Related papers: Characterizing the Efficiency vs. Accuracy Trade-o…
Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…
The recent rise of Large Reasoning Models (LRMs) has significantly improved multi-step reasoning performance, but often at the cost of generating excessively long reasoning chains. This paper revisits the efficiency of such reasoning…
Recurrent neural networks (RNNs) have shown state of the art results for speech recognition, natural language processing, image captioning and video summarizing applications. Many of these applications run on low-power platforms, so their…
Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance…
Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…
The rapid adoption of Large Language Models (LLMs) has raised significant environmental concerns. Unlike the one-time cost of training, LLM inference occurs continuously and dominates the AI energy footprint. Yet most sustainability studies…
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks but come with substantial energy and computational costs, particularly in request-heavy scenarios. In many real-world applications, the full scale and…
This study presents an empirical investigation into the energy consumption of Discriminative and Generative AI models within real-world MLOps pipelines. For Discriminative models, we examine various architectures and hyperparameters during…
Large language models (LLMs), based on transformer architectures, have revolutionized numerous domains within artificial intelligence, science, and engineering due to their exceptional scalability and adaptability. However, the exponential…
Language models (LMs) are being scaled and becoming powerful. Improving their efficiency is one of the core research topics in neural information processing systems. Tay et al. (2022) provided a comprehensive overview of efficient…
The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform…
Recent advancements in large language models (LLMs) have significantly improved code generation and program comprehension, accelerating the evolution of software engineering. Current methods primarily enhance model performance by leveraging…
Energy system models are essential for planning and supporting the energy transition. However, increasing temporal, spatial, and sectoral resolutions have led to large-scale linear programming (LP) models that are often (over)simplified to…
The rapid advancement of AI technologies and their accelerated adoption in software development necessitates a systematic evaluation of their environmental impact alongside functional correctness. While prior studies have examined…
Large language models (LLMs) power many state-of-the-art systems in natural language processing. However, these models are extremely computationally expensive, even at inference time, raising the natural question: when is the extra cost of…
Patent classification into CPC codes underpins large scale analyses of technological change but remains challenging due to its hierarchical, multi label, and highly imbalanced structure. While pre Generative AI supervised encoder based…
Efficient and accurate load flow calculations are a bedrock of modern power system operation. Classical numerical methods such as the Newton-Raphson algorithm provide highly precise results but are computationally demanding, which limits…
Encoding long sequences in Natural Language Processing (NLP) is a challenging problem. Though recent pretraining language models achieve satisfying performances in many NLP tasks, they are still restricted by a pre-defined maximum length,…
Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…
Development sets are impractical to obtain for real low-resource languages, since using all available data for training is often more effective. However, development sets are widely used in research papers that purport to deal with…