论文检索

Deep Learning · Large Language Models

Yicheng Xiao, Lin Song, Rui Yang, Cheng Cheng, Yixiao Ge, Xiu Li, Ying Shan

Recent advances have highlighted the benefits of scaling language models to enhance performance across a wide range of NLP tasks. However, these approaches still face limitations in effectiveness and efficiency when applied to domain-specific tasks, particularly for small edge-side models. We propose the LoRA-Gen framework, which utilizes a large cloud-side model to generate LoRA parameters for edge-side models based on task descriptions. By employing the reparameterization technique, we merge the LoRA parameters into the edge-side model to achieve flexible specialization. Our method facilitates knowledge transfer between models while significantly improving the inference efficiency of the specialized model by reducing the input context length. Without specialized training, LoRA-Gen outperforms conventional LoRA fine-tuning, which achieves competitive accuracy and a 2.1x speedup with TinyLLaMA-1.1B in reasoning tasks.Besides, our method delivers a compress ratio of 10.1x with Gemma-2B on intelligent agent tasks.

Deep Learning · Large Language Models

Hanshi Sun, Li-Wen Chang, Wenlei Bao, Size Zheng, Ningxin Zheng, Xin Liu, Harry Dong, Yuejie Chi, Beidi Chen

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for decoding both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to accelerate inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory usage or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on benchmarks like RULER, LongBench, and models such as Llama-3.1-8B and GLM-4-9B-1M, we demonstrate that it achieves up to 6$\times$ larger batch sizes and 3.04$\times$ higher throughput on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory.

Applications · Robotics

Xiaowei Chi, Chun-Kai Fan, Hengyuan Zhang, Xingqun Qi, Rongyu Zhang, Anthony Chen, Chi-Min Chan, Wei Xue, Qifeng Liu, Shanghang Zhang 等

Video generation models have made significant progress in simulating future states, showcasing their potential as world simulators in embodied scenarios. However, existing models often lack robust understanding, limiting their ability to perform multi-step predictions or handle Out-of-Distribution (OOD) scenarios. To address this challenge, we propose the Reflection of Generation (RoG), a set of intermediate reasoning strategies designed to enhance video prediction. It leverages the complementary strengths of pre-trained vision-language and video generation models, enabling them to function as a world model in embodied scenarios. To support RoG, we introduce Embodied Video Anticipation Benchmark(EVA-Bench), a comprehensive benchmark that evaluates embodied world models across diverse tasks and scenarios, utilizing both in-domain and OOD datasets. Building on this foundation, we devise a world model, Embodied Video Anticipator (EVA), that follows a multistage training paradigm to generate high-fidelity video frames and apply an autoregressive strategy to enable adaptive generalization for longer video sequences. Extensive experiments demonstrate the efficacy of EVA in various downstream tasks like video generation and robotics, thereby paving the way for large-scale pre-trained models in real-world video prediction applications. The video demos are available at https://sites.google.com/view/icml-eva.

Theory · Deep Learning

Philipp Misof, Pan Kessel, Jan Gerken

Little is known about the training dynamics of equivariant neural networks, in particular how it compares to data augmented training of their non-equivariant counterparts. Recently, neural tangent kernels (NTKs) have emerged as a powerful tool to analytically study the training dynamics of wide neural networks. In this work, we take an important step towards a theoretical understanding of training dynamics of equivariant models by deriving neural tangent kernels for a broad class of equivariant architectures based on group convolutions. As a demonstration of the capabilities of our framework, we show an interesting relationship between data augmentation and group convolutional networks. Specifically, we prove that they share the same expected prediction over initializations at all training times and even off the data manifold. In this sense, they have the same training dynamics. We demonstrate in numerical experiments that this still holds approximately for finite-width ensembles. By implementing equivariant NTKs for roto-translations in the plane ($G=C_{n}\ltimes\mathbb{R}^{2}$) and 3d rotations ($G=\mathrm{SO}(3)$), we show that equivariant NTKs outperform their non-equivariant counterparts as kernel predictors for histological image classification and quantum mechanical property prediction.

General Machine Learning · Transfer, Multitask and Meta-learning

Zhongyang Li, Ziyue Li, Tianyi Zhou

In large multimodal models (LMMs), the perception of non-language modalities (e.g., visual representations) is usually not on par with the large language models (LLMs)' powerful reasoning capabilities, deterring LMMs' performance on challenging downstream tasks. This weakness has been recently mitigated by replacing the vision encoder with a mixture-of-experts (MoE), which provides rich, multi-granularity, and diverse representations required by different downstream tasks. The performance of multimodal MoE largely depends on its router, which reweights and mixes the representations of different experts for each input. However, we find that the end-to-end trained router does not always produce the optimal routing weights for every test sample. To bridge the gap, we propose a novel and efficient method ''**R**e-**R**outing in **T**est-**T**ime (R2-T2)'' that locally optimizes the vector of routing weights in test-time by moving it toward those vectors of the correctly predicted samples in a neighborhood of the test sample. We propose three R2-T2 strategies with different optimization objectives and neighbor-search spaces. R2-T2 consistently and significantly improves state-of-the-art LMMs' performance on challenging multimodal benchmarks of diverse tasks, without training any parameters in the base model. Our code can be accessed here.

General Machine Learning · Transfer, Multitask and Meta-learning

Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli

We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional training data. This overcomes the limitations of traditional methods that require retraining when switching base models, often challenging due to data constraints. ProLoRA achieves this via projection of source adjustments into the target model's weight space, leveraging subspace and null space similarities and selectively targeting aligned layers. Evaluations on established text-to-image models demonstrate successful knowledge transfer and comparable performance without retraining.

Theory · Online Learning and Bandits

Sanghoon Yu, Min-hwan Oh

We study the linear bandit problem under limited adaptivity, known as the batched linear bandit. While existing approaches can achieve near-optimal regret in theory, they are often computationally prohibitive or underperform in practice. We propose BLAE, a novel batched algorithm that integrates arm elimination with regularized G-optimal design, achieving the minimax optimal regret (up to logarithmic factors in $T$) in both large-$K$ and small-$K$ regimes for the first time, while using only $O(\log\log T)$ batches. Our analysis introduces new techniques for batch-wise optimal design and refined concentration bounds. Crucially, BLAE demonstrates low computational overhead and strong empirical performance, outperforming state-of-the-art methods in extensive numerical evaluations. Thus, BLAE is the first algorithm to combine provable minimax-optimality in all regimes and practical superiority in batched linear bandits.

Deep Learning · Large Language Models

Weizhong Huang, Yuxin Zhang, Xiawu Zheng, Fei Chao, Rongrong Ji

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of **"reconstruction error explosion"** in existing LLMs sparsification methods. This refers to the cumulative effect of reconstruction errors throughout the sparsification process, where errors from earlier layers propagate and amplify in subsequent layers. As a result, the overall reconstruction error increases significantly, leading to a substantial degradation in model performance. Through theoretical analysis, we derive a simple yet effective approach to layer-wise sparsity allocation that mitigates this issue. Our method uses a monotonically increasing arithmetic progression, reducing the process of determining sparsity rates for multiple layers to the determination of a single common difference hyperparameter. Remarkably, this allows for the optimal layer-wise sparsity rates to be identified with just a few trials. Both our theoretical analysis and experimental results demonstrate that this sparsity allocation scheme is near optimal. Extensive experiments show that our method significantly improves the performance of sparse LLMs across various architectures, outperforming existing layer-wise sparsity methods. Furthermore, it enhances the performance of various compression techniques and is applicable to vision and multimodal models. Notably, our method achieves a reduction of 52.10 in perplexity for the 70% sparse LLaMA2-7B model obtained via Wanda, improves average zero-shot accuracy by 10.50%, and delivers speedups of 2.63$\times$ and 2.23$\times$ on CPU and GPU, respectively. Code is available at https://github.com/wzhuang-xmu/ATP.

Reinforcement Learning

Shangzhe Li, Zhiao Huang, Hao Su

Imitation learning (IL) enables agents to acquire skills directly from expert demonstrations, providing a compelling alternative to reinforcement learning. However, prior online IL approaches struggle with complex tasks characterized by high-dimensional inputs and complex dynamics. In this work, we propose a novel approach to online imitation learning that leverages reward-free world models. Our method learns environmental dynamics entirely in latent spaces without reconstruction, enabling efficient and accurate modeling. We adopt the inverse soft-Q learning objective, reformulating the optimization process in the Q-policy space to mitigate the instability associated with traditional optimization in the reward-policy space. By employing a learned latent dynamics model and planning for control, our approach consistently achieves stable, expert-level performance in tasks with high-dimensional observation or action spaces and intricate dynamics. We evaluate our method on a diverse set of benchmarks, including DMControl, MyoSuite, and ManiSkill2, demonstrating superior empirical performance compared to existing approaches.

Deep Learning · Large Language Models

Ibrahim Alabdulmohsin, Andreas Steiner

Language exhibits a fractal structure in its information-theoretic complexity (i.e. bits per token), with self-similarity across scales and long-range dependence (LRD). In this work, we investigate whether large language models (LLMs) can replicate such fractal characteristics and identify conditions-such as temperature setting and prompting method-under which they may fail. Moreover, we find that the fractal parameters observed in natural language are contained within a narrow range, whereas those of LLMs' output vary widely, suggesting that fractal parameters might prove helpful in detecting a non-trivial portion of LLM-generated texts. Notably, these findings, and many others reported in this work, are robust to the choice of the architecture; e.g. Gemini 1.0 Pro, Mistral-7B and Gemma-2B. We also release a dataset comprising over 240,000 articles generated by various LLMs (both pretrained and instruction-tuned) with different decoding temperatures and prompting methods, along with their corresponding human-generated texts. We hope that this work highlights the complex interplay between fractal properties, prompting, and statistical mimicry in LLMs, offering insights for generating, evaluating and detecting synthetic texts.

Applications · Language, Speech and Dialog

William English, Dominic Simon, Sumit Jha, Rickard Ewetz

Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a grounding of atomic propositions (APs) phase and a translation phase. However, existing methods struggle with accurate grounding, the existence of co-references, and learning from limited data. In this paper, we propose a framework for NL to TL translation called Grammar Forced Translation (GraFT). The framework is based on the observation that previous work solves both the grounding and translation steps by letting a language model iteratively predict tokens from its full vocabulary. In contrast, GraFT reduces the complexity of both tasks by restricting the set of valid output tokens from the full vocabulary to only a handful in each step. The solution space reduction is obtained by exploiting the unique properties of each problem. We also provide a theoretical justification for why the solution space reduction leads to more efficient learning. We evaluate the effectiveness of GraFT using the CW, GLTL, and Navi benchmarks. Compared with state-of-the-art translation approaches, it can be observed that GraFT improves the end-to-end translation accuracy by 5.49% and out-of-domain translation accuracy by 14.06% on average.

Theory · Online Learning and Bandits

Junze Deng, Qinhang Wu, Peizhong Ju, Sen Lin, Yingbin LIANG, Ness Shroff

Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside new data in current task. While such a concurrent rehearsal strategy is widely used, it remains unclear if this approach is always optimal. Inspired by human learning, where sequentially revisiting tasks helps mitigate forgetting, we explore whether sequential rehearsal can offer greater benefits for CL compared to standard concurrent rehearsal. To address this question, we conduct a theoretical analysis of rehearsal-based CL in overparameterized linear models, comparing two strategies: 1) Concurrent Rehearsal, where past and new data are trained together, and 2) Sequential Rehearsal, where new data is trained first, followed by revisiting past data sequentially. By explicitly characterizing forgetting and generalization error, we show that sequential rehearsal performs better when tasks are less similar. These insights further motivate a novel Hybrid Rehearsal method, which trains similar tasks concurrently and revisits dissimilar tasks sequentially. We characterize its forgetting and generalization performance, and our experiments with deep neural networks further confirm that the hybrid approach outperforms standard concurrent rehearsal. This work provides the first comprehensive theoretical analysis of rehearsal-based CL.

Probabilistic Methods

Jian-Feng Cai, Zhuozhi XIAN, Jiaxi Ying

We explore the single-spiked covariance model within the context of sparse principal component analysis (PCA), which aims to recover a sparse unit vector from noisy samples. From an information-theoretic perspective, $O(k \log p)$ observations are sufficient to recover a $k$-sparse $p$-dimensional vector $\mathbf{v}$. However, existing polynomial-time methods require at least $O(k^2)$ samples for successful recovery, highlighting a significant gap in sample efficiency. To bridge this gap, we introduce a novel thresholding-based algorithm that requires only $\Omega(k \log p)$ samples, provided the signal strength $\lambda = \Omega(||\mathbf{v}||_\infty^{-1})$. We also propose a two-stage nonconvex algorithm that further enhances estimation performance. This approach integrates our thresholding algorithm with truncated power iteration, achieving the minimax optimal rate of statistical error under the desired sample complexity. Numerical experiments validate the superior performance of our algorithms in terms of estimation accuracy and computational efficiency.

Optimization · Non-Convex

Yuanwei Zhang, Fengmiao Bian, Xiaoqun Zhang, Jian-Feng Cai

Tensors play a crucial role in numerous scientific and engineering fields. This paper addresses the low-multilinear-rank tensor completion problem, a fundamental task in tensor-related applications. By exploiting the manifold structure inherent to the fixed-multilinear-rank tensor set, we introduce a simple yet highly effective preconditioned Riemannian metric and propose the Preconditioned Riemannian Gradient Descent (PRGD) algorithm. Compared to the standard Riemannian Gradient Descent (RGD), PRGD achieves faster convergence while maintaining the same order of per-iteration computational complexity. Theoretically, we provide the recovery guarantee for PRGD under near-optimal sampling complexity. Numerical results highlight the efficiency of PRGD, outperforming state-of-the-art methods on both synthetic data and real-world video inpainting tasks.

Reinforcement Learning · Batch/Offline

Jihwan Jeong, Xiaoyu Wang, Jingmin Wang, Scott Sanner, Pascal Poupart

Offline reinforcement learning (RL) is crucial when online exploration is costly or unsafe but often struggles with high epistemic uncertainty due to limited data. Existing methods rely on fixed conservative policies, restricting adaptivity and generalization. To address this, we propose Reflect-then-Plan (RefPlan), a novel _doubly Bayesian_ offline model-based (MB) planning approach. RefPlan unifies uncertainty modeling and MB planning by recasting planning as Bayesian posterior estimation. At deployment, it updates a belief over environment dynamics using real-time observations, incorporating uncertainty into MB planning via marginalization. Empirical results on standard benchmarks show that RefPlan significantly improves the performance of conservative offline RL policies. In particular, RefPlan maintains robust performance under high epistemic uncertainty and limited data, while demonstrating resilience to changing environment dynamics, improving the flexibility, generalizability, and robustness of offline-learned policies.

General Machine Learning

Yingpeng Tang, Chao Ren, Xiaoli Tang, Sheng-Jun Huang, Lizhen Cui, Han Yu

Federated Active Learning (FAL) aims to learn an effective global model, while minimizing label queries. Owing to privacy requirements, it is challenging to design effective active data selection schemes due to the lack of cross-client query information. In this paper, we bridge this important gap by proposing the \underline{F}ederated \underline{A}ctive data selection by \underline{LE}verage score sampling (FALE) method. It is designed for regression tasks in the presence of non-i.i.d. client data to enable the server to select data globally in a privacy-preserving manner. Based on FedSVD, FALE aims to estimate the utility of unlabeled data and perform data selection via leverage score sampling. Besides, a secure model learning framework is designed for federated regression tasks to exploit supervision. FALE can operate without requiring an initial labeled set and select the instances in a single pass, significantly reducing communication overhead. Theoretical analyze establishes the query complexity for FALE to achieve constant factor approximation and relative error approximation. Extensive experiments on 11 benchmark datasets demonstrate significant improvements of FALE over existing state-of-the-art methods.

Deep Learning · Generative Models and Autoencoders

Zebin You, Jingyang Ou, Xiaolu Zhang, Jun Hu, JUN ZHOU, Chongxuan Li

Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key factors that contribute to both performance and efficiency. Based on the improvements observed during this exploration, we develop our model, referred to as \textbf{eMIGM}. Empirically, eMIGM demonstrates strong performance on ImageNet generation, as measured by Fréchet Inception Distance (FID). In particular, on ImageNet $256\times256$, with similar number of function evaluations (NFEs) and model parameters, eMIGM outperforms the seminal VAR. Moreover, as NFE and model parameters increase, eMIGM achieves performance comparable to the state-of-the-art continuous diffusion model REPA while requiring less than 45\% of the NFE. Additionally, on ImageNet $512\times512$, eMIGM outperforms the strong continuous diffusion model EDM2. Code is available at \url{https://github.com/ML-GSAI/eMIGM}.

Applications · Robotics

zhou changshi, Feng Luan, hujiarui, Shaoqiang Meng, Zhipeng Wang, Yanchao Dong, Yanmin Zhou, Bin He

Garment manipulation is a significant challenge for robots due to the complex dynamics and potential self-occlusion of garments. Most existing methods of efficient garment unfolding overlook the crucial role of standardization of flattened garments, which could significantly simplify downstream tasks like folding, ironing, and packing. This paper presents APS-Net, a novel approach to garment manipulation that combines unfolding and standardization in a unified framework. APS-Net employs a dual-arm, multi-primitive policy with dynamic fling to quickly unfold crumpled garments and pick-and-place(p&p) for precise alignment. The purpose of garment standardization during unfolding involves not only maximizing surface coverage but also aligning the garment’s shape and orientation to predefined requirements. To guide effective robot learning, we introduce a novel factorized reward function for standardization, which incorporates garment coverage (Cov), keypoint distance (KD), and intersection-over-union (IoU) metrics. Additionally, we introduce a spatial action mask and an Action Optimized Module to improve unfolding efficiency by selecting actions and operation points effectively. In simulation, APS-Net outperforms state-of-the-art methods for long sleeves, achieving 3.9% better coverage, 5.2% higher IoU, and a 0.14 decrease in KD (7.09% relative reduction). Real-world folding tasks further demonstrate that standardization simplifies the folding process. Project page: https://hellohaia.github.io/APS/

Optimization · Large Scale, Parallel and Distributed

Jiayuan Zhang, Xuefeng Liu, Jianwei Niu, Shaojie Tang, Haotian Yang, Xinghao Wu

The out-of-distribution (OOD) generalization problem in federated learning (FL) has recently attracted significant research interest. A common approach, derived from centralized learning, is to extract causal features which exhibit causal relationships with the label. However, in FL, the global feature extractor typically captures only invariant causal features shared across clients and thus discards many other causal features that are potentially useful for OOD generalization. To address this problem, we propose FedUni, a simple yet effective architecture trained to extract all possible causal features from any input. FedUni consists of a comprehensive feature extractor, designed to identify a union of all causal feature types in the input, followed by a feature compressor, which discards potential \textit{inactive} causal features. With this architecture, FedUni can benefit from collaborative training in FL while avoiding the cost of model aggregation (i.e., extracting only invariant features). In addition, to further enhance the feature extractor's ability to capture causal features, FedUni add a causal intervention module on the client side, which employs a counterfactual generator to generate counterfactual examples that simulate distributions shifts. Extensive experiments and theoretical analysis demonstrate that our method significantly improves OOD generalization performance.

Optimization

Qi He, Peiran Yu, Ziyi Chen, Heng Huang

Shuffling-type gradient methods are favored in practice for their simplicity and rapid empirical performance. Despite extensive development of convergence guarantees under various assumptions in recent years, most require the Lipschitz smoothness condition, which is often not met in common machine learning models. We highlight this issue with specific counterexamples. To address this gap, we revisit the convergence rates of shuffling-type gradient methods without assuming Lipschitz smoothness. Using our stepsize strategy, the shuffling-type gradient algorithm not only converges under weaker assumptions but also match the current best-known convergence rates, thereby broadening its applicability. We prove the convergence rates for nonconvex, strongly convex, and non-strongly convex cases, each under both random reshuffling and arbitrary shuffling schemes, under a general bounded variance condition. Numerical experiments further validate the performance of our shuffling-type gradient algorithm, underscoring its practical efficacy.