Related papers: To Diff or Not to Diff? Structure-Aware and Adapti…

Diffusion-based large language models (dLLMs) are gaining attention for their inherent capacity for parallel decoding, offering a compelling alternative to autoregressive LLMs. Among various decoding strategies, block-wise…

Code differencing is a fundamental technique in software engineering practice and research. While researchers have proposed text-based differencing techniques capable of identifying line changes over the past decade, existing methods…

Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse formats, such as…

Despite rapid advances in Large Language Models and Multimodal Large Language Models (LLMs), numerous challenges related to interpretability, scalability, resource requirements and repeatability remain, related to their application in the…

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Code review is a critical practice in software engineering, yet the growing scale and frequency of code patches in modern projects, together with the widespread adoption of AI code assistants, make manual review increasingly challenging.…

Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity of code editing tasks forces existing approaches to rely on…

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Large Language Models (LLMs) have reshaped natural language processing, powering applications from multi-hop retrieval and question answering to autonomous agent workflows. Yet, prompt engineering -- the task of crafting textual inputs to…

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

Modern software programs are built on stacks that are often undergoing changes that introduce updates and improvements, but may also break any project that depends upon them. In this paper we explore the use of Large Language Models (LLMs)…

The rapidly increasing size of large language models (LLMs) presents significant challenges in memory usage and computational costs. Quantizing both weights and activations can address these issues, with hardware-supported fine-grained…

Recently, researchers have proposed many multi-agent frameworks for function-level code generation, which aim to improve software development productivity by automatically generating function-level source code based on task descriptions. A…

Code generation with large language models (LLMs) is highly sensitive to token selection during decoding, particularly at uncertain decision points that influence program logic. While standard strategies such as greedy decoding treat all…

Reliable handling of code diffs is central to agents that edit and refactor repositories at scale. We introduce Diff-XYZ, a compact benchmark for code-diff understanding with three supervised tasks: apply (old code $+$ diff $\rightarrow$…

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing…

Code generation is increasingly critical for real-world applications. Still, diffusion-based large language models continue to struggle with this demand. Unlike free-form text, code requires syntactic precision; even minor structural…

Large Language Models (LLMs), particularly Code LLMs, have demonstrated impressive performance in code generation. Current research primarily focuses on the correctness of generated code, while efficiency remains less explored. Recent works…