Related papers: A Circuit Domain Generalization Framework for Effi…
Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones…
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…
Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably…
Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…
The escalating complexity of modern digital systems has imposed significant challenges on integrated circuit (IC) design, necessitating tools that can simplify the IC design flow. The advent of Large Language Models (LLMs) has been seen as…
High-level synthesis (HLS) is an automated design process that transforms high-level code into hardware designs, enabling the rapid development of hardware accelerators. HLS relies on pragmas, which are directives inserted into the source…
Binary Decision Diagrams (BDDs) are instrumental in many electronic design automation (EDA) tasks thanks to their compact representation of Boolean functions. In BDD-based reversible-circuit synthesis, which is critical for quantum…
Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote…
In statistics, series of ordinary least squares problems (OLS) are used to study the linear correlation among sets of variables of interest; in many studies, the number of such variables is at least in the millions, and the corresponding…
In Autonomous Driving Systems (ADS), Directed Acyclic Graphs (DAGs) are widely used to model complex data dependencies and inter-task communication. However, existing DAG scheduling approaches oversimplify data fusion tasks by assuming…
We experimentally evaluate the practical state-of-the-art in graph bipartization (Odd Cycle Transversal), motivated by recent advances in near-term quantum computing hardware and the related embedding problems. We assemble a preprocessing…
Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited…
Learning directed acyclic graphs (DAGs) from data is a challenging task both in theory and in practice, because the number of possible DAGs scales superexponentially with the number of nodes. In this paper, we study the problem of learning…
Token reduction accelerates Multimodal Large Language Models (MLLMs) by reducing excessive tokens, but overlooks structural redundancy differences, where critical and redundant modules process identical token loads. For fine-grained…
Non-convex optimization problems are pervasive across mathematical programming, engineering design, and scientific computing, often posing intractable challenges for traditional solvers due to their complex objective functions and…
In this paper, we investigate whether we could use pruning as a reliable method to boost the generalization ability of the model. We found that existing pruning method like L2 can already offer small improvement on the target domain…
Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance.…
Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid '5Ws' questions. However, significant challenges remain when addressing '1H' questions, specifically…
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to program synthesis--whether based on natural language descriptions…
Layer fusion techniques are critical to improving the inference efficiency of deep neural networks (DNN) for deployment. Fusion aims to lower inference costs by reducing data transactions between an accelerator's on-chip buffer and DRAM.…