Related papers: The KoLMogorov Test: Compression by Code Generatio…

Chain-of-thought (CoT) prompting improves LLM reasoning but incurs high latency and memory cost due to verbose traces, motivating CoT compression with preserved correctness. Existing methods either shorten CoTs at the semantic level, which…

Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation. While existing memory-efficient methods largely focus on…

Recent breakthroughs in Large Reasoning Models (LRMs) have demonstrated that extensive Chain-of-Thought (CoT) generation is critical for enabling intricate cognitive behaviors, such as self-verification and backtracking, to solve complex…

Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require…

Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has…

Compressing long chain-of-thought (CoT) from large language models (LLMs) is an emerging strategy to improve the reasoning efficiency of LLMs. Despite its promising benefits, existing studies equally compress all thoughts within a long CoT,…

Code generation problems differ from common natural language problems - they require matching the exact syntax of the target language, identifying happy paths and edge cases, paying attention to numerous small details in the problem spec,…

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

Key-value~(KV) caching is an important technique to accelerate the inference of large language models~(LLMs), but incurs significant memory overhead. To compress the size of KV cache, existing methods often compromise precision or require…

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs offer promise for automation, both general-purpose and…

This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experiments across eight diverse datasets, focusing on four…

Large language models (LLMs), both proprietary and open-source, have demonstrated remarkable capabilities across various natural language processing tasks. However, they face significant limitations in legal reasoning tasks. Proprietary…

Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens, poses a significant challenge. Existing training-based…

Kernel two-sample testing provides a powerful framework for distinguishing any pair of distributions based on $n$ sample points. However, existing kernel tests either run in $n^2$ time or sacrifice undue power to improve runtime. To address…

Robust statistical inference often faces a severe computational-statistical gap when dealing with complex parameter spaces. We investigate minimax signal detection in the Gaussian sequence model under strong $\epsilon$-contamination, where…

With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding…

Low-rank compression, a popular model compression technique that produces compact convolutional neural networks (CNNs) with low rankness, has been well-studied in the literature. On the other hand, low-rank training, as an alternative way…

The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, that can be described by a set of features, can…

Current Large Language Models (LLMs) face three major challenges: context length limitations, high inference costs, and catastrophic forgetting during continual learning. While Mixture-of-Experts (MoE) architectures mitigate some of these…