surprisingly, we show that SGD achieves min-max optimal rates up to constants among all the scales, $without$ suffering the saturation, a prevalent phenomenon observed in (ridge) regression, except when the model is highly misspecified and the learning is in a final stage where $n\gg d^\gamma$ with any constant $\gamma >0$. The main reason for SGD to overcome the curse of saturation is the exponentially decaying step size schedule, a common practice in deep neural network training. As a byproduct, we provide the $first$ provable advantage of the scheme over the iterative averaging method in the common setting.

Deep Learning · Graph Neural Networks

Karish Grover, Geoff Gordon, Christos Faloutsos

Does the intrinsic curvature of complex networks hold the key to unveiling graph anomalies that conventional approaches overlook? Reconstruction-based graph anomaly detection (GAD) methods overlook such geometric outliers, focusing only on structural and attribute-level anomalies. To this end, we propose CurvGAD - a mixed-curvature graph autoencoder that introduces the notion of curvature-based geometric anomalies. CurvGAD introduces two parallel pipelines for enhanced anomaly interpretability: (1) Curvature-equivariant geometry reconstruction, which focuses exclusively on reconstructing the edge curvatures using a mixed-curvature, Riemannian encoder and Gaussian kernel-based decoder; and (2) Curvature-invariant structure and attribute reconstruction, which decouples structural and attribute anomalies from geometric irregularities by regularizing graph curvature under discrete Ollivier-Ricci flow, thereby isolating the non-geometric anomalies. By leveraging curvature, CurvGAD refines the existing anomaly classifications and identifies new curvature-driven anomalies. Extensive experimentation over 10 real-world datasets (both homophilic and heterophilic) demonstrates an improvement of up to 6.5% over state-of-the-art GAD methods. The code is available at: https://github.com/karish-grover/curvgad.

Deep Learning · Large Language Models

Lennart Schneider, Martin Wistuba, Aaron Klein, Jacek Golebiowski, Giovanni Zappella, Felice Antonio Merra

Optimal prompt selection is crucial for maximizing large language model (LLM) performance on downstream tasks, especially in black-box settings where models are only accessible via APIs.Black-box prompt selection is challenging due to potentially large, combinatorial search spaces, absence of gradient information, and high evaluation cost of prompts on a validation set.We propose HbBoPs, a novel method that combines a structural-aware deep kernel Gaussian Process with Hyperband as a multi-fidelity scheduler to efficiently select prompts.HbBoPs uses embeddings of instructions and few-shot exemplars, treating them as modular components within prompts.This enhances the surrogate model's ability to predict which prompt to evaluate next in a sample-efficient manner.Hyperband improves query-efficiency by adaptively allocating resources across different fidelity levels, reducing the number of validation instances required for evaluating prompts.Extensive experiments across ten diverse benchmarks and three LLMs demonstrate that HbBoPs outperforms state-of-the-art methods in both performance and efficiency.

Deep Learning · Algorithms

Mustafa Burak Gurbuz, Xingyu Zheng, Constantine Dovrolis

As deep learning continues to be driven by ever-larger datasets, understanding which examples are most important for generalization has become a critical question. While progress in data selection continues, emerging applications require studying this problem in dynamic contexts. To bridge this gap, we pose the Incremental Data Selection (IDS) problem, where examples arrive as a continuous stream, and need to be selected without access to the full data source. In this setting, the learner must incrementally build a training dataset of predefined size while simultaneously learning the underlying task. We find that in IDS, the impact of a new sample on the model state depends fundamentally on both its geometric relationship in the feature space and its prediction error. Leveraging this insight, we propose PEAKS (Prediction Error Anchored by Kernel Similarity), an efficient data selection method tailored for IDS. Our comprehensive evaluations demonstrate that PEAKS consistently outperforms existing selection strategies. Furthermore, PEAKS yields increasingly better performance returns than random selection as training data size grows on real-world datasets. The code is available at https://github.com/BurakGurbuz97/PEAKS.

Deep Learning

Xuanshu Luo, Martin Werner

Two-dimensional (2D) convolutional kernels have dominated convolutional neural networks (CNNs) in image processing. While linearly scaling 1D convolution provides parameter efficiency, its naive integration into CNNs disrupts image locality, thereby degrading performance. This paper presents path convolution (PathConv), a novel CNN design exclusively with 1D operations, achieving ResNet-level accuracy using only 1/3 parameters. To obtain locality-preserving image traversal paths, we analyze Hilbert/Z-order paths and expose a fundamental trade-off: improved proximity for most pixels comes at the cost of excessive distances for other sacrificed ones to their neighbors. We resolve this issue by proposing path shifting, a succinct method to reposition sacrificed pixels. Using the randomized rounding algorithm, we show that three shifted paths are sufficient to offer better locality preservation than trivial raster scanning. To mitigate potential convergence issues caused by multiple paths, we design a lightweight path-aware channel attention mechanism to capture local intra-path and global inter-path dependencies. Experimental results further validate the efficacy of our method, establishing the proposed 1D PathConv as a viable backbone for efficient vision models.