Related papers: AMC: AutoML for Model Compression and Acceleration…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories…

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external…

Current large language models (LLMs) generally lack an effective runtime memory mechanism,making it difficult to adapt to dynamic and personalized interaction requirements. To address this issue, this paper proposes a novel neural memory…

Automatic modulation classification (AMC) is an essential technique for noncooperative spectrum monitoring and intelligent wireless receivers. However, practical AMC models must identify modulation formats from short and noisy I/Q…

The rapid growth of large models' size has far outpaced that of computing resources. To bridge this gap, encouraged by the parsimonious relationship between genotype and phenotype in the brain's growth and development, we propose the…

Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or…

Data-driven model predictive control (MPC) has demonstrated significant potential for improving robot control performance in the presence of model uncertainties. However, existing approaches often require extensive offline data collection…

Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference. However, existing tuning techniques fall short because of the high…

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning…

As the increasing complexity of Neural Network(NN) models leads to high demands for computation, AMD introduces a heterogeneous programmable system-on-chip (SoC), i.e., Versal ACAP architectures featured with programmable logic (PL), CPUs,…

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…

Linear models are used in online decision making, such as in machine learning, policy algorithms, and experimentation platforms. Many engineering systems that use linear models achieve computational efficiency through distributed systems…

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Due to the over-fitting problem caused by imbalance samples, there is still room to improve the performance of data-driven automatic modulation classification (AMC) in noisy scenarios. By fully considering the signal characteristics, an AMC…

Neural network deployment on low-cost embedded systems, hence on microcontrollers (MCUs), has recently been attracting more attention than ever. Since MCUs have limited memory capacity as well as limited compute-speed, it is critical that…