Related papers: Parameterized Synthesis Case Study: AMBA AHB (exte…

The recent surge in State Space Models (SSMs), particularly the emergence of Mamba, has established them as strong alternatives or complementary modules to Transformers across diverse domains. In this work, we aim to explore the potential…

This paper considers hybrid beamforming (HB) for downlink multiuser massive multiple input multiple output (MIMO) systems with frequency selective channels. For this system, first we determine the required number of radio frequency (RF)…

Sequential recommendation systems have become a cornerstone of personalized services, adept at modeling the temporal evolution of user preferences by capturing dynamic interaction sequences. Existing approaches predominantly rely on…

APIs are central to modern software development, yet composing new APIs from large libraries is difficult due to the exponential search space; traditional component-based synthesis relies on costly exploration and hand-crafted…

State-space models (SSMs), particularly the Mamba architecture, have emerged as powerful alternatives to Transformers for sequence modeling, offering linear-time complexity and competitive performance across diverse tasks. However, their…

We present a novel algorithm that synthesizes imperative programs for introductory programming courses. Given a set of input-output examples and a partial program, our algorithm generates a complete program that is consistent with every…

Analysis based reconstruction has recently been introduced as an alternative to the well-known synthesis sparsity model used in a variety of signal processing areas. In this paper we convert the analysis exact-sparse reconstruction problem…

This work focuses on the problem of hyper-parameter tuning (HPT) for robust (i.e., adversarially trained) models, shedding light on the new challenges and opportunities arising during the HPT process for robust models. To this end, we…

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading…

Timed regular expressions serve as a formalism for specifying real-time behaviors of Cyber-Physical Systems. In this paper, we consider the synthesis of timed regular expressions, focusing on generating a timed regular expression consistent…

State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple yet effective trick…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling…

With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a…

Partial observability and controllability are two well-known issues in test-case synthesis for interactive systems. We address the problem of partial control in the synthesis of test cases from timed-automata specifications. Building on the…

Malware code often resorts to various self-protection techniques to complicate analysis. One such technique is applying Mixed-Boolean Arithmetic (MBA) expressions as a way to create opaque predicates and diversify and obfuscate the data…

Pipeline parallelism enables training models that exceed single-device memory, but practical throughput remains limited by pipeline bubbles. Although parameter freezing can improve training throughput by adaptively skipping backward…

The preparation of quantum Gibbs state is an essential part of quantum computation and has wide-ranging applications in various areas, including quantum simulation, quantum optimization, and quantum machine learning. In this paper, we…

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…

Automatic synthesis of hardware components from declarative specifications is an ambitious endeavor in computer aided design. Existing synthesis algorithms are often implemented with Binary Decision Diagrams (BDDs), inheriting their…