As large language models (LLMs) evolve, the increase in model depth and parameter number leads to substantial redundancy. To enhance the efficiency of the attention mechanism, previous works primarily compress the KV cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive analyses across various LLMs show that highly similar attention patterns persist within most layers. It's intuitive to save the computation by sharing attention weights across layers. However, further analysis reveals two challenges: (1) Directly sharing the weight matrix without carefully rearranging the attention heads proves to be ineffective; (2) Shallow layers are vulnerable to small deviations in attention weights. Driven by these insights, we introduce LiSA, a lightweight substitute for self-attention in well-trained LLMs. LiSA employs tiny feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. Evaluations encompassing 13 typical benchmarks demonstrate that LiSA maintains high response quality in terms of accuracy and perplexity while reducing redundant attention calculations within 53-84% of the total layers. Our implementations of LiSA achieve a 6X compression of Q and K, with maximum throughput improvements of 19.5% for LLaMA3-8B and 32.3% for LLaMA2-7B.

Our research investigates the impact of Generative Artificial Intelligence (GAI) models, specifically text-to-image generators (T2Is), on the representation of non-Western cultures, with a focus on Indian contexts. Despite the transformative potential of T2Is in content creation, concerns have arisen regarding biases that may lead to misrepresentations and marginalizations. Through a community-centered approach and grounded theory analysis of 5 focus groups from diverse Indian subcultures, we explore how T2I outputs to English prompts depict Indian culture and its subcultures, uncovering novel representational harms such as exoticism and cultural misappropriation. These findings highlight the urgent need for inclusive and culturally sensitive T2I systems. We propose design guidelines informed by a sociotechnical perspective, aiming to address these issues and contribute to the development of more equitable and representative GAI technologies globally. Our work also underscores the necessity of adopting a community-centered approach to comprehend the sociotechnical dynamics of these models, complementing existing work in this space while identifying and addressing the potential negative repercussions and harms that may arise when these models are deployed on a global scale.

If you were asked to picture an Australian Olympian, swimmer Emma McKeon, cyclist Grace Brown, or equestrian Chris Burton might spring to mind. But ask the same question to an AI bot, and the answer is very different. Amid the Olympic excitement, researchers from Edith Cowan University asked the AI-driven image generation platform, Midjourney, to create images of the Olympic teams from 40 nations. Bizarrely, the AI tool depicts the Australian team with kangaroo bodies and koala heads, while the Greek team is depicted wearing ancient armour. So, what do you think of AI's depiction of your favourite team?

At first glance, "Jenny" looks like a young, attractive Asian-American woman with a penchant for posting flirty photos and captions on her X account. Even if some of her features look a little enhanced – her skin is unnaturally smooth and her bust unusually large for her petite frame – it is easy to look past the slight uncanniness of her appearance in an era of widespread cosmetic procedures and photo editing tools. In fact, Jenny is not a real person, but an artificial intelligence-generated model, available for hire as an online influencer or virtual companion. Jenny is the brainchild of LushAI, a startup that bills itself as the world's first AI-powered modelling agency aiming to rival OnlyFans, the subscription-based website best known for hosting adult content creators. Jenny offers essentially the same services as the human content creators that make up OnlyFans, except she is powered by an algorithm – which means she can work 24 hours a day, 365 days a year.

Deep learning has gained significant attention in remote sensing, especially in pixel- or patch-level applications. Despite initial attempts to integrate deep learning into object-based image analysis (OBIA), its full potential remains largely unexplored. In this article, as OBIA usage becomes more widespread, we conducted a comprehensive review and expansion of its task subdomains, with or without the integration of deep learning. Furthermore, we have identified and summarized five prevailing strategies to address the challenge of deep learning's limitations in directly processing unstructured object data within OBIA, and this review also recommends some important future research directions. Our goal with these endeavors is to inspire more exploration in this fascinating yet overlooked area and facilitate the integration of deep learning into OBIA processing workflows.

Solving partial differential equations (PDEs) is a fundamental problem in engineering and science. While neural PDE solvers can be more efficient than established numerical solvers, they often require large amounts of training data that is costly to obtain. Active Learning (AL) could help surrogate models reach the same accuracy with smaller training sets by querying classical solvers with more informative initial conditions and PDE parameters. While AL is more common in other domains, it has yet to be studied extensively for neural PDE solvers. To bridge this gap, we introduce AL4PDE, a modular and extensible active learning benchmark. It provides multiple parametric PDEs and state-of-the-art surrogate models for the solver-in-the-loop setting, enabling the evaluation of existing and the development of new AL methods for PDE solving. We use the benchmark to evaluate batch active learning algorithms such as uncertainty- and feature-based methods. We show that AL reduces the average error by up to 71% compared to random sampling and significantly reduces worst-case errors. Moreover, AL generates similar datasets across repeated runs, with consistent distributions over the PDE parameters and initial conditions. The acquired datasets are reusable, providing benefits for surrogate models not involved in the data generation.

Multi-agent learning algorithms have been successful at generating superhuman planning in a wide variety of games but have had little impact on the design of deployed multi-agent planners. A key bottleneck in applying these techniques to multi-agent planning is that they require billions of steps of experience. To enable the study of multi-agent planning at this scale, we present GPUDrive, a GPU-accelerated, multi-agent simulator built on top of the Madrona Game Engine that can generate over a million steps of experience per second. Observation, reward, and dynamics functions are written directly in C++, allowing users to define complex, heterogeneous agent behaviors that are lowered to high-performance CUDA. We show that using GPUDrive we are able to effectively train reinforcement learning agents over many scenes in the Waymo Motion dataset, yielding highly effective goal-reaching agents in minutes for individual scenes and generally capable agents in a few hours.

In order to follow the ever-growing computational complexity and data intensity of state-of-the-art AI models, new computing paradigms are being proposed. These paradigms aim at achieving high energy efficiency, by mitigating the Von Neumann bottleneck that relates to the energy cost of moving data between the processing cores and the memory. Convolutional Neural Networks (CNNs) are particularly susceptible to this bottleneck, given the massive data they have to manage. Systolic Arrays (SAs) are promising architectures to mitigate the data transmission cost, thanks to high data utilization carried out by an array of Processing Elements (PEs). These PEs continuously exchange and process data locally based on specific dataflows (like weight stationary and row stationary), in turn reducing the number of memory accesses to the main memory. The hardware specialization of SAs can meet different workloads, ranging from matrix multiplications to multi-dimensional convolutions. In this paper, we propose TrIM: a novel dataflow for SAs based on a Triangular Input Movement and compatible with CNN computing. When compared to state-of-the-art SA dataflows, like weight stationary and row stationary, the high data utilization offered by TrIM guarantees ~10x less memory access. Furthermore, considering that PEs continuously overlap multiplications and accumulations, TrIM achieves high throughput (up to 81.8% higher than row stationary), other than requiring a limited number of registers (up to 15.6x fewer registers than row stationary).

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing (NLP) tasks, such as question-answering, sentiment analysis, text summarization, and machine translation. However, the ever-growing complexity of LLMs demands immense computational resources, hindering the broader research and application of these models. To address this, various parameter-efficient fine-tuning strategies, such as Low-Rank Approximation (LoRA) and Adapters, have been developed. Despite their potential, these methods often face limitations in compressibility. Specifically, LoRA struggles to scale effectively with the increasing number of trainable parameters in modern large scale LLMs. Additionally, Low-Rank Economic Tensor-Train Adaptation (LoRETTA), which utilizes tensor train decomposition, has not yet achieved the level of compression necessary for fine-tuning very large scale models with limited resources. This paper introduces Tensor Train Low-Rank Approximation (TT-LoRA), a novel parameter-efficient fine-tuning (PEFT) approach that extends LoRETTA with optimized tensor train (TT) decomposition integration. By eliminating Adapters and traditional LoRA-based structures, TT-LoRA achieves greater model compression without compromising downstream task performance, along with reduced inference latency and computational overhead. We conduct an exhaustive parameter search to establish benchmarks that highlight the trade-off between model compression and performance. Our results demonstrate significant compression of LLMs while maintaining comparable performance to larger models, facilitating their deployment on resource-constraint platforms.

In Part I, we created an ensemble based on Spherical Fourier Neural Operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires several orders of magnitude fewer computational resources. Here in Part II, we generate a huge ensemble (HENS), with 7,424 members initialized each day of summer 2023. We enumerate the technical requirements for running huge ensembles at this scale. HENS precisely samples the tails of the forecast distribution and presents a detailed sampling of internal variability. For extreme climate statistics, HENS samples events 4$\sigma$ away from the ensemble mean. At each grid cell, HENS improves the skill of the most accurate ensemble member and enhances coverage of possible future trajectories. As a weather forecasting model, HENS issues extreme weather forecasts with better uncertainty quantification. It also reduces the probability of outlier events, in which the verification value lies outside the ensemble forecast distribution.