Related papers: Memory-Efficient Fixpoint Computation
The recently introduced Gradient Methods with Memory use a subset of the past oracle information to create an accurate model of the objective function that enables them to surpass the Gradient Method in practical performance. The model…
Analyzing the behavior of a program running on a processor that supports speculative execution is crucial for applications such as execution time estimation and side channel detection. Unfortunately, existing static analysis techniques…
Approximate computing (AC) leverages the inherent error resilience and is used in many big-data applications from various domains such as multimedia, computer vision, signal processing, and machine learning to improve systems performance…
Recently, Interleaved-modal Chain-of-Thought (ICoT) reasoning has achieved remarkable success by leveraging both multimodal inputs and outputs, attracting increasing attention. While achieving promising performance, current ICoT methods…
Bayesian method is capable of capturing real world uncertainties/incompleteness and properly addressing the over-fitting issue faced by deep neural networks. In recent years, Bayesian Neural Networks (BNNs) have drawn tremendous attentions…
Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…
The core challenge in designing an effective static program analysis is to find a good program abstraction -- one that retains only details relevant to a given query. In this paper, we present a new approach for automatically finding such…
Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance…
This work introduces a novel blackbox optimization algorithm for computationally expensive constrained multi-fidelity problems. When applying a direct search method to such problems, the scarcity of feasible points may lead to numerous…
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence…
State-of-the-art systolic array-based accelerators adopt the traditional im2col algorithm to accelerate the inference of convolutional layers. However, traditional im2col cannot efficiently support AI backpropagation. Backpropagation in…
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional…
Punctuation restoration plays an essential role in the post-processing procedure of automatic speech recognition, but model efficiency is a key requirement for this task. To that end, we present EfficientPunct, an ensemble method with a…
Many algorithms feature an iterative loop that converges to the result of interest. The numerical operations in such algorithms are generally implemented using finite-precision arithmetic, either fixed- or floating-point, most of which…
Static program analysis by abstract interpretation is an efficient method to determine properties of embedded software. One example is value analysis, which determines the values stored in the processor registers. Its results are used as…
Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens…
Larger deep learning models usually lead to higher model quality with an ever-increasing GPU memory footprint. Although tensor checkpointing techniques have been proposed to enable training under a restricted GPU memory budget, the input…
Conventional LLM inference architectures suffer from high energy and latency due to frequent data movement across memory hierarchies. We propose Ouroboros, a wafer-scale SRAM-based Computing-in-Memory (CIM) architecture that executes all…
Deep neural networks are increasingly bottlenecked by the cost of optimization, both in terms of GPU memory and compute time. Existing acceleration techniques, such as mixed precision, second-order methods, and batch size scaling, are…
Abstract argumentation frameworks are formal systems that facilitate obtaining conclusions from non-monotonic knowledge systems. Within such a system, an argumentation semantics is defined as a set of arguments with some desired qualities,…