Yao Qin

Jindong Gu, Ahmad Beirami, Xuezhi Wang et al. · deepmind, oxford

With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the support set of the prompts? In this work, we first define two types of robustness to distribution shift on VLMs, namely, robustness on base classes (the classes included in the support set of prompts) and robustness on novel classes. Then, we study the robustness of existing in-context learning and prompt learning approaches, where we find that prompt learning performs robustly on test images from base classes, while it does not generalize well on images from novel classes. We propose robust prompt learning by integrating multiple-scale image features into the prompt, which improves both types of robustness. Comprehensive experiments are conducted to study the defined robustness on six benchmarks and show the effectiveness of our proposal.

Yuanxin Ye, Mengmeng Wang, Liang Zhou et al.

Deep learning-based change detection (CD) using remote sensing images has received increasing attention in recent years. However, how to effectively extract and fuse the deep features of bi-temporal images for improving the accuracy of CD is still a challenge. To address that, a novel adjacent-level feature fusion network with 3D convolution (named AFCF3D-Net) is proposed in this article. First, through the inner fusion property of 3D convolution, we design a new feature fusion way that can simultaneously extract and fuse the feature information from bi-temporal images. Then, to alleviate the semantic gap between low-level features and high-level features, we propose an adjacent-level feature cross-fusion (AFCF) module to aggregate complementary feature information between the adjacent levels. Furthermore, the full-scale skip connection strategy is introduced to improve the capability of pixel-wise prediction and the compactness of changed objects in the results. Finally, the proposed AFCF3D-Net has been validated on the three challenging remote sensing CD datasets: the Wuhan building dataset (WHU-CD), the LEVIR building dataset (LEVIR-CD), and the Sun Yat-Sen University dataset (SYSU-CD). The results of quantitative analysis and qualitative comparison demonstrate that the proposed AFCF3D-Net achieves better performance compared to other state-of-the-art methods. The code for this work is available at https://github.com/wm-Githuber/AFCF3D-Net.

Shuo Chen, Zhen Han, Bailan He et al.

Large Language Models (LLMs) with in-context learning (ICL) ability can quickly adapt to a specific context given a few demonstrations (demos). Recently, Multimodal Large Language Models (MLLMs) built upon LLMs have also shown multimodal ICL ability, i.e., responding to queries given a few multimodal demos, including images, queries, and answers. While ICL has been extensively studied on LLMs, its research on MLLMs remains limited. One essential question is whether these MLLMs can truly conduct multimodal ICL, or if only the textual modality is necessary. We investigate this question by examining two primary factors that influence ICL: 1) Demo content, i.e., understanding the influences of demo content in different modalities. 2) Demo selection strategy, i.e., how to select better multimodal demos for improved performance. Experiments revealed that multimodal ICL is predominantly driven by the textual content whereas the visual information in the demos has little influence. Interestingly, visual content is still necessary and useful for selecting demos to increase performance. Motivated by our analysis, we propose a simple yet effective approach, termed Mixed Modality In-Context Example Selection (MMICES), which considers both visual and language modalities when selecting demos. Extensive experiments are conducted to support our findings and verify the improvement brought by our method. Code is available at \url{https://chenxshuo.github.io/m-icl/}.

Shaila Niazi, Navid Anjum Aadit, Masoud Mohseni et al.

The slowing down of Moore's law has driven the development of unconventional computing paradigms, such as specialized Ising machines tailored to solve combinatorial optimization problems. In this paper, we show a new application domain for probabilistic bit (p-bit) based Ising machines by training deep generative AI models with them. Using sparse, asynchronous, and massively parallel Ising machines we train deep Boltzmann networks in a hybrid probabilistic-classical computing setup. We use the full MNIST and Fashion MNIST (FMNIST) dataset without any downsampling and a reduced version of CIFAR-10 dataset in hardware-aware network topologies implemented in moderately sized Field Programmable Gate Arrays (FPGA). For MNIST, our machine using only 4,264 nodes (p-bits) and about 30,000 parameters achieves the same classification accuracy (90%) as an optimized software-based restricted Boltzmann Machine (RBM) with approximately 3.25 million parameters. Similar results follow for FMNIST and CIFAR-10. Additionally, the sparse deep Boltzmann network can generate new handwritten digits and fashion products, a task the 3.25 million parameter RBM fails at despite achieving the same accuracy. Our hybrid computer takes a measured 50 to 64 billion probabilistic flips per second, which is at least an order of magnitude faster than superficially similar Graphics and Tensor Processing Unit (GPU/TPU) based implementations. The massively parallel architecture can comfortably perform the contrastive divergence algorithm (CD-n) with up to n = 10 million sweeps per update, beyond the capabilities of existing software implementations. These results demonstrate the potential of using Ising machines for traditionally hard-to-train deep generative Boltzmann networks, with further possible improvement in nanodevice-based realizations.

Zhouxing Shi, Nicholas Carlini, Ananth Balashankar et al.

"Effective robustness" measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as ImageNet to evaluate the ID accuracy. This becomes problematic when evaluating models trained on different data distributions, e.g., comparing models trained on ImageNet vs. zero-shot language-image pre-trained models trained on LAION. In this paper, we propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data. To do this, we control for the accuracy on multiple ID test sets that cover the training distributions for all the evaluated models. Our new evaluation metric provides a better estimate of effective robustness when there are models with different training data. It may also explain the surprising effective robustness gains of zero-shot CLIP-like models exhibited in prior works that used ImageNet as the only ID test set, while the gains diminish under our new evaluation. Additional artifacts including interactive visualizations are provided at https://shizhouxing.github.io/effective-robustness.

Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan et al.

A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can end up being far from the clean training data and what is the appropriate label is less clear. Despite this, most existing work simply uses one-hot labels for augmented data. In this paper, we show re-using one-hot labels for highly distorted data might run the risk of adding noise and degrading accuracy and calibration. To mitigate this, we propose a generic method AutoLabel to automatically learn the confidence in the labels for augmented data, based on the transformation distance between the clean distribution and augmented distribution. AutoLabel is built on label smoothing and is guided by the calibration-performance over a hold-out validation set. We successfully apply AutoLabel to three different data augmentation techniques: the state-of-the-art RandAug, AugMix, and adversarial training. Experiments on CIFAR-10, CIFAR-100 and ImageNet show that AutoLabel significantly improves existing data augmentation techniques over models' calibration and accuracy, especially under distributional shift.

Litian Liu, Yao Qin

Out-of-Distribution (OOD) detection is critical for safe deployment; however, existing detectors often struggle to generalize across datasets of varying scales and model architectures, and some can incur high computational costs in real-world applications. Inspired by the phenomenon of Neural Collapse, we propose a versatile and efficient OOD detection method. Specifically, we re-characterize prior observations that in-distribution (ID) samples form clusters, demonstrating that, with appropriate centering, these clusters align closely with model weight vectors. Additionally, we reveal that ID features tend to expand into a simplex Equiangular Tight Frame, explaining the common observation that ID features are situated farther from the origin than OOD features. Incorporating both insights from Neural Collapse, our OOD detector leverages feature proximity to weight vectors and complements this approach by using feature norms to effectively filter out OOD samples. Extensive experiments on off-the-shelf models demonstrate the robustness of our OOD detector across diverse scenarios, mitigating generalization discrepancies and enhancing overall performance, with inference latency comparable to that of the basic softmax-confidence detector. Code is available here: https://github.com/litianliu/NCI-OOD.

Jieyu Zhao, Xuezhi Wang, Yao Qin et al.

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the training scenario. There have been several approaches proposed to reduce model's reliance on these bias features which can improve model robustness in the out-of-distribution setting. However, existing methods usually use a fixed low-capacity model to deal with various bias features, which ignore the learnability of those features. In this paper, we analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases. We further show that by choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.

Ananth Balashankar, Xiao Ma, Aradhana Sinha et al.

As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well. If we have only observed a few examples of violations of a new safety rule, how can we build a classifier to detect violations? In this paper, we study the novel setting of domain-generalized few-shot learning for LLM-based text safety classifiers. Unlike prior few-shot work, these new safety issues can be hard to uncover and we do not get to choose the few examples. We demonstrate that existing few-shot techniques do not perform well in this setting, and rather we propose to do parameter-efficient fine-tuning (PEFT) combined with augmenting training data based on similar examples in prior existing rules. We empirically show that our approach of similarity-based data-augmentation + prompt-tuning (DAPT) consistently outperforms baselines that either do not rely on data augmentation or on PEFT by 7-17% F1 score in the Social Chemistry moral judgement and 9-13% AUC in the Toxicity detection tasks, even when the new rule is loosely correlated with existing ones.

Bhagyashree Puranik, Ahmad Beirami, Yao Qin et al.

State-of-the-art techniques for enhancing robustness of deep networks mostly rely on empirical risk minimization with suitable data augmentation. In this paper, we propose a complementary approach motivated by communication theory, aimed at enhancing the signal-to-noise ratio at the output of a neural network layer via neural competition during learning and inference. In addition to standard empirical risk minimization, neurons compete to sparsely represent layer inputs by maximization of a tilted exponential (TEXP) objective function for the layer. TEXP learning can be interpreted as maximum likelihood estimation of matched filters under a Gaussian model for data noise. Inference in a TEXP layer is accomplished by replacing batch norm by a tilted softmax, which can be interpreted as computation of posterior probabilities for the competing signaling hypotheses represented by each neuron. After providing insights via simplified models, we show, by experimentation on standard image datasets, that TEXP learning and inference enhances robustness against noise and other common corruptions, without requiring data augmentation. Further cumulative gains in robustness against this array of distortions can be obtained by appropriately combining TEXP with data augmentation techniques. The code for all our experiments is available at https://github.com/bhagyapuranik/texp_for_robustness.

Miriam K. Wolff, Peter Calhoun, Eleonora Maria Aiello et al.

Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D management datasets. Current datasets differ substantially in structure and are time-consuming to access and process, which impedes data integration and reduces the comparability and generalizability of algorithmic developments. This work aims to establish a unified and accessible data resource for T1D algorithm development. Multiple publicly available T1D datasets were consolidated into a unified resource, termed the MetaboNet dataset. Inclusion required the availability of both continuous glucose monitoring (CGM) data and corresponding insulin pump dosing records. Additionally, auxiliary information such as reported carbohydrate intake and physical activity was retained when present. The MetaboNet dataset comprises 3135 subjects and 1228 patient-years of overlapping CGM and insulin data, making it substantially larger than existing standalone benchmark datasets. The resource is distributed as a fully public subset available for immediate download at https://metabo-net.org/ , and with a Data Use Agreement (DUA)-restricted subset accessible through their respective application processes. For the datasets in the latter subset, processing pipelines are provided to automatically convert the data into the standardized MetaboNet format. A consolidated public dataset for T1D research is presented, and the access pathways for both its unrestricted and DUA-governed components are described. The resulting dataset covers a broad range of glycemic profiles and demographics and thus can yield more generalizable algorithmic performance than individual datasets.

Litian Liu, Yao Qin

Efficient and effective Out-of-Distribution (OOD) detection is essential for the safe deployment of AI systems. Existing feature space methods, while effective, often incur significant computational overhead due to their reliance on auxiliary models built from training features. In this paper, we propose a computationally-efficient OOD detector without using auxiliary models while still leveraging the rich information embedded in the feature space. Specifically, we detect OOD samples based on their feature distances to decision boundaries. To minimize computational cost, we introduce an efficient closed-form estimation, analytically proven to tightly lower bound the distance. Based on our estimation, we discover that In-Distribution (ID) features tend to be further from decision boundaries than OOD features. Additionally, ID and OOD samples are better separated when compared at equal deviation levels from the mean of training features. By regularizing the distances to decision boundaries based on feature deviation from the mean, we develop a hyperparameter-free, auxiliary model-free OOD detector. Our method matches or surpasses the effectiveness of state-of-the-art methods in extensive experiments while incurring negligible overhead in inference latency. Overall, our approach significantly improves the efficiency-effectiveness trade-off in OOD detection. Code is available at: https://github.com/litianliu/fDBD-OOD.

Kenan Tang, Jiasheng Guo, Jeffrey Lin et al.

Facial expressions of characters are a vital component of visual storytelling. While current AI image editing models hold promise for assisting artists in the task of stylized expression editing, these models introduce global noise and pixel drift into the edited image, preventing the integration of these models into professional image editing software and workflows. To bridge this gap, we introduce ExpressEdit, a fully open-source Photoshop plugin that is free from common artifacts of proprietary image editing models and robustly synergizes with native Photoshop operations such as Liquify. ExpressEdit seamlessly edits an expression within 3 seconds on a single consumer-grade GPU, significantly faster than popular proprietary models. Moreover, to support the generation of diverse expressions according to different narrative needs, we compile a comprehensive expression database of 135 expression tags enriched with example stories and images designed for retrieval-augmented generation. We open source the code and dataset to facilitate future research and artistic exploration.

Yao Qin, Yangyang Yan, Jinhua Pang et al.

The integration of Large Language Models (LLMs) into life sciences has catalyzed the development of "AI Scientists." However, translating these theoretical capabilities into deployment-ready research environments exposes profound infrastructural vulnerabilities. Current frameworks are bottlenecked by fragile JSON-based tool-calling protocols, easily disrupted execution sandboxes that lose graphical outputs, and rigid conversational interfaces inherently ill-suited for high-dimensional scientific data.We introduce BloClaw, a unified, multi-modal operating system designed for Artificial Intelligence for Science (AI4S). BloClaw reconstructs the Agent-Computer Interaction (ACI) paradigm through three architectural innovations: (1) An XML-Regex Dual-Track Routing Protocol that statistically eliminates serialization failures (0.2% error rate vs. 17.6% in JSON); (2) A Runtime State Interception Sandbox that utilizes Python monkey-patching to autonomously capture and compile dynamic data visualizations (Plotly/Matplotlib), circumventing browser CORS policies; and (3) A State-Driven Dynamic Viewport UI that morphs seamlessly between a minimalist command deck and an interactive spatial rendering engine. We comprehensively benchmark BloClaw across cheminformatics (RDKit), de novo 3D protein folding via ESMFold, molecular docking, and autonomous Retrieval-Augmented Generation (RAG), establishing a highly robust, self-evolving paradigm for computational research assistants. The open-source repository is available at https://github.com/qinheming/BloClaw.

Andong Hua, Mehak Preet Dhaliwal, Laya Pullela et al.

Accurate nutrition estimation helps people make informed dietary choices and is essential in the prevention of serious health complications. We present NutriBench, the first publicly available natural language meal description nutrition benchmark. NutriBench consists of 11,857 meal descriptions generated from real-world global dietary intake data. The data is human-verified and annotated with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. We conduct an extensive evaluation of NutriBench on the task of carbohydrate estimation, testing twelve leading Large Language Models (LLMs), including GPT-4o, Llama3.1, Qwen2, Gemma2, and OpenBioLLM models, using standard, Chain-of-Thought and Retrieval-Augmented Generation strategies. Additionally, we present a study involving professional nutritionists, finding that LLMs can provide comparable but significantly faster estimates. Finally, we perform a real-world risk assessment by simulating the effect of carbohydrate predictions on the blood glucose levels of individuals with diabetes. Our work highlights the opportunities and challenges of using LLMs for nutrition estimation, demonstrating their potential to aid professionals and laypersons and improve health outcomes. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html

Mehak Dhaliwal, Shashwat Chaurasia, Yao Qin et al.

Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of the interplay between training language coverage, model scale, and task domain, based on 220 supervised fine-tuning runs on parallel translated multilingual data mixtures spanning mathematical reasoning and API calling tasks, with models up to 8B parameters. We find that increasing language coverage during post-training is largely beneficial across tasks and model scales, with low-resource languages benefiting the most and high-resource languages plateauing rather than degrading. Even minimal multilinguality helps: incorporating a single non-English language improves both English performance and cross-lingual generalization, making English-only post-training largely suboptimal. Moreover, at sufficient language diversity, zero-shot cross-lingual transfer can match or exceed the effects of direct language inclusion in a low-diversity setting, although gains remain limited for typologically distant, low-resource languages.

Youngseok Yoon, Dainong Hu, Iain Weissburg et al.

Model collapse, the severe degradation of generative models when iteratively trained on their own outputs, has gained significant attention in recent years. This paper examines Chain of Diffusion, where a pretrained text-to-image diffusion model is finetuned on its own generated images. We demonstrate that severe image quality degradation was universal and identify CFG scale as the key factor impacting this model collapse. Drawing on an analogy between the Chain of Diffusion and biological evolution, we then introduce a novel theoretical analysis based on quantitative trait modeling from statistical genetics. Our theoretical analysis aligns with empirical observations of the generated images in the Chain of Diffusion. Finally, we propose Reusable Diffusion Finetuning (ReDiFine), a simple yet effective strategy inspired by genetic mutations. It operates robustly across various scenarios without requiring any hyperparameter tuning, making it a plug-and-play solution for reusable image generation.

Litian Liu, Reza Pourreza, Yubing Jian et al.

Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability. While existing hallucination detection methods achieve strong performance in question-answering tasks, they remain less effective on tasks requiring reasoning. In this work, we revisit hallucination detection through the lens of out-of-distribution (OOD) detection, a well-studied problem in areas like computer vision. Treating next-token prediction in language models as a classification task allows us to apply OOD techniques, provided appropriate modifications are made to account for the structural differences in large language models. We show that OOD-based approaches yield training-free, single-sample-based detectors, achieving strong accuracy in hallucination detection for reasoning tasks. Overall, our work suggests that reframing hallucination detection as OOD detection provides a promising and scalable pathway toward language model safety.

Kenan Tang, Yanhong Li, Yao Qin

Existing language learning tools, even those powered by Large Language Models (LLMs), often lack support for polyglot learners to build linguistic connections across vocabularies in multiple languages, provide limited customization for individual learning paces or needs, and suffer from detrimental cognitive offloading. To address these limitations, we design Do-It-Yourself Multilingual Knowledge Graph (DIY-MKG), an open-source system that supports polyglot language learning. DIY-MKG allows the user to build personalized vocabulary knowledge graphs, which are constructed by selective expansion with related words suggested by an LLM. The system further enhances learning through rich annotation capabilities and an adaptive review module that leverages LLMs for dynamic, personalized quiz generation. In addition, DIY-MKG allows users to flag incorrect quiz questions, simultaneously increasing user engagement and providing a feedback loop for prompt refinement. Our evaluation of LLM-based components in DIY-MKG shows that vocabulary expansion is reliable and fair across multiple languages, and that the generated quizzes are highly accurate, validating the robustness of DIY-MKG.

Andong Hua, Jindong Gu, Zhiyu Xue et al.

With the prevalence of the Pretraining-Finetuning paradigm in transfer learning, the robustness of downstream tasks has become a critical concern. In this work, we delve into adversarial robustness in transfer learning and reveal the critical role of initialization, including both the pretrained model and the linear head. First, we discover the necessity of an adversarially robust pretrained model. Specifically, we reveal that with a standard pretrained model, Parameter-Efficient Finetuning (PEFT) methods either fail to be adversarially robust or continue to exhibit significantly degraded adversarial robustness on downstream tasks, even with adversarial training during finetuning. Leveraging a robust pretrained model, surprisingly, we observe that a simple linear probing can outperform full finetuning and other PEFT methods with random initialization on certain datasets. We further identify that linear probing excels in preserving robustness from the robust pretraining. Based on this, we propose Robust Linear Initialization (RoLI) for adversarial finetuning, which initializes the linear head with the weights obtained by adversarial linear probing to maximally inherit the robustness from pretraining. Across five different image classification datasets, we demonstrate the effectiveness of RoLI and achieve new state-of-the-art results. Our code is available at \url{https://github.com/DongXzz/RoLI}.

Xinlu Zhang, Shiyang Li, Xianjun Yang et al.

Large language models (LLMs) demonstrate remarkable medical expertise, but data privacy concerns impede their direct use in healthcare environments. Although offering improved data privacy protection, domain-specific small language models (SLMs) often underperform LLMs, emphasizing the need for methods that reduce this performance gap while alleviating privacy concerns. In this paper, we present a simple yet effective method that harnesses LLMs' medical proficiency to boost SLM performance in medical tasks under privacy-restricted scenarios. Specifically, we mitigate patient privacy issues by extracting keywords from medical data and prompting the LLM to generate a medical knowledge-intensive context by simulating clinicians' thought processes. This context serves as additional input for SLMs, augmenting their decision-making capabilities. Our method significantly enhances performance in both few-shot and full training settings across three medical knowledge-intensive tasks, achieving up to a 22.57% increase in absolute accuracy compared to SLM fine-tuning without context, and sets new state-of-the-art results in two medical tasks within privacy-restricted scenarios. Further out-of-domain testing and experiments in two general domain datasets showcase its generalizability and broad applicability. Our code can be found at https://github.com/XZhang97666/PrivacyBoost-SLM.

Kenan Tang, Praveen Arunshankar, Andong Hua et al.

The multi-step, iterative image editing capabilities of multi-modal agentic systems have transformed digital content creation. Although latest image editing models faithfully follow instructions and generate high-quality images in single-turn edits, we identify a critical weakness in multi-turn editing, which is the iterative degradation of image quality. As images are repeatedly edited, minor artifacts accumulate, rapidly leading to a severe accumulation of visible noise and a failure to follow simple editing instructions. To systematically study these failures, we introduce Banana100, a comprehensive dataset of 28,000 degraded images generated through 100 iterative editing steps, including diverse textures and image content. Alarmingly, image quality evaluators fail to detect the degradation. Among 21 popular no-reference image quality assessment (NR-IQA) metrics, none of them consistently assign lower scores to heavily degraded images than to clean ones. The dual failures of generators and evaluators may threaten the stability of future model training and the safety of deployed agentic systems, if the low-quality synthetic data generated by multi-turn edits escape quality filters. We release the full code and data to facilitate the development of more robust models, helping to mitigate the fragility of multi-modal agentic systems.

Litian Liu, Reza Pourreza, Sunny Panchal et al.

Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked hallucinations to model uncertainty, suggesting that hallucinations can be detected by measuring dispersion over answer distributions obtained from a set of samples drawn from a model. While drawing from the distribution over tokens defined by the model is a natural way to obtain samples, in this work, we argue that it is sub-optimal for the purpose of detecting hallucinations. We show that detection can be improved significantly by taking into account model uncertainty in the Bayesian sense. To this end, we propose a very simple and efficient approach that perturbs an appropriate subset of model parameters, or equivalently hidden unit activations, during sampling. We demonstrate its effectiveness across a wide range of datasets and model architectures.

Zhenshuai Liu, Yitong Li, Zirui Wang et al.

There has been widespread global increasing use of renewable energy sources, which are usually connected to the electricity grids via power electronic inverters. Traditionally, these inverter-based resources operate in either grid-forming (GFM) or grid-following (GFL) mode. But more recently, the need of switching between these two modes are glowingly required because of the complex operation scenarios of systems such as source-side limitations, grid-side services, fault disturbances, etc. However, due to the differences between GFM and GFL modes, a direct switching between them would lead to large oscillations or even instability of inverters. Therefore, in this paper, a method called state mapping method for analyzing the switching transient and designing the switching control is proposed. Based on this method, an ideally-smooth transition between GFM and GFL can be achieved. The effectiveness of the proposed method is verified by both the theoretical analysis and experiment tests.

Yicheng Tao, Yao Qin, Yepang Liu

Recent advancements in large language models (LLMs) have substantially improved automated code generation. While function-level and file-level generation have achieved promising results, real-world software development typically requires reasoning across entire repositories. This gives rise to the challenging task of Repository-Level Code Generation (RLCG), where models must capture long-range dependencies, ensure global semantic consistency, and generate coherent code spanning multiple files or modules. To address these challenges, Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm that integrates external retrieval mechanisms with LLMs, enhancing context-awareness and scalability. In this survey, we provide a comprehensive review of research on Retrieval-Augmented Code Generation (RACG), with an emphasis on repository-level approaches. We categorize existing work along several dimensions, including generation strategies, retrieval modalities, model architectures, training paradigms, and evaluation protocols. Furthermore, we summarize widely used datasets and benchmarks, analyze current limitations, and outline key challenges and opportunities for future research. Our goal is to establish a unified analytical framework for understanding this rapidly evolving field and to inspire continued progress in AI-powered software engineering.

Andong Hua, Kenan Tang, Chenhe Gu et al.

Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a core limitation of LLMs. In this work, we revisit this issue and ask: Is the widely reported high prompt sensitivity truly an inherent weakness of LLMs, or is it largely an artifact of evaluation processes? To answer this question, we systematically evaluate 7 LLMs (e.g., GPT and Gemini family) across 6 benchmarks, including both multiple-choice and open-ended tasks on 12 diverse prompt templates. We find that much of the prompt sensitivity stems from heuristic evaluation methods, including log-likelihood scoring and rigid answer matching, which often overlook semantically correct responses expressed through alternative phrasings, such as synonyms or paraphrases. When we adopt LLM-as-a-Judge evaluations, we observe a substantial reduction in performance variance and a consistently higher correlation in model rankings across prompts. Our findings suggest that modern LLMs are more robust to prompt templates than previously believed, and that prompt sensitivity may be more an artifact of evaluation than a flaw in the models.

Chenruo Liu, Kenan Tang, Yao Qin et al.

This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages fundamental integration between distribution shift and AI safety research.

Chenhe Gu, Jindong Gu, Andong Hua et al.

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of these attacks across different models remains limited, especially under targeted attack setting. Existing methods primarily focus on vision-specific perturbations but struggle with the complex nature of vision-language modality alignment. In this work, we introduce the Dynamic Vision-Language Alignment (DynVLA) Attack, a novel approach that injects dynamic perturbations into the vision-language connector to enhance generalization across diverse vision-language alignment of different models. Our experimental results show that DynVLA significantly improves the transferability of adversarial examples across various MLLMs, including BLIP2, InstructBLIP, MiniGPT4, LLaVA, and closed-source models such as Gemini.

Yao Qin, Yangyang Yan, YuanChao Yang et al.

Deep learning models have achieved remarkable success in medical image analysis but are fundamentally constrained by the requirement for large-scale, meticulously annotated datasets. This dependency on "big data" is a critical bottleneck in the medical domain, where patient data is inherently difficult to acquire and expert annotation is expensive, particularly for rare diseases where samples are scarce by definition. To overcome this fundamental challenge, we propose a novel paradigm: Zero-Training Task-Specific Model Synthesis (ZS-TMS). Instead of adapting a pre-existing model or training a new one, our approach leverages a large-scale, pre-trained generative engine to directly synthesize the entire set of parameters for a task-specific classifier. Our framework, the Semantic-Guided Parameter Synthesizer (SGPS), takes as input minimal, multi-modal task information as little as a single example image (1-shot) and a corresponding clinical text description to directly synthesize the entire set of parameters for a task-specific classifier. The generative engine interprets these inputs to generate the weights for a lightweight, efficient classifier (e.g., an EfficientNet-V2), which can be deployed for inference immediately without any task-specific training or fine-tuning. We conduct extensive evaluations on challenging few-shot classification benchmarks derived from the ISIC 2018 skin lesion dataset and a custom rare disease dataset. Our results demonstrate that SGPS establishes a new state-of-the-art, significantly outperforming advanced few-shot and zero-shot learning methods, especially in the ultra-low data regimes of 1-shot and 5-shot classification. This work paves the way for the rapid development and deployment of AI-powered diagnostic tools, particularly for the long tail of rare diseases where data is critically limited.

Kenan Tang, Yanhong Li, Yao Qin

Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality often deteriorates immediately after a single editing step. To address these challenges, we introduce SPICE, a training-free workflow that accepts arbitrary resolutions and aspect ratios, accurately follows user requirements, and consistently improves image quality during more than 100 editing steps, while keeping the unedited regions intact. By synergizing the strengths of a base diffusion model and a Canny edge ControlNet model, SPICE robustly handles free-form editing instructions from the user. On a challenging realistic image-editing dataset, SPICE quantitatively outperforms state-of-the-art baselines and is consistently preferred by human annotators. We release the workflow implementation for popular diffusion model Web UIs to support further research and artistic exploration.

Youngseok Yoon, Sangwoo Hong, Hyungjun Joo et al.

Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the problem by i) adjusting a loss function, ii) decoupling classifier learning, or iii) proposing a new multi-head architecture called experts. In this paper, we tackle the problem from a different perspective to augment a training dataset to enhance the sample diversity of minority classes. Specifically, our method, namely Confusion-Pairing Mixup (CP-Mix), estimates the confusion distribution of the model and handles the data deficiency problem by augmenting samples from confusion pairs in real-time. In this way, CP-Mix trains the model to mitigate its weakness and distinguish a pair of classes it frequently misclassifies. In addition, CP-Mix utilizes a novel mixup formulation to handle the bias in decision boundaries that originated from the imbalanced dataset. Extensive experiments demonstrate that CP-Mix outperforms existing methods for long-tailed image recognition and successfully relieves the confusion of the classifier.

Zhiyu Xue, Haohan Wang, Yao Qin et al.

Adversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure. To obtain an accurate and robust model, the weighted-average method is applied to optimize standard loss and adversarial loss simultaneously. In this paper, we argue that the weighted-average method does not provide the best tradeoff for the standard performance and adversarial robustness. We argue that the failure of the weighted-average method is due to the conflict between the gradients derived from standard and adversarial loss, and further demonstrate such a conflict increases with attack budget theoretically and practically. To alleviate this problem, we propose a new trade-off paradigm for adversarial training with a conflict-aware factor for the convex combination of standard and adversarial loss, named \textbf{Conflict-Aware Adversarial Training~(CA-AT)}. Comprehensive experimental results show that CA-AT consistently offers a superior trade-off between standard performance and adversarial robustness under the settings of adversarial training from scratch and parameter-efficient finetuning.

Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha et al.

Safety classifiers are critical in mitigating toxicity on online forums such as social media and in chatbots. Still, they continue to be vulnerable to emergent, and often innumerable, adversarial attacks. Traditional automated adversarial data generation methods, however, tend to produce attacks that are not diverse, but variations of previously observed harm types. We formalize the task of automated adversarial discovery for safety classifiers - to find new attacks along previously unseen harm dimensions that expose new weaknesses in the classifier. We measure progress on this task along two key axes (1) adversarial success: does the attack fool the classifier? and (2) dimensional diversity: does the attack represent a previously unseen harm type? Our evaluation of existing attack generation methods on the CivilComments toxicity task reveals their limitations: Word perturbation attacks fail to fool classifiers, while prompt-based LLM attacks have more adversarial success, but lack dimensional diversity. Even our best-performing prompt-based method finds new successful attacks on unseen harm dimensions of attacks only 5\% of the time. Automatically finding new harmful dimensions of attack is crucial and there is substantial headroom for future research on our new task.

Meng Song, Xuezhi Wang, Tanay Biradar et al.

Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstrations, as a way of task specification, can capture rich information that may be hard to specify by language, it remains unclear what information is extracted from the demonstrations to help generalization. Moreover, assuming access to demonstrations of an unseen task is impractical or unreasonable in many real-world scenarios, especially in robotics applications. These questions motivate us to explore what the minimally sufficient prompt could be to elicit the same level of generalization ability as the demonstrations. We study this problem in the contextural RL setting which allows for quantitative measurement of generalization and is commonly adopted by meta-RL and multi-task RL benchmarks. In this setting, the training and test Markov Decision Processes (MDPs) only differ in certain properties, which we refer to as task parameters. We show that conditioning a decision transformer on these task parameters alone can enable zero-shot generalization on par with or better than its demonstration-conditioned counterpart. This suggests that task parameters are essential for the generalization and DT models are trying to recover it from the demonstration prompt. To extract the remaining generalizable information from the supervision, we introduce an additional learnable prompt which is demonstrated to further boost zero-shot generalization across a range of robotic control, manipulation, and navigation benchmark tasks.

Jindong Gu, Zhen Han, Shuo Chen et al.

Prompt engineering is a technique that involves augmenting a large pre-trained model with task-specific hints, known as prompts, to adapt the model to new tasks. Prompts can be created manually as natural language instructions or generated automatically as either natural language instructions or vector representations. Prompt engineering enables the ability to perform predictions based solely on prompts without updating model parameters, and the easier application of large pre-trained models in real-world tasks. In past years, Prompt engineering has been well-studied in natural language processing. Recently, it has also been intensively studied in vision-language modeling. However, there is currently a lack of a systematic overview of prompt engineering on pre-trained vision-language models. This paper aims to provide a comprehensive survey of cutting-edge research in prompt engineering on three types of vision-language models: multimodal-to-text generation models (e.g. Flamingo), image-text matching models (e.g. CLIP), and text-to-image generation models (e.g. Stable Diffusion). For each type of model, a brief model summary, prompting methods, prompting-based applications, and the corresponding responsibility and integrity issues are summarized and discussed. Furthermore, the commonalities and differences between prompting on vision-language models, language models, and vision models are also discussed. The challenges, future directions, and research opportunities are summarized to foster future research on this topic.

Ananth Balashankar, Xuezhi Wang, Yao Qin et al.

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with minimal human labeling cost. Most existing methods either completely rely on human-annotated labels, an expensive process which limits the scale of counterfactual data, or implicitly assume label invariance, which may mislead the model with incorrect labels. In this paper, we present a novel framework that utilizes counterfactual generative models to generate a large number of diverse counterfactuals by actively sampling from regions of uncertainty, and then automatically label them with a learned pairwise classifier. Our key insight is that we can more correctly label the generated counterfactuals by training a pairwise classifier that interpolates the relationship between the original example and the counterfactual. We demonstrate that with a small amount of human-annotated counterfactual data (10%), we can generate a counterfactual augmentation dataset with learned labels, that provides an 18-20% improvement in robustness and a 14-21% reduction in errors on 6 out-of-domain datasets, comparable to that of a fully human-annotated counterfactual dataset for both sentiment classification and question paraphrase tasks.

Jindong Gu, Volker Tresp, Yao Qin

Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a sequence of image patches. The patch-based input image representation makes the following question interesting: How does ViT perform when individual input image patches are perturbed with natural corruptions or adversarial perturbations, compared to CNNs? In this work, we study the robustness of ViT to patch-wise perturbations. Surprisingly, we find that ViTs are more robust to naturally corrupted patches than CNNs, whereas they are more vulnerable to adversarial patches. Furthermore, we discover that the attention mechanism greatly affects the robustness of vision transformers. Specifically, the attention module can help improve the robustness of ViT by effectively ignoring natural corrupted patches. However, when ViTs are attacked by an adversary, the attention mechanism can be easily fooled to focus more on the adversarially perturbed patches and cause a mistake. Based on our analysis, we propose a simple temperature-scaling based method to improve the robustness of ViT against adversarial patches. Extensive qualitative and quantitative experiments are performed to support our findings, understanding, and improvement of ViT robustness to patch-wise perturbations across a set of transformer-based architectures.

Yao Qin, Chiyuan Zhang, Ting Chen et al.

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to patch-based transformations, even when the transformation largely destroys the original semantics and makes the image unrecognizable by humans. This indicates that ViTs heavily use features that survived such transformations but are generally not indicative of the semantic class to humans. Further investigations show that these features are useful but non-robust, as ViTs trained on them can achieve high in-distribution accuracy, but break down under distribution shifts. From this understanding, we ask: can training the model to rely less on these features improve ViT robustness and out-of-distribution performance? We use the images transformed with our patch-based operations as negatively augmented views and offer losses to regularize the training away from using non-robust features. This is a complementary view to existing research that mostly focuses on augmenting inputs with semantic-preserving transformations to enforce models' invariance. We show that patch-based negative augmentation consistently improves robustness of ViTs across a wide set of ImageNet based robustness benchmarks. Furthermore, we find our patch-based negative augmentation are complementary to traditional (positive) data augmentation, and together boost the performance further.

Junzheng Wu, Biao Li, Yao Qin et al.

Change detection (CD) in remote sensing images has been an ever-expanding area of research. To date, although many methods have been proposed using various techniques, accurately identifying changes is still a great challenge, especially in the high resolution or heterogeneous situations, due to the difficulties in effectively modeling the features from ground objects with different patterns. In this paper, a novel CD method based on the graph convolutional network (GCN) and multiscale object-based technique is proposed for both homogeneous and heterogeneous images. First, the object-wise high level features are obtained through a pre-trained U-net and the multiscale segmentations. Treating each parcel as a node, the graph representations can be formed and then, fed into the proposed multiscale graph convolutional network with each channel corresponding to one scale. The multiscale GCN propagates the label information from a small number of labeled nodes to the other ones which are unlabeled. Further, to comprehensively incorporate the information from the output channels of multiscale GCN, a fusion strategy is designed using the father-child relationships between scales. Extensive Experiments on optical, SAR and heterogeneous optical/SAR data sets demonstrate that the proposed method outperforms some state-of the-art methods in both qualitative and quantitative evaluations. Besides, the Influences of some factors are also discussed.

Tianlu Wang, Xuezhi Wang, Yao Qin et al.

NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that are known to be invariant to task labels. For example, in order to attack a model for sentiment classification over product reviews, we can use the product categories as the controllable attribute which would not change the sentiment of the reviews. Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches. We further use our generated adversarial examples to improve models through adversarial training, and we demonstrate that our generated attacks are more robust against model re-training and different model architectures.

Yao Qin, Xuezhi Wang, Alex Beutel et al.

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions, i.e., the predicted probability is not a good indicator of how much we should trust our model. In this paper, we study the connection between adversarial robustness and calibration and find that the inputs for which the model is sensitive to small perturbations (are easily attacked) are more likely to have poorly calibrated predictions. Based on this insight, we examine if calibration can be improved by addressing those adversarially unrobust inputs. To this end, we propose Adversarial Robustness based Adaptive Label Smoothing (AR-AdaLS) that integrates the correlations of adversarial robustness and calibration into training by adaptively softening labels for an example based on how easily it can be attacked by an adversary. We find that our method, taking the adversarial robustness of the in-distribution data into consideration, leads to better calibration over the model even under distributional shifts. In addition, AR-AdaLS can also be applied to an ensemble model to further improve model calibration.

Yao Qin, Nicholas Frosst, Colin Raffel et al.

There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks by causing the attacker to produce an input that semantically resembles the attack's target class. To this end, we first propose a stronger defense based on Capsule Networks that combines three detection mechanisms to achieve state-of-the-art detection performance on both standard and defense-aware attacks. We then show that undetected attacks against our defense often perceptually resemble the adversarial target class by performing a human study where participants are asked to label images produced by the attack. These attack images can no longer be called "adversarial'' because our network classifies them the same way as humans do.

Yao Qin, Nicholas Frosst, Sara Sabour et al.

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional reconstruction of the input. To specifically attack our detection mechanism, we propose the Reconstructive Attack which seeks both to cause a misclassification and a low reconstruction error. This reconstructive attack produces undetected adversarial examples but with much smaller success rate. Among all these attacks, we find that CapsNets always perform better than convolutional networks. Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class. Additionally, the resulting perturbations can cause the input image to appear visually more like the target class and hence become non-adversarial. This suggests that CapsNets use features that are more aligned with human perception and have the potential to address the central issue raised by adversarial examples.

Yao Qin, Nicholas Carlini, Ian Goodfellow et al.

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in the physical world. In contrast, current targeted adversarial examples applied to speech recognition systems have neither of these properties: humans can easily identify the adversarial perturbations, and they are not effective when played over-the-air. This paper makes advances on both of these fronts. First, we develop effectively imperceptible audio adversarial examples (verified through a human study) by leveraging the psychoacoustic principle of auditory masking, while retaining 100% targeted success rate on arbitrary full-sentence targets. Next, we make progress towards physical-world over-the-air audio adversarial examples by constructing perturbations which remain effective even after applying realistic simulated environmental distortions.

Yao Qin, Lorenzo Bruzzone, Biao Li

This paper presents a tensor alignment (TA) based domain adaptation method for hyperspectral image (HSI) classification. To be specific, HSIs in both domains are first segmented into superpixels and tensors of both domains are constructed to include neighboring samples from single superpixel. Then we consider the subspace invariance between two domains as projection matrices and original tensors are projected as core tensors with lower dimensions into the invariant tensor subspace by applying Tucker decomposition. To preserve geometric information in original tensors, we employ a manifold regularization term for core tensors into the decomposition progress. The projection matrices and core tensors are solved in an alternating optimization manner and the convergence of TA algorithm is analyzed. In addition, a post-processing strategy is defined via pure samples extraction for each superpixel to further improve classification performance. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art subspace learning methods when a limited amount of source labeled samples are available.

Yao Qin, Lorenzo Bruzzone, Biao Li et al.

This paper introduces a novel heterogenous domain adaptation (HDA) method for hyperspectral image classification with a limited amount of labeled samples in both domains. The method is achieved in the way of cross-domain collaborative learning (CDCL), which is addressed via cluster canonical correlation analysis (C-CCA) and random walker (RW) algorithms. To be specific, the proposed CDCL method is an iterative process of three main stages, i.e. twice of RW-based pseudolabeling and cross domain learning via C-CCA. Firstly, given the initially labeled target samples as training set ($\mathbf{TS}$), the RW-based pseudolabeling is employed to update $\mathbf{TS}$ and extract target clusters ($\mathbf{TCs}$) by fusing the segmentation results obtained by RW and extended RW (ERW) classifiers. Secondly, cross domain learning via C-CCA is applied using labeled source samples and $\mathbf{TCs}$. The unlabeled target samples are then classified with the estimated probability maps using the model trained in the projected correlation subspace. Thirdly, both $\mathbf{TS}$ and estimated probability maps are used for updating $\mathbf{TS}$ again via RW-based pseudolabeling. When the iterative process finishes, the result obtained by the ERW classifier using the final $\mathbf{TS}$ and estimated probability maps is regarded as the final classification map. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art HDA and ERW methods.

Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha et al.

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive field based on the processed context to generate more powerful features. This is achieved by parallelising multiple convolutional layers with different dilation rates, combined by an attention mechanism that learns to focus on the optimal scales driven by context. By sharing the weights of the parallel convolutions we make the network scale-invariant, with only a modest increase in the number of parameters. The proposed autofocus layer can be easily integrated into existing networks to improve a model's representational power. We evaluate our models on the challenging tasks of multi-organ segmentation in pelvic CT and brain tumor segmentation in MRI and achieve very promising performance.

Yao Qin, Mengyang Feng, Huchuan Lu et al.

Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA) -- a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism, Single-layer Cellular Automata can exploit the intrinsic relevance of similar regions through interactions with neighbors. Low-level image features as well as high-level semantic information extracted from deep neural networks are incorporated into the SCA to measure the correlation between different image patches. With these hierarchical deep features, an impact factor matrix and a coherence matrix are constructed to balance the influences on each cell's next state. The saliency values of all cells are iteratively updated according to a well-defined update rule. Furthermore, we propose CCA to integrate multiple saliency maps generated by SCA at different scales in a Bayesian framework. Therefore, single-layer propagation and multi-layer integration are jointly modeled in our unified HCA. Surprisingly, we find that the SCA can improve all existing methods that we applied it to, resulting in a similar precision level regardless of the original results. The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results. Extensive experiments on four challenging datasets demonstrate that the proposed algorithm outperforms state-of-the-art conventional methods and is competitive with deep learning based approaches.

Yao Qin, Dongjin Song, Haifeng Chen et al.

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them can capture the long-term temporal dependencies appropriately and select the relevant driving series to make predictions. In this paper, we propose a dual-stage attention-based recurrent neural network (DA-RNN) to address these two issues. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a.k.a., input features) at each time step by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all time steps. With this dual-stage attention scheme, our model can not only make predictions effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that the DA-RNN can outperform state-of-the-art methods for time series prediction.