Related papers: LeGend: A Data-Driven Framework for Lemma Generati…

Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highly structured source code. Consequently, how to further…

One of the key tasks in machine learning for tabular data is feature engineering. Although it is vital for improving the performance of models, it demands considerable human expertise and deep domain knowledge, making it labor-intensive…

The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A true AGI agent should not only possess the capability to…

The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating…

Generative Artificial Intelligence (GenAI) has demonstrated its capabilities in the present world that reduce human effort significantly. It utilizes deep learning techniques to create original and realistic content in terms of text,…

Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research--relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive…

When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is…

The design of Systems on Chips (SoCs) is becoming more and more complex due to technological advancements. Missed bugs can cause drastic failures in safety-critical environments leading to the endangerment of lives. To overcome these…

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains…

Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences,…

Progress in hardware model checking depends critically on high-quality benchmarks. However, the community faces a significant benchmark gap: existing suites are limited in number, often distributed only in representations such as BTOR2…

Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing…

The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis.…

Large Language Models (LLMs) are increasingly used to automatically generate optimized CUDA kernels, substantially improving developer productivity. However, despite rapid generation, these kernels often contain subtle correctness bugs and…

In Natural Language Processing (NLP), Machine Reading Comprehension (MRC) is the task of answering a question based on a given context. To handle questions in the medical domain, modern language models such as BioBERT, SciBERT and even…

Recent advances show that large language models (LLMs) can act as autonomous agents capable of generating GPU kernels, but integrating these AI-generated kernels into real-world inference systems remains challenging. FlashInfer-Bench…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data…

While Large Language Models (LLMs) demonstrate immense potential for automating integrated circuit (IC) development, their practical deployment is fundamentally limited by restricted context windows. Existing context-extension methods…

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…