Search

Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the fidelity of the generated images remains suboptimal. In this study, we reevaluate and streamline this framework by hypothesizing that text-to-image DiTs inherently possess in-context generation capabilities, requiring only minimal tuning to activate them. Through diverse task experiments, we qualitatively demonstrate that existing text-to-image DiTs can effectively perform in-context generation without any tuning. Building on this insight, we propose a remarkably simple pipeline to leverage the in-context abilities of DiTs: (1) concatenate images instead of tokens, (2) perform joint captioning of multiple images, and (3) apply task-specific LoRA tuning using small datasets (e.g., 20~100 samples) instead of full-parameter tuning with large datasets. We name our models In-Context LoRA (IC-LoRA). This approach requires no modifications to the original DiT models, only changes to the training data. Remarkably, our pipeline generates high-fidelity image sets that better adhere to prompts. While task-specific in terms of tuning data, our framework remains task-agnostic in architecture and pipeline, offering a powerful tool for the community and providing valuable insights for further research on product-level task-agnostic generation systems. We release our code, data, and models at https://github.com/ali-vilab/In-Context-LoRA, Comment: Tech report. Project page: https://ali-vilab.github.io/In-Context-LoRA-Page/

While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem. In this approach, a set of related images is generated simultaneously, optionally conditioned on a subset of the group. GDTs build upon diffusion transformers with minimal architectural modifications by concatenating self-attention tokens across images. This allows the model to implicitly capture cross-image relationships (e.g., identities, styles, layouts, surroundings, and color schemes) through caption-based correlations. Our design enables scalable, unsupervised, and task-agnostic pretraining using extensive collections of image groups sourced from multimodal internet articles, image galleries, and video frames. We evaluate GDTs on a comprehensive benchmark featuring over 200 instructions across 30 distinct visual generation tasks, including picture book creation, font design, style transfer, sketching, colorization, drawing sequence generation, and character customization. Our models achieve competitive zero-shot performance without any additional fine-tuning or gradient updates. Furthermore, ablation studies confirm the effectiveness of key components such as data scaling, group size, and model design. These results demonstrate the potential of GDTs as scalable, general-purpose visual generation systems.

Situational visual impairments (SVIs) significantly impact mobile readability, causing user discomfort and hindering information access. This paper introduces SituFont, a novel just-in-time adaptive intervention (JITAI) system designed to enhance mobile text readability by semi-automatically adjusting font parameters in response to real-time contextual changes. Leveraging smartphone sensors and a human-in-the-loop approach, SituFont personalizes the reading experience by adapting to individual user preferences, including personal factors such as fatigue and distraction level, and environmental factors like lighting, motion, and location. To inform the design of SituFont, we conducted formative interviews (N=15) to identify key SVI factors affecting readability and controlled experiments (N=18) to quantify the relationship between these factors and optimal text parameters. We then evaluated SituFont's effectiveness through a comparative user study under eight simulated SVI scenarios (N=12), demonstrating its ability to overcome SVIs. Our findings highlight the potential of JITAI systems like SituFont to mitigate the impact of SVIs and enhance mobile accessibility.

The increasing complexity of deep learning models used for calculating user representations presents significant challenges, particularly with limited computational resources and strict service-level agreements (SLAs). Previous research efforts have focused on optimizing model inference but have overlooked a critical question: is it necessary to perform user model inference for every ad request in large-scale social networks? To address this question and these challenges, we first analyze user access patterns at Meta and find that most user model inferences occur within a short timeframe. T his observation reveals a triangular relationship among model complexity, embedding freshness, and service SLAs. Building on this insight, we designed, implemented, and evaluated ERCache, an efficient and robust caching framework for large-scale user representations in ads recommendation systems on social networks. ERCache categorizes cache into direct and failover types and applies customized settings and eviction policies for each model, effectively balancing model complexity, embedding freshness, and service SLAs, even considering the staleness introduced by caching. ERCache has been deployed at Meta for over six months, supporting more than 30 ranking models while efficiently conserving computational resources and complying with service SLA requirements.

Recent advances in generative AI technologies like large language models have boosted the incorporation of AI assistance in writing workflows, leading to the rise of a new paradigm of human-AI co-creation in writing. To understand how people perceive writings that are produced under this paradigm, in this paper, we conduct an experimental study to understand whether and how the disclosure of the level and type of AI assistance in the writing process would affect people's perceptions of the writing on various aspects, including their evaluation on the quality of the writing and their ranking of different writings. Our results suggest that disclosing the AI assistance in the writing process, especially if AI has provided assistance in generating new content, decreases the average quality ratings for both argumentative essays and creative stories. This decrease in the average quality ratings often comes with an increased level of variations in different individuals' quality evaluations of the same writing. Indeed, factors such as an individual's writing confidence and familiarity with AI writing assistants are shown to moderate the impact of AI assistance disclosure on their writing quality evaluations. We also find that disclosing the use of AI assistance may significantly reduce the proportion of writings produced with AI's content generation assistance among the top-ranked writings., Comment: EMNLP 2024. arXiv admin note: text overlap with arXiv:2403.12004

The data scarcity problem is a crucial factor that hampers the model performance of IMU-based human motion capture. However, effective data augmentation for IMU-based motion capture is challenging, since it has to capture the physical relations and constraints of the human body, while maintaining the data distribution and quality. We propose PoseAugment, a novel pipeline incorporating VAE-based pose generation and physical optimization. Given a pose sequence, the VAE module generates infinite poses with both high fidelity and diversity, while keeping the data distribution. The physical module optimizes poses to satisfy physical constraints with minimal motion restrictions. High-quality IMU data are then synthesized from the augmented poses for training motion capture models. Experiments show that PoseAugment outperforms previous data augmentation and pose generation methods in terms of motion capture accuracy, revealing a strong potential of our method to alleviate the data collection burden for IMU-based motion capture and related tasks driven by human poses., Comment: Accepted to ECCV 2024. Code: https://github.com/CaveSpiderLZJ/PoseAugment-ECCV2024

Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches.

Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional training practices, as discrete expert routing hinders standard backpropagation and thus gradient-based optimization, which are the cornerstone of deep learning. To better pursue the scaling power of MoE, we introduce GRIN (GRadient-INformed MoE training), which incorporates sparse gradient estimation for expert routing and configures model parallelism to avoid token dropping. Applying GRIN to autoregressive language modeling, we develop a top-2 16$\times$3.8B MoE model. Our model, with only 6.6B activated parameters, outperforms a 7B dense model and matches the performance of a 14B dense model trained on the same data. Extensive evaluations across diverse tasks demonstrate the potential of GRIN to significantly enhance MoE efficacy, achieving 79.4 on MMLU, 83.7 on HellaSwag, 74.4 on HumanEval, and 58.9 on MATH., Comment: 58 pages

We present CasualGaze, a novel eye-gaze-based target selection technique to support natural and casual eye-gaze input. Unlike existing solutions that require users to keep the eye-gaze center on the target actively, CasualGaze allows users to glance at the target object to complete the selection simply. To understand casual gaze behavior, we studied the spatial distribution of casual gaze for different layouts and user behavior in a simulated real-world environment. Results revealed the impacts of object parameters, the speed and randomness features of casual gaze, and special gaze behavior patterns in "blurred areas". Based on the results, we devised CasualGaze algorithms, employing a bivariate Gaussian distribution model along with temporal compensation and voting algorithms for robust target prediction. Usability evaluation study showed significant improvements in recognition and selection speed for CasualGaze compared with two baseline techniques. Subjective ratings and comments further supported the preference for CasualGaze regarding efficiency, accuracy, and stability.

A long-standing challenge in end-user programming (EUP) is to trade off between natural user expression and the complexity of programming tasks. As large language models (LLMs) are empowered to handle semantic inference and natural language understanding, it remains under-explored how such capabilities can facilitate end-users to configure complex automation more naturally and easily. We propose AwareAuto, an EUP system that standardizes user expression and finishes two-step inference with the LLMs to achieve automation generation. AwareAuto allows contextual, multi-modality, and flexible user expression to configure complex automation tasks (e.g., dynamic parameters, multiple conditional branches, and temporal constraints), which are non-manageable in traditional EUP solutions. By studying realistic, complex rules data, AwareAuto gains 91.7% accuracy in matching user intentions and feasibility. We introduced user interaction to ensure system controllability and usability. We discuss the opportunities and challenges of incorporating LLMs in end-user programming techniques and grounding complex smart home contexts.

Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle to cope with small-scale or class-imbalanced video datasets. This leads to inconsistent segmentation results across frames. To address these issues, we propose a training strategy Masked Video Consistency, which enhances spatial and temporal feature aggregation. MVC introduces a training strategy that randomly masks image patches, compelling the network to predict the entire semantic segmentation, thus improving contextual information integration. Additionally, we introduce Object Masked Attention (OMA) to optimize the cross-attention mechanism by reducing the impact of irrelevant queries, thereby enhancing temporal modeling capabilities. Our approach, integrated into the latest decoupled universal video segmentation framework, achieves state-of-the-art performance across five datasets for three video segmentation tasks, demonstrating significant improvements over previous methods without increasing model parameters.

Message passing neural networks have demonstrated significant efficacy in predicting molecular interactions. Introducing equivariant vectorial representations augments expressivity by capturing geometric data symmetries, thereby improving model accuracy. However, two-body bond vectors in opposition may cancel each other out during message passing, leading to the loss of directional information on their shared node. In this study, we develop Equivariant N-body Interaction Networks (ENINet) that explicitly integrates equivariant many-body interactions to preserve directional information in the message passing scheme. Experiments indicate that integrating many-body equivariant representations enhances prediction accuracy across diverse scalar and tensorial quantum chemical properties. Ablation studies show an average performance improvement of 7.9% across 11 out of 12 properties in QM9, 27.9% in forces in MD17, and 11.3% in polarizabilities (CCSD) in QM7b.

Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making accurate forecasting challenging. Traditional methods model point-to-point relationships, which limits their ability to capture complex temporal patterns and increases their susceptibility to noise.To address these issues, we introduce the WindowMixer model, built on an all-MLP framework. WindowMixer leverages the continuous nature of time series by examining temporal variations from a window-based perspective. It decomposes time series into trend and seasonal components, handling them individually. For trends, a fully connected (FC) layer makes predictions. For seasonal components, time windows are projected to produce window tokens, processed by Intra-Window-Mixer and Inter-Window-Mixer modules. The Intra-Window-Mixer models relationships within each window, while the Inter-Window-Mixer models relationships between windows. This approach captures intricate patterns and long-range dependencies in the data.Experiments show WindowMixer consistently outperforms existing methods in both long-term and short-term forecasting tasks., Comment: We have found some errors in the paper, involving inaccurate data, and therefore request to withdraw the manuscript

Efficiently modeling sequences with infinite context length has been a long-standing problem. Past works suffer from either the quadratic computation complexity or the limited extrapolation ability on length generalization. In this work, we present Samba, a simple hybrid architecture that layer-wise combines Mamba, a selective State Space Model (SSM), with Sliding Window Attention (SWA). Samba selectively compresses a given sequence into recurrent hidden states while still maintaining the ability to precisely recall memories with the attention mechanism. We scale Samba up to 3.8B parameters with 3.2T training tokens and show that Samba substantially outperforms the state-of-the-art models based on pure attention or SSMs on a wide range of benchmarks. When trained on 4K length sequences, Samba can be efficiently extrapolated to 256K context length with perfect memory recall and show improved token predictions up to 1M context length. As a linear-time sequence model, Samba enjoys a 3.73x higher throughput compared to Transformers with grouped-query attention when processing user prompts of 128K length, and 3.64x speedup when generating 64K tokens with unlimited streaming. A sample implementation of Samba is publicly available in https://github.com/microsoft/Samba.

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has changed this paradigm. TabPFN uses a 12-layer transformer trained on large synthetic datasets to learn universal tabular representations. This method enables fast and accurate predictions on new tasks with a single forward pass and no need for additional training. Although TabPFN has been successful on small datasets, it generally shows weaker performance when dealing with categorical features. To overcome this limitation, we propose FT-TabPFN, which is an enhanced version of TabPFN that includes a novel Feature Tokenization layer to better handle classification features. By fine-tuning it for downstream tasks, FT-TabPFN not only expands the functionality of the original model but also significantly improves its applicability and accuracy in tabular classification. Our full source code is available for community use and development.

With the exponential growth of data and evolving use cases, petabyte-scale OLAP data platforms are increasingly adopting a model that decouples compute from storage. This shift, evident in organizations like Uber and Meta, introduces operational challenges including massive, read-heavy I/O traffic with potential throttling, as well as skewed and fragmented data access patterns. Addressing these challenges, this paper introduces the Alluxio local (edge) cache, a highly effective architectural optimization tailored for such environments. This embeddable cache, optimized for petabyte-scale data analytics, leverages local SSD resources to alleviate network I/O and API call pressures, significantly improving data transfer efficiency. Integrated with OLAP systems like Presto and storage services like HDFS, the Alluxio local cache has demonstrated its effectiveness in handling large-scale, enterprise-grade workloads over three years of deployment at Uber and Meta. We share insights and operational experiences in implementing these optimizations, providing valuable perspectives on managing modern, massive-scale OLAP workloads., Comment: Accepted to the USENIX Annual Technical Conference (USENIX ATC) 2024

Pixel-level Video Understanding requires effectively integrating three-dimensional data in both spatial and temporal dimensions to learn accurate and stable semantic information from continuous frames. However, existing advanced models on the VSPW dataset have not fully modeled spatiotemporal relationships. In this paper, we present our solution for the PVUW competition, where we introduce masked video consistency (MVC) based on existing models. MVC enforces the consistency between predictions of masked frames where random patches are withheld. The model needs to learn the segmentation results of the masked parts through the context of images and the relationship between preceding and succeeding frames of the video. Additionally, we employed test-time augmentation, model aggeregation and a multimodal model-based post-processing method. Our approach achieves 67.27% mIoU performance on the VSPW dataset, ranking 2nd place in the PVUW2024 challenge VSS track.

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity of user-provided concept visual examples. By revisiting the two major stages leading to the success of TGDMs -- 1) contrastive image-language pre-training (CLIP) for text encoder that encodes visual semantics, and 2) training TGDM that decodes the textual embeddings into pixels -- we point that existing customized generation methods only focus on fine-tuning the second stage while overlooking the first one. To this end, we propose a simple yet effective solution called CLIF: contrastive image-language fine-tuning. Specifically, given a few samples of customized concepts, we obtain non-confusing textual embeddings of a concept by fine-tuning CLIP via contrasting a concept and the over-segmented visual regions of other concepts. Experimental results demonstrate the effectiveness of CLIF in preventing the confusion of multi-customized concept generation.

We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3.5 (e.g., phi-3-mini achieves 69% on MMLU and 8.38 on MT-bench), despite being small enough to be deployed on a phone. Our training dataset is a scaled-up version of the one used for phi-2, composed of heavily filtered publicly available web data and synthetic data. The model is also further aligned for robustness, safety, and chat format. We also provide parameter-scaling results with a 7B, 14B models trained for 4.8T tokens, called phi-3-small, phi-3-medium, both significantly more capable than phi-3-mini (e.g., respectively 75%, 78% on MMLU, and 8.7, 8.9 on MT-bench). To enhance multilingual, multimodal, and long-context capabilities, we introduce three models in the phi-3.5 series: phi-3.5-mini, phi-3.5-MoE, and phi-3.5-Vision. The phi-3.5-MoE, a 16 x 3.8B MoE model with 6.6 billion active parameters, achieves superior performance in language reasoning, math, and code tasks compared to other open-source models of similar scale, such as Llama 3.1 and the Mixtral series, and on par with Gemini-1.5-Flash and GPT-4o-mini. Meanwhile, phi-3.5-Vision, a 4.2 billion parameter model derived from phi-3.5-mini, excels in reasoning tasks and is adept at handling both single-image and text prompts, as well as multi-image and text prompts., Comment: 24 pages

Unsupervised (a.k.a. Self-supervised) representation learning (URL) has emerged as a new paradigm for time series analysis, because it has the ability to learn generalizable time series representation beneficial for many downstream tasks without using labels that are usually difficult to obtain. Considering that existing approaches have limitations in the design of the representation encoder and the learning objective, we have proposed Contrastive Shapelet Learning (CSL), the first URL method that learns the general-purpose shapelet-based representation through unsupervised contrastive learning, and shown its superior performance in several analysis tasks, such as time series classification, clustering, and anomaly detection. In this paper, we develop TimeCSL, an end-to-end system that makes full use of the general and interpretable shapelets learned by CSL to achieve explorable time series analysis in a unified pipeline. We introduce the system components and demonstrate how users interact with TimeCSL to solve different analysis tasks in the unified pipeline, and gain insight into their time series by exploring the learned shapelets and representation.

We extend constructions of classical Clifford analysis to the case of indefinite non-degenerate quadratic forms. Clifford analogues of complex holomorphic functions - called monogenic functions - are defined by means of the Dirac operators that factor a certain wave operator. One of the fundamental features of quaternionic analysis is the invariance of quaternionic analogues of holomorphic function under conformal (or Mobius) transformations. A similar invariance property is known to hold in the context of Clifford algebras associated to positive definite quadratic forms. We generalize these results to the case of Clifford algebras associated to all non-degenerate quadratic forms. This result puts the indefinite signature case on the same footing as the classical positive definite case., Comment: 22 pages, to appear in Complex Analysis and Operator Theory

The Lion optimizer has been a promising competitor with the AdamW for training large AI models, with advantages on memory, computation, and sample efficiency. In this paper, we introduce Distributed Lion, an innovative adaptation of Lion for distributed training environments. Leveraging the sign operator in Lion, our Distributed Lion only requires communicating binary or lower-precision vectors between workers to the center server, significantly reducing the communication cost. Our theoretical analysis confirms Distributed Lion's convergence properties. Empirical results demonstrate its robustness across a range of tasks, worker counts, and batch sizes, on both vision and language problems. Notably, Distributed Lion attains comparable performance to standard Lion or AdamW optimizers applied on aggregated gradients, but with significantly reduced communication bandwidth. This feature is particularly advantageous for training large models. In addition, we also demonstrate that Distributed Lion presents a more favorable performance-bandwidth balance compared to existing efficient distributed methods such as deep gradient compression and ternary gradients., Comment: 22 pages

Recent advances in generative AI technologies like large language models raise both excitement and concerns about the future of human-AI co-creation in writing. To unpack people's attitude towards and experience with generative AI-powered writing assistants, in this paper, we conduct an experiment to understand whether and how much value people attach to AI assistance, and how the incorporation of AI assistance in writing workflows changes people's writing perceptions and performance. Our results suggest that people are willing to forgo financial payments to receive writing assistance from AI, especially if AI can provide direct content generation assistance and the writing task is highly creative. Generative AI-powered assistance is found to offer benefits in increasing people's productivity and confidence in writing. However, direct content generation assistance offered by AI also comes with risks, including decreasing people's sense of accountability and diversity in writing. We conclude by discussing the implications of our findings., Comment: CHI 2024

There are two challenges presented in parsing road scenes from UAV images: the complexity of processing high-resolution images and the dependency on extensive manual annotations required by traditional supervised deep learning methods to train robust and accurate models. In this paper, a novel unsupervised road parsing framework that leverages advancements in vision language models with fundamental computer vision techniques is introduced to address these critical challenges. Our approach initiates with a vision language model that efficiently processes ultra-high resolution images to rapidly identify road regions of interest. Subsequent application of the vision foundation model, SAM, generates masks for these regions without requiring category information. A self-supervised learning network then processes these masked regions to extract feature representations, which are clustered using an unsupervised algorithm that assigns unique IDs to each feature cluster. The masked regions are combined with the corresponding IDs to generate initial pseudo-labels, which initiate an iterative self-training process for regular semantic segmentation. Remarkably, the proposed method achieves a mean Intersection over Union (mIoU) of 89.96% on the development dataset without any manual annotation, demonstrating extraordinary flexibility by surpassing the limitations of human-defined categories, and autonomously acquiring knowledge of new categories from the dataset itself.

Training an effective Machine learning (ML) model is an iterative process that requires effort in multiple dimensions. Vertically, a single pipeline typically includes an initial ETL (Extract, Transform, Load) of raw datasets, a model training stage, and an evaluation stage where the practitioners obtain statistics of the model performance. Horizontally, many such pipelines may be required to find the best model within a search space of model configurations. Many practitioners resort to maintaining logs manually and writing simple glue code to automate the workflow. However, carrying out this process on the cloud is not a trivial task in terms of resource provisioning, data management, and bookkeeping of job histories to make sure the results are reproducible. We propose an end-to-end cloud-based machine learning platform, Accelerated Cloud for AI (ACAI), to help improve the productivity of ML practitioners. ACAI achieves this goal by enabling cloud-based storage of indexed, labeled, and searchable data, as well as automatic resource provisioning, job scheduling, and experiment tracking. Specifically, ACAI provides practitioners (1) a data lake for storing versioned datasets and their corresponding metadata, and (2) an execution engine for executing ML jobs on the cloud with automatic resource provisioning (auto-provision), logging and provenance tracking. To evaluate ACAI, we test the efficacy of our auto-provisioner on the MNIST handwritten digit classification task, and we study the usability of our system using experiments and interviews. We show that our auto-provisioner produces a 1.7x speed-up and 39% cost reduction, and our system reduces experiment time for ML scientists by 20% on typical ML use cases.

Crypto donations now represent a significant fraction of charitable giving worldwide. Nonfungible token (NFT) charity fundraisers, which involve the sale of NFTs of artistic works with the proceeds donated to philanthropic causes, have emerged as a novel development in this space. A unique aspect of NFT charity fundraisers is the significant potential for donors to reap financial gains from the rising value of purchased NFTs. Questions may arise about the motivations of donors in these charity fundraisers, resulting in a negative social image. NFT charity fundraisers thus offer a unique opportunity to understand the economic consequences of a donor's social image. We investigate these effects in the context of a large NFT charity fundraiser. We identify the causal effect of purchasing an NFT within the charity fundraiser on a donor's later market outcomes by leveraging random variation in transaction processing times on the blockchain. Further, we demonstrate a clear pattern of heterogeneity, based on an individual's decision to relist (versus hold) the purchased charity NFTs (a sign of strategic generosity), and based on an individual's degree of social exposure within the NFT marketplace. We show that charity-NFT "relisters" experience significant penalties in the market, in terms of the prices they are able to command on other NFT listings, particularly among those who relist quickly and those who are more socially exposed. Our study underscores the growing importance of digital visibility and traceability, features that characterize crypto-philanthropy, and online philanthropy more broadly.

Automatic colorization of grayscale image has been a challenging task. Previous research have applied supervised methods in conquering this problem [ 1]. In this paper, we reproduces a GAN-based coloring model, and experiments one of its variant. We also proposed a CycleGAN based model and experiments those methods on various datasets. The result shows that the proposed CycleGAN model does well in human-face coloring and comic coloring, but lack the ability to diverse colorization.

In robust optimization problems, the magnitude of perturbations is relatively small. Consequently, solutions within certain regions are less likely to represent the robust optima when perturbations are introduced. Hence, a more efficient search process would benefit from increased opportunities to explore promising regions where global optima or good local optima are situated. In this paper, we introduce a novel robust evolutionary algorithm named the dual-stage robust evolutionary algorithm (DREA) aimed at discovering robust solutions. DREA operates in two stages: the peak-detection stage and the robust solution-searching stage. The primary objective of the peak-detection stage is to identify peaks in the fitness landscape of the original optimization problem. Conversely, the robust solution-searching stage focuses on swiftly identifying the robust optimal solution using information obtained from the peaks discovered in the initial stage. These two stages collectively enable the proposed DREA to efficiently obtain the robust optimal solution for the optimization problem. This approach achieves a balance between solution optimality and robustness by separating the search processes for optimal and robust optimal solutions. Experimental results demonstrate that DREA significantly outperforms five state-of-the-art algorithms across 18 test problems characterized by diverse complexities. Moreover, when evaluated on higher-dimensional robust optimization problems (100-$D$ and 200-$D$), DREA also demonstrates superior performance compared to all five counterpart algorithms.

This paper proposes a multi-day needs-based model for activity and travel demand analysis. The model captures the multi-day dynamics in activity generation, which enables the modeling of activities with increased flexibility in time and space (e.g., e-commerce and remote working). As an enhancement to activity-based models, the proposed model captures the underlying decision-making process of activity generation by accounting for psychological needs as the drivers of activities. The level of need satisfaction is modeled as a psychological inventory, whose utility is optimized via decisions on activity participation, location, and duration. The utility includes both the benefit in the inventory gained and the cost in time, monetary expense as well as maintenance of safety stock. The model includes two sub-models, a Deterministic Model that optimizes the utility of the inventory, and an Empirical Model that accounts for heterogeneity and stochasticity. Numerical experiments are conducted to demonstrate model scalability. A maximum likelihood estimator is proposed, the properties of the log-likelihood function are examined and the recovery of true parameters is tested. This research contributes to the literature on transportation demand models in the following three aspects. First, it is arguably better grounded in psychological theory than traditional models and allows the generation of activity patterns to be policy-sensitive (while avoiding the need for ad hoc utility definitions). Second, it contributes to the development of needs-based models with a non-myopic approach to model multi-day activity patterns. Third, it proposes a tractable model formulation via problem reformulation and computational enhancements, which allows for maximum likelihood parameter estimation., Comment: 38 pages, 11 figures

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model. Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction for our LLM-based scenarios, with lossless generation accuracy. In the traditional inference process, each token is generated sequentially by the LLM, leading to a time consumption proportional to the number of generated tokens. To enhance this process, our framework, named \textit{lookahead}, introduces a \textit{multi-branch} strategy. Instead of generating a single token at a time, we propose a Trie-based retrieval and verification mechanism to be able to accept several tokens at a forward step. Our strategy offers two distinct advantages: (1) it guarantees absolute correctness of the output, avoiding any approximation algorithms, and (2) the worst-case performance of our approach is equivalent to the conventional process. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework. Our framework is widely deployed in Alipay since April 2023, and obtain remarkable 2.66x to 6.26x speedup. Our code is available at https://github.com/alipay/PainlessInferenceAcceleration., Comment: 10 pages, 6 figures

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

In recent times, the field of unsupervised representation learning (URL) for time series data has garnered significant interest due to its remarkable adaptability across diverse downstream applications. Unsupervised learning goals differ from downstream tasks, making it tricky to ensure downstream task utility by focusing only on temporal feature characterization. Researchers have proposed multiple transformations to extract discriminative patterns implied in informative time series, trying to fill the gap. Despite the introduction of a variety of feature engineering techniques, e.g. spectral domain, wavelet transformed features, features in image form and symbolic features etc. the utilization of intricate feature fusion methods and dependence on heterogeneous features during inference hampers the scalability of the solutions. To address this, our study introduces an innovative approach that focuses on aligning and binding time series representations encoded from different modalities, inspired by spectral graph theory, thereby guiding the neural encoder to uncover latent pattern associations among these multi-modal features. In contrast to conventional methods that fuse features from multiple modalities, our proposed approach simplifies the neural architecture by retaining a single time series encoder, consequently leading to preserved scalability. We further demonstrate and prove mechanisms for the encoder to maintain better inductive bias. In our experimental evaluation, we validated the proposed method on a diverse set of time series datasets from various domains. Our approach outperforms existing state-of-the-art URL methods across diverse downstream tasks.

Effective user representations are pivotal in personalized advertising. However, stringent constraints on training throughput, serving latency, and memory, often limit the complexity and input feature set of online ads ranking models. This challenge is magnified in extensive systems like Meta's, which encompass hundreds of models with diverse specifications, rendering the tailoring of user representation learning for each model impractical. To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models. SUM leverages a few designated upstream user models to synthesize user embeddings from massive amounts of user features with advanced modeling techniques. These embeddings then serve as inputs to downstream online ads ranking models, promoting efficient representation sharing. To adapt to the dynamic nature of user features and ensure embedding freshness, we designed SUM Online Asynchronous Platform (SOAP), a latency free online serving system complemented with model freshness and embedding stabilization, which enables frequent user model updates and online inference of user embeddings upon each user request. We share our hands-on deployment experiences for the SUM framework and validate its superiority through comprehensive experiments. To date, SUM has been launched to hundreds of ads ranking models in Meta, processing hundreds of billions of user requests daily, yielding significant online metric gains and improved infrastructure efficiency., Comment: 8 pages, 3 figures

Deformable robots are notoriously difficult to model or control due to its high-dimensional configuration spaces. Direct trajectory optimization suffers from the curse-of-dimensionality and incurs a high computational cost, while learning-based controller optimization methods are sensitive to hyper-parameter tuning. To overcome these limitations, we hypothesize that high fidelity soft robots can be both simulated and controlled by restricting to low-dimensional spaces. Under such assumption, we propose a two-stage algorithm to identify such simulation- and control-spaces. Our method first identifies the so-called simulation-space that captures the salient deformation modes, to which the robot's governing equation is restricted. We then identify the control-space, to which control signals are restricted. We propose a multi-fidelity Riemannian Bayesian bilevel optimization to identify task-specific control spaces. We show that the dimension of control-space can be less than $10$ for a high-DOF soft robot to accomplish walking and swimming tasks, allowing low-dimensional MPC controllers to be applied to soft robots with tractable computational complexity.

Finding robot poses and trajectories represents a foundational aspect of robot motion planning. Despite decades of research, efficiently and robustly addressing these challenges is still difficult. Existing approaches are often plagued by various limitations, such as intricate geometric approximations, violations of collision constraints, or slow first-order convergence. In this paper, we introduce two novel optimization formulations that offer provable robustness, achieving second-order convergence while requiring only a convex approximation of the robot's links and obstacles. Our first method, known as the Explicit Collision Barrier (ECB) method, employs a barrier function to guarantee separation between convex objects. ECB uses an efficient matrix factorization technique, enabling a second-order Newton's method with an iterative complexity linear in the number of separating planes. Our second method, referred to as the Implicit Collision Barrier (ICB) method, further transforms the separating planes into implicit functions of robot poses. We show such an implicit objective function is twice-differentiable, with derivatives evaluated at a linear complexity. To assess the effectiveness of our approaches, we conduct a comparative study with a first-order baseline algorithm across six testing scenarios. Our results unequivocally justify that our method exhibits significantly faster convergence rates compared to the baseline algorithm.

This paper explores a prevailing trend in the industry: migrating data-intensive analytics applications from on-premises to cloud-native environments. We find that the unique cost models associated with cloud-based storage necessitate a more nuanced understanding of optimizing performance. Specifically, based on traces collected from Uber's Presto fleet in production, we argue that common I/O optimizations, such as table scan and filter, and broadcast join, may lead to unexpected costs when naively applied in the cloud. This is because traditional I/O optimizations mainly focus on improving throughput or latency in on-premises settings, without taking into account the monetary costs associated with storage API calls. In cloud environments, these costs can be significant, potentially involving billions of API calls per day just for Presto workloads at Uber scale. Presented as a case study, this paper serves as a starting point for further research to design efficient I/O strategies specifically tailored for data-intensive applications in cloud settings., Comment: 6 pages, 3 figures