Related papers: Adaptive Computation Modules: Granular Conditional…

Multi-modal transformers are rapidly gaining attention in video captioning tasks. Existing multi-modal video captioning methods typically extract a fixed number of frames, which raises critical challenges. When a limited number of frames…

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…

Large Language Models (LLMs), such as GPT and LLaMA, introduce unique memory access characteristics during inference due to frequent token sequence lookups and embedding vector retrievals. These workloads generate highly irregular and…

Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a…

The explosive growth of interactive Large Language Models (LLMs) has placed unprecedented demands for low latency on cloud GPUs, forcing them into high-power modes and causing escalating energy costs. Real-time inference workloads exhibit…

Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability…

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches…

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Edge computing is emerging as a new paradigm to allow processing data at the edge of the network, where data is typically generated and collected, by exploiting multiple devices at the edge collectively. However, exploiting the potential of…

Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical analysis reveals challenging tokens induce abrupt gradient…

Modern Augmented reality applications require performing multiple tasks on each input frame simultaneously. Multi-task learning (MTL) represents an effective approach where multiple tasks share an encoder to extract representative features…

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorithm, have been…

As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. Recently, it has attracted the attention of deep learning…

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Empowered by transformer-based models, visual tracking has advanced significantly. However, the slow speed of current trackers limits their applicability on devices with constrained computational resources. To address this challenge, we…

To meet the ever growing demand for both high throughput and uniform coverage in future wireless networks, dense network deployment will be ubiquitous, for which co- operation among the access points is critical. Considering the…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

We introduce a framework, which we denote as the augmented estimate sequence, for deriving fast algorithms with provable convergence guarantees. We use this framework to construct a new first-order scheme, the Accelerated Composite Gradient…

In this paper, we present Adaptive Computation Steps (ACS) algo-rithm, which enables end-to-end speech recognition models to dy-namically decide how many frames should be processed to predict a linguistic output. The model that applies ACS…

Analog Content Addressable Memories (aCAMs) have proven useful for associative in-memory computing applications like Decision Trees, Finite State Machines, and Hyper-dimensional Computing. While non-volatile implementations using FeFETs and…