Related papers: Hardware Complexity Aware Design Strategy for a Fu…
When serving a single base LLM with several different LoRA adapters simultaneously, the adapters cannot simply be merged with the base model's weights as the adapter swapping would create overhead and requests using different adapters could…
Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…
We calculate the complete double logarithmic contribution to cross sections for semi-inclusive hadron production in the modified minimal-subtraction scheme by applying dimensional regularization to the double logarithm approximation. The…
Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We…
While Clifford operations are relatively easy to implement in fault-tolerant quantum computers,continuous rotation gates remain a significant bottleneck in typical quantum algorithms. In this work, we ask the question: "What is the most…
The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of…
This article presents two area/latency optimized gate level asynchronous full adder designs which correspond to early output logic. The proposed full adders are constructed using the delay-insensitive dual-rail code and adhere to the…
In this paper, we introduce the gauge-fixed QLDPC surgery scheme, an improved logical measurement scheme based on the construction of Cohen et al. (Sci. Adv. 8, eabn1717). Our scheme leverages expansion properties of the Tanner graph to…
Crosstalk computing, involving engineered interference between nanoscale metal lines, offers a fresh perspective to scaling through co-existence with CMOS. Through capacitive manipulations and innovative circuit style, not only primitive…
Reversible logic allows low power dissipating circuit design and founds its application in cryptography, digital signal processing, quantum and optical information processing. This paper presents a novel quantum cost efficient reversible…
Modern key-value stores rely heavily on Log-Structured Merge (LSM) trees for write optimization, but this design introduces significant read amplification. Auxiliary structures like Bloom filters help, but impose memory costs that scale…
We present a theoretical analysis and empirical evaluations of a novel set of techniques for computational cost reduction of classifiers that are based on learned transform and soft-threshold. By modifying optimization procedures for…
Specialized accelerators have recently garnered attention as a method to reduce the power consumption of neural network inference. A promising category of accelerators utilizes nonvolatile memory arrays to both store weights and perform…
We consider a low-complexity version of the Compute and Forward scheme that involves only scaling, offset (dithering removal) and scalar quantization at the relays. The proposed scheme is suited for the uplink of a distributed antenna…
Analog multiplexing appears to be a promising solution for modern transmitters, where speed is the primary limitation. The objective is the development of a low-cost solution to compare different digital to analog (DAC) schemes. In…
As IoT and edge inference proliferate,there is a growing need to simultaneously optimize area and delay in lookup-table (LUT)-based multipliers that implement large numbers of low-bitwidth operations in parallel. This paper proposes a…
Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…
In the paper, the family of conformal four-point ladder diagrams in arbitrary space-time dimensions is considered. We use the representation obtained via explicit calculation using the operator approach and conformal quantum mechanics to…
Liquid Argon Time Projection Chamber (LArTPC) technology is commonly utilized in neutrino detector designs. It enables detailed reconstruction of neutrino events with high spatial precision and low energy threshold. Its field response (FR)…
For decoding non-binary low-density parity check (LDPC) codes, logarithm-domain sum-product (Log-SP) algorithms were proposed for reducing quantization effects of SP algorithm in conjunction with FFT. Since FFT is not applicable in the…