Related papers: ECO: Enhanced Code Optimization via Performance-Aw…

Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally…

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by…

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…

Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to…

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapid evolution of new hardware architectures and software…

Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus…

Improvements in the performance of computing systems, driven by Moore's Law, have transformed society. As such hardware-driven gains slow down, it becomes even more important for software developers to focus on performance and efficiency…

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using…

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

In this paper, we study the peak-aware energy scheduling problem using the competitive framework with machine learning prediction. With the uncertainty of energy demand as the fundamental challenge, the goal is to schedule the energy output…

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code…

Prompting with natural language instructions has recently emerged as a popular method of harnessing the capabilities of large language models. Given the inherent ambiguity present in natural language, it is intuitive to consider the…

Recent advancements in large language models (LLMs) have been driven by their emergent reasoning capabilities, particularly through long chain-of-thought (CoT) prompting, which enables thorough exploration and deliberation. Despite these…

The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy…

Profile Guided Optimization (PGO) uses runtime profiling to direct compiler optimization decisions, effectively combining static analysis with actual execution behavior to enhance performance. Runtime profiles, collected through…

The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding of scaling properties. This is challenged by: 1) the…

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…