Related papers: GaiaFlow: Semantic-Guided Diffusion Tuning for Car…
Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they…
Despite deep-learning being state-of-the-art for data-driven model predictions, it has not yet found frequent application in ecology. Given the low sample size typical in many environmental research fields, the default choice for the…
The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This…
Training large-scale artificial intelligence (AI) models demands significant computational power and energy, leading to increased carbon footprint with potential environmental repercussions. This paper delves into the challenges of training…
Modern AI practices all strive towards the same goal: better results. In the context of deep learning, the term "results" often refers to the achieved accuracy on a competitive problem set. In this paper, we adopt an idea from the emerging…
Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling multi-hop reasoning. Yet most existing graph-based methods…
Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…
Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on training-free guidance addressing challenges from…
Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer…
As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language Models (LLMs) presents a critical sustainability challenge. Current paradigms indiscriminately apply…
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…
Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seamless integration of geometric precision and semantic…
This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…
Training large-scale Neural Networks requires substantial computational power and energy. Federated Learning enables distributed model training across geospatially distributed data centers, leveraging renewable energy sources to reduce the…
This work presents a novel approach to neural architecture search (NAS) that aims to reduce energy costs and increase carbon efficiency during the model design process. The proposed framework, called carbon-efficient NAS (CE-NAS), consists…
Efficient attention deployment in visual search is limited by human visual memory, yet this limitation can be offset by exploiting the environment's structure. This paper introduces a computational cognitive model that simulates how the…
Active search for recovering objects of interest through online, adaptive decision making with autonomous agents requires trading off exploration of unknown environments with exploitation of prior observations in the search space. Prior…
The size and complexity of deep neural networks continue to grow exponentially, significantly increasing energy consumption for training and inference by these models. We introduce an open-source package eco2AI to help data scientists and…
We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two…
The pursuit of carbon-neutral wireless networks is increasingly constrained by the escalating energy demands of deep learning-based signal processing. Here, we introduce SpikACom (Spiking Adaptive Communications), a neuromorphic computing…