Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from varying viewpoints. For a prolonged period, this field has been predominantly driven by deep convolutional neural networks. In recent years, the Transformer has witnessed remarkable advancements in computer vision, prompting an increasing body of research to delve into the application of Transformer in Re-ID. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. In categorizing existing works into Image/Video-Based Re-ID, Re-ID with limited data/annotations, Cross-Modal Re-ID, and Special Re-ID Scenarios, we thoroughly elucidate the advantages demonstrated by the Transformer in addressing a multitude of challenges across these domains. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance on both single-/cross modal tasks. Besides, this survey also covers a wide range of Re-ID research objects, including progress in animal Re-ID. Given the diversity of species in animal Re-ID, we devise a standardized experimental benchmark and conduct extensive experiments to explore the applicability of Transformer for this task to facilitate future research. Finally, we discuss some important yet under-investigated open issues in the big foundation model era, we believe it will serve as a new handbook for researchers in this field.

Understanding the multifaceted effects of climate change across diverse geographic locations is crucial for timely adaptation and the development of effective mitigation strategies. As the volume of scientific literature on this topic continues to grow exponentially, manually reviewing these documents has become an immensely challenging task. Utilizing Natural Language Processing (NLP) techniques to analyze this wealth of information presents an efficient and scalable solution. By gathering extensive amounts of peer-reviewed articles and studies, we can extract and process critical information about the effects of climate change in specific regions. We employ BERT (Bidirectional Encoder Representations from Transformers) for Named Entity Recognition (NER), which enables us to efficiently identify specific geographies within the climate literature. This, in turn, facilitates location-specific analyses. We conduct region-specific climate trend analyses to pinpoint the predominant themes or concerns related to climate change within a particular area, trace the temporal progression of these identified issues, and evaluate their frequency, severity, and potential development over time. These in-depth examinations of location-specific climate data enable the creation of more customized policy-making, adaptation, and mitigation strategies, addressing each region's unique challenges and providing more effective solutions rooted in data-driven insights. This approach, founded on a thorough exploration of scientific texts, offers actionable insights to a wide range of stakeholders, from policymakers to engineers to environmentalists. By proactively understanding these impacts, societies are better positioned to prepare, allocate resources wisely, and design tailored strategies to cope with future climate conditions, ensuring a more resilient future for all.

Try to generate new bridge types using generative artificial intelligence technology. Using symmetric structured image dataset of three-span beam bridge, arch bridge, cable-stayed bridge and suspension bridge , based on Python programming language, TensorFlow and Keras deep learning platform framework , PixelCNN is constructed and trained. The model can capture the statistical structure of the images and calculate the probability distribution of the next pixel when the previous pixels are given. From the obtained latent space sampling, new bridge types different from the training dataset can be generated. PixelCNN can organically combine different structural components on the basis of human original bridge types, creating new bridge types that have a certain degree of human original ability. Autoregressive models cannot understand the meaning of the sequence, while multimodal models combine regression and autoregressive models to understand the sequence. Multimodal models should be the way to achieve artificial general intelligence in the future.

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, coined as OCD, to further reduce latency by allocating computations more towards foreground edited regions that are arguably more important for perceptual quality. We achieve this by two novel proposals: i) Object-Centric Sampling, decoupling the diffusion steps spent on salient regions or background, allocating most of the model capacity to the former, and ii) Object-Centric 3D Token Merging, which reduces cost of cross-frame attention by fusing redundant tokens in unimportant background regions. Both techniques are readily applicable to a given video editing model \textit{without} retraining, and can drastically reduce its memory and computational cost. We evaluate our proposals on inversion-based and control-signal-based editing pipelines, and show a latency reduction up to 10x for a comparable synthesis quality.

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal `attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. This approach allows for the creation of style-consistent images using a reference style through a straightforward inversion operation. Our method's evaluation across diverse styles and text prompts demonstrates high-quality synthesis and fidelity, underscoring its efficacy in achieving consistent style across various inputs.

Microsoft has been quietly debating the future of its advanced AI lab in China, sources say. The lab was opened in 1998 and has become one of the most important artificial intelligence hubs in the world, leading to advancements in the company's speech, image and facial recognition software. Microsoft Research Lab Asia (MSRA) opened at a time of optimism about China as an emerging democracy but as tensions between the US and the communist state have intensified, internal pressure has mounted to shut or scale it down. That pressure has only intensified in recent months, after the Biden administration banned US investments in Chinese tech ventures that might aid the rival superpower's'military, intelligence, surveillance, or cyber-enabled capabilities.' But, the tech giant's founder Bill Gates continues to defend the lab and has pushed to keep it open, alongside Microsoft's research leaders and its current president.

To enable the electrification of transportation systems, it is important to understand how technologies such as grid storage, solar photovoltaic systems, and control strategies can aid the deployment of electric vehicle charging at scale. In this work, we present EV-EcoSim, a co-simulation platform that couples electric vehicle charging, battery systems, solar photovoltaic systems, grid transformers, control strategies, and power distribution systems, to perform cost quantification and analyze the impacts of electric vehicle charging on the grid. This python-based platform can run a receding horizon control scheme for real-time operation and a one-shot control scheme for planning problems, with multi-timescale dynamics for different systems to simulate realistic scenarios. We demonstrate the utility of EV-EcoSim through a case study focused on economic evaluation of battery size to reduce electricity costs while considering impacts of fast charging on the power distribution grid. We present qualitative and quantitative evaluations on the battery size in tabulated results. The tabulated results delineate the trade-offs between candidate battery sizing solutions, providing comprehensive insights for decision-making under uncertainty. Additionally, we demonstrate the implications of the battery controller model fidelity on the system costs and show that the fidelity of the battery controller can completely change decisions made when planning an electric vehicle charging site.

The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading methods focus on the single-page setting, while documents can span hundreds of pages. We present GRAM, a method that seamlessly extends pre-trained single-page models to the multi-page setting, without requiring computationally-heavy pretraining. To do so, we leverage a single-page encoder for local page-level understanding, and enhance it with document-level designated layers and learnable tokens, facilitating the flow of information across pages for global reasoning. To enforce our model to utilize the newly introduced document-level tokens, we propose a tailored bias adaptation method. For additional computational savings during decoding, we introduce an optional compression stage using our C-Former model, which reduces the encoded sequence length, thereby allowing a tradeoff between quality and latency. Extensive experiments showcase GRAM's state-of-the-art performance on the benchmarks for multi-page DocVQA, demonstrating the effectiveness of our approach.

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Performance loss due to static dataflow. Kernel performance in LLM depends on varied input data features, hardware configurations, etc. A single and static dataflow may lead to a 50.25% performance loss for GEMMs of different shapes in LLM inference. We present FlashDecoding++, a fast LLM inference engine supporting mainstream LLMs and hardware back-ends. To tackle the above challenges, FlashDecoding++ creatively proposes: (1) Asynchronized softmax with unified max value. FlashDecoding++ introduces a unified max value technique for different partial softmax computations to avoid synchronization. (2) Flat GEMM optimization with double buffering. FlashDecoding++ points out that flat GEMMs with different shapes face varied bottlenecks. Then, techniques like double buffering are introduced. (3) Heuristic dataflow with hardware resource adaptation. FlashDecoding++ heuristically optimizes dataflow using different hardware resource considering input dynamics. Due to the versatility of optimizations in FlashDecoding++, FlashDecoding++ can achieve up to 4.86x and 2.18x speedup on both NVIDIA and AMD GPUs compared to Hugging Face implementations. FlashDecoding++ also achieves an average speedup of 1.37x compared to state-of-the-art LLM inference engines on mainstream LLMs.

Large Language Models (LLMs) are transforming the way people generate, explore, and engage with content. We study how we can develop LLM applications for online social networks. Despite LLMs' successes in other domains, it is challenging to develop LLM-based products for social networks for numerous reasons, and it has been relatively under-reported in the research community. We categorize LLM applications for social networks into three categories. First is knowledge tasks where users want to find new knowledge and information, such as search and question-answering. Second is entertainment tasks where users want to consume interesting content, such as getting entertaining notification content. Third is foundational tasks that need to be done to moderate and operate the social networks, such as content annotation and LLM monitoring. For each task, we share the challenges we found, solutions we developed, and lessons we learned. To the best of our knowledge, this is the first comprehensive paper about developing LLM applications for social networks.