Related papers: Speculative Automated Refactoring of Imperative De…

Deep learning (DL) is becoming the cornerstone of numerous applications both in datacenters and at the edge. Specialized hardware is often necessary to meet the performance requirements of state-of-the-art DL models, but the rapid pace of…

Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these…

Dynamic programming (DP) is an algorithmic design paradigm for the efficient, exact solution of otherwise intractable, combinatorial problems. However, DP algorithm design is often presented in an ad-hoc manner. It is sometimes difficult to…

Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…

Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assistant systems, and applications concerned with the General…

We propose the concept of Speculative Execution for Visual Analytics and discuss its effectiveness for model exploration and optimization. Speculative Execution enables the automatic generation of alternative, competing model configurations…

Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an attractive remedy to increasing concerns about data privacy in deep learning (DL). However, building DL models that operate on ciphertext is…

Deep Learning (DL) has recently achieved tremendous success. A variety of DL frameworks and platforms play a key role to catalyze such progress. However, the differences in architecture designs and implementations of existing frameworks and…

Emerging research in edge devices and micro-controller units (MCU) enables on-device computation of Deep Learning Training and Inferencing tasks. More recently, contemporary trends focus on making the Deep Neural Net (DNN) Models runnable…

Deep Reinforcement Learning (DRL) is vital in various AI applications. DRL algorithms comprise diverse compute kernels, which may not be simultaneously optimized using a homogeneous architecture. However, even with available heterogeneous…

Deep learning (DL) has proven to be a highly effective approach for developing models in diverse contexts, including visual perception, speech recognition, and machine translation. However, the end-to-end process for applying DL is not…

In recent years, Hypergraph Neural Networks (HNNs) have demonstrated immense potential in handling complex systems with high-order interactions. However, acquiring large-scale, high-quality labeled data for these models is costly, making…

Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves…

One of the key challenges arising when compilers vectorize loops for today's SIMD-compatible architectures is to decide if vectorization or interleaving is beneficial. Then, the compiler has to determine how many instructions to pack…

Iterative graph algorithms often compute intermediate values and update them as computation progresses. Updated output values are used as inputs for computations in current or subsequent iterations; hence the number of iterations required…

Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex…

It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…

Automatic parallelization remains a challenging problem in software engineering, particularly in identifying code regions where loops can be safely executed in parallel on modern multi-core architectures. Traditional static analysis…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Planning in code is considered a more reliable approach for many orchestration tasks. This is because code is more tractable than steps generated via Natural Language and make it easy to support more complex sequences by abstracting…