Aaron Chan

Total preprojective algebras

Aaron Chan, Osamu Iyama, René Marczinzik

Abstract We introduce total preprojective algebras $\Psi $ of path algebras of Dynkin quivers $kQ$ and prove that they are isomorphic to $2$-Auslander algebras of preprojective algebras $\Pi $ of $kQ$. In particular, $\Psi $ has global dimension $3$ and dominant dimension …

jp, de (code pays fourni par la source)

Composer 2 Technical Report

Cursor Research, :, Aaron Chan, Ahmed Shalaby et autres

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to …

Composer 2 Technical Report

Cursor Research, :, Aaron Chan, Ahmed Shalaby et autres

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to …

Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference

A. Longfei Tian, Alan H.B. Wu, Aaron Chan, B Zhang

Decentralized large language model (LLM) inference promises transparent and censorship resistant access to advanced AI, yet existing verification approaches struggle to scale to modern models. Proof of Quality (PoQ) replaces cryptographic verification of computation with consensus over output quality, but the original …

Tilting theoretic approach to quasi-hereditary structures

Takahide Adachi, Aaron Chan, Mayu Tsukamoto

A quasi-hereditary algebra is an algebra equipped with a certain partial order $\unlhd$ on its simple modules. Such a partial order -- called a quasi-hereditary structure -- gives rise to a characteristic tilting module $T_{\unlhd}$ by a classical result due to Ringel. …

1371-P: Identifying Facilitators and Barriers to Outpatient Follow-up among Emergency Department Patients with Newly Diagnosed Diabetes

HAESEUNG YI, TAMMY A. FLORES, CRYSTAL SO, Aaron Chan et autres

Introduction and Objective: Coordination of outpatient care is critical for managing chronic diseases, especially for newly diagnosed diabetes. This study sought to identify the facilitators and barriers to outpatient follow-up among emergency department (ED) patients who were identified as having previously undiagnosed …

1333-P: Using Machine-Learning Algorithms to Predict Follow-up among Emergency Department Patients with Newly Diagnosed Diabetes

Daniel B. Neill, Z. H. Qu, Zhenyu Shi, TAMMY A. FLORES et autres

Introduction and Objective: Expanding diabetes screening to emergency departments (ED) identifies new diabetes cases, especially among patients with poor access to care. This study leveraged electronic health record (EHR) data to identify key factors that predicted lack of follow-up care among newly …

Periodic trivial extension algebras and fractionally Calabi-Yau algebras

Aaron Chan, Erik Darpö, Osamu Iyama, René Marczinzik

Auslander-Reiten's Cohen-Macaulay algebras and contracted preprojective algebras

Aaron Chan, Osamu Iyama, René Marczinzik

Auslander and Reiten called a finite dimensional algebra $A$ over a field Cohen-Macaulay if there is an $A$-bimodule $W$ which gives an equivalence between the category of finitely generated $A$-modules of finite projective dimension and the category of finitely generated $A$-modules of …

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Anisha Agarwal, Aaron Chan, Shubham Chandel, Jinu Jang et autres

The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development. LLMs such as OpenAI GPT-3.5/4 and Code Llama offer the potential to significantly augment developer productivity by serving as intelligent, chat-driven programming …

RESPROMPT: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi et autres

Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi, Hamed Firooz, Yinglong Xia, Bugra Akyildiz, Yizhou Sun, Jinchao Li, Qifan Wang, Asli Celikyilmaz. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume …

us (code pays fourni par la source)

Tailoring Self-Rationalizers with Multi-Reward Distillation

Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu et autres

Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B parameter GPT-3); and 2) focuses largely on downstream performance, ignoring the semantics …