Related papers: DiffuTester: Accelerating Unit Test Generation for…

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we…

Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challenging due to the need for satisfying both language…

We introduce Differential Performance Evaluation (DPE), a framework designed to reliably evaluate Large Language Models (LLMs) for efficient code generation. Traditional coding benchmarks often fail to provide reliable insights into code…

Generating visual layouts is an essential ingredient of graphic design. The ability to condition layout generation on a partial subset of component attributes is critical to real-world applications that involve user interaction. Recently,…

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon,…

The rapid advancement of large language models (LLMs) has drawn urgent attention to the task of machine-generated text detection (MGTD). However, existing approaches struggle in complex real-world scenarios: zero-shot detectors rely heavily…

Large language models (LLMs) have emerged as powerful tools for knowledge-intensive tasks across domains. In materials science, to find novel materials for various energy efficient devices for various real-world applications, requires…

Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we…

Recent advances in generative modeling have shown significant promise in designing novel periodic crystal structures. Existing approaches typically rely on either large language models (LLMs) or equivariant denoising models, each with…

In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…

Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We…

Unit tests play a vital role in the software development lifecycle. Recent advances in Large Language Model (LLM)-based approaches have significantly improved automated test generation, garnering attention from both academia and industry.…

Diffusion models have emerged as an expressive family of generative models rivaling GANs in sample quality and autoregressive models in likelihood scores. Standard diffusion models typically require hundreds of forward passes through the…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Though many learning-based approaches have been proposed for unit test generation and achieved remarkable performance, they still have limitations in relying on task-specific datasets. Recently, Large Language Models (LLMs) guided by prompt…

Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability…

Effective code generation with language models hinges on two critical factors: accurately understanding the intent of the prompt and generating code that applies algorithmic reasoning to produce correct solutions capable of passing diverse…

The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. However, does such…

We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confidence across blocks and steps. Based on this observation, we…

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast…