Related papers: Parameterized Synthesis Case Study: AMBA AHB (exte…
This volume contains the proceedings of the 1st International Workshop on Synthesis of Continuous Parameters (SynCoP'14). The workshop was held in Grenoble, France on April 6th, 2014, as a satellite event of the 17th European Joint…
Programming by Example (PBE) is a program synthesis paradigm in which the synthesizer creates a program that matches a set of given examples. In many applications of such synthesis (e.g., program repair or reverse engineering), we are to…
Preparation of a target quantum many-body state on quantum simulators is one of the significant steps in quantum science and technology. With a small number of qubits, a few quantum states, such as the Greenberger-Horne-Zeilinger state,…
The ability to synthesize realistic data in a parametrizable way is valuable for a number of reasons, including privacy, missing data imputation, and evaluating the performance of statistical and computational methods. When the underlying…
Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this…
We present Supernova, a 650M-parameter decoder-only transformer that demonstrates how careful architectural design and tokenization innovation can achieve the performance of larger models while maintaining computational efficiency. Our…
Deep learning models have become a cornerstone of modern AI research, yet their initializations and learning rates may at times be set in an opaque or ad-hoc fashion due to the high cost of hyperparameter sweeps. The $\mu$-Parameterization…
We develop a computational approach to Metric Answer Set Programming (ASP) to allow for expressing quantitative temporal constrains, like durations and deadlines. A central challenge is to maintain scalability when dealing with fine-grained…
Fast matching of regular expressions with bounded repetition, aka counting, such as (ab){50,100}, i.e., matching linear in the length of the text and independent of the repetition bounds, has been an open problem for at least two decades.…
Logic synthesis, a pivotal stage in chip design, entails optimizing chip specifications encoded in hardware description languages like Verilog into highly efficient implementations using Boolean logic gates. The process involves a…
Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity-such as deeper nesting and frequent Unions-of real-world regexes. To overcome the resulting performance…
Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due the quadratic complexity of multi-head self-attention…
Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we…
Deep learning models define the state-of-the-art in Automatic Drum Transcription (ADT), yet their performance is contingent upon large-scale, paired audio-MIDI datasets, which are scarce. Existing workarounds that use synthetic data often…
Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…
Most of the existing algorithms for approximate Bayesian computation (ABC) assume that it is feasible to simulate pseudo-data from the model at each iteration. However, the computational cost of these simulations can be prohibitive for high…
Generating realistic dyadic human motion from text descriptions presents significant challenges, particularly for extended interactions that exceed typical training sequence lengths. While recent transformer-based approaches have shown…
Self-supervised learning (SSL) models usually require weeks of pre-training with dozens of high-end GPUs. These models typically have a multi-headed self-attention (MHSA) context encoder. However, MHSA takes quadratic time and space in the…
Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily…
As a present to Mizar on its 40th anniversary, we develop an AI/ATP system that in 30 seconds of real time on a 14-CPU machine automatically proves 40% of the theorems in the latest official version of the Mizar Mathematical Library (MML).…