Related papers: BatchWeave: A Consistent Object-Store-Native Data …

The ultimate aim of the study is to explore the inverse design of porous metamaterials using a deep learning-based generative framework. Specifically, we develop a property-variational autoencoder (pVAE), a variational autoencoder (VAE)…

Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive…

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in AIoT (Artificial Intelligence of Things) design. However, due…

Training large language models (LLMs) requires substantial compute and energy. At the same time, renewable energy sources regularly produce more electricity than the grid can absorb, leading to curtailment, the deliberate reduction of clean…

We present an extension of the PatchworkMHD code [1], itself an MHD-capable extension of the Patchwork code [2], for which several algorithms presented here were co-developed. Its purpose is to create a multipatch scheme compatible with…

Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown…

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling.…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve…

Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning. In this paper, we present a novel framework for learning generative models…

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…

Modern large language foundation models (LLM) have now entered the daily lives of millions of users. We ask a natural question whether it is possible to customize LLM for every user or every task. From system and industrial economy…

The efficacy of Large Language Models (LLMs) in long-context tasks is often hampered by the substantial memory footprint and computational demands of the Key-Value (KV) cache. Current compression strategies, including token eviction and…

Machine learning (ML) techniques have been demonstrated to improve the accuracy and efficiency of anomaly detection (AD) when compared to conventional methods. This has led to the adoption of ML for data quality monitoring (DQM) use cases…

Efficiently deploying large language models (LLMs) in real-world scenarios remains a critical challenge, primarily due to hardware heterogeneity, inference framework limitations, and workload complexities.Efficiently deploying large…

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Efficient Federated learning (FL) is crucial for training deep networks over devices with limited compute resources and bounded networks. With the advent of big data, devices either generate or collect multimodal data to train either…

Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate…

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Federated Learning (FL) aims to train a global inference model from remotely distributed clients, gaining popularity due to its benefit of improving data privacy. However, traditional FL often faces challenges in practical applications,…