Tootfinder

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki, Jonathan Bell, Arjun Guha
https://arxiv.org/abs/2509.21891

AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the changes that implement that intent. However, much of the previously collected data is noisy: commit messages are terse, human-written commits commingle several unrelated edits, and many commits come from simple, rule-based bots. The recent adoption of softwar…

Lattice-induced spin dynamics in Dirac magnet CoTiO3
Andrey Baydin, Jiaming Luo, Zhiren He, Jacques Doumani, Tong Lin, Fuyang Tay, Jiaming He, Jianshi Zhou, Guru Khalsa, Junichiro Kono, Hanyu Zhu
https://arxiv.org/abs/2508.20354

Lattice-induced spin dynamics in Dirac magnet CoTiO3
Spin-lattice coupling is crucial for understanding the spin transport and dynamics for spintronics and magnonics applications. Recently, cobalt titanate (CoTiO3), an easy-plane antiferromagnet, has been found to host axial phonons with a large magnetic moment, which may originate from spin-lattice coupling. Here, we investigate the effect of light-driven lattice dynamics on the magnetic properties of CoTiO3 using time-resolved spectroscopy with a THz pump and a magneto-optic probe. We found res…

A provision in the recently passed Wisconsin state budget that diverts $2.2 million annually from schools to fund 12 Milwaukee County prosecutors may violate the Wisconsin Constitution.
The positions had previously been paid for with federal funding that is set to expire.
The budget act redirects all traffic fines and forfeiture revenues in Milwaukee County to the Milwaukee County District Attorney’s Office to fund 12 positions.

State Budget Shifts Money from Schools to Milwaukee Prosecutors
$2.2 million per year diverted from city schools could violate state constitution.

The Las Vegas Raiders Should Bring Back A Fan Favorite The Carolina Panthers Recently Cut https://heavy.com/sports/nfl/las-vegas-raiders/bring-back-hunter-renfrow/?adt_ei=[email]

Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
Zhen-Hao Wen, Yan Wang, Ji Feng, Han-Jia Ye, De-Chuan Zhan, Da-Wei Zhou
https://arxiv.org/abs/2509.22645

Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task. However, existing approaches often rely on simplistic templates, such as "a photo of a [CLASS]", which overlook the hierarchical nature of visual concepts. For example, recognizing "cat" versus "car" depends on coarse-grained cues, while distinguishing "cat" from "lio…

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras
https://arxiv.org/abs/2508.19827

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?
Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the dynamics and faithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings reveal differences in how these models rely on CoT, and show that CoT influence and faithfulness are not always aligned.

Can We End the Cat-and-Mouse Game? Simulating Self-Evolving Phishing Attacks with LLMs and Genetic Algorithms
Seiji Sato, Tetsushi Ohki, Masakatsu Nishigaki
https://arxiv.org/abs/2507.21538

Can We End the Cat-and-Mouse Game? Simulating Self-Evolving Phishing Attacks with LLMs and Genetic Algorithms
Anticipating emerging attack methodologies is crucial for proactive cybersecurity. Recent advances in Large Language Models (LLMs) have enabled the automated generation of phishing messages and accelerated research into potential attack techniques. However, predicting future threats remains challenging due to reliance on existing training data. To address this limitation, we propose a novel framework that integrates LLM-based phishing attack simulations with a genetic algorithm in a psychologic…

HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions
Jing Wang, Shang Liu, Yao Lu, Zhiyao Xie
https://arxiv.org/abs/2507.21485 https://…

HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions
High-level synthesis (HLS) accelerates hardware design by enabling the automatic translation of high-level descriptions into efficient hardware implementations. However, debugging HLS code is a challenging and labor-intensive task, especially for novice circuit designers or software engineers without sufficient hardware domain knowledge. The recent emergence of Large Language Models (LLMs) is promising in automating the HLS debugging process. Despite the great potential, three key challenges pe…

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
Yuqiao Meng, Luoxi Tang, Feiyang Yu, Jinyuan Jia, Guanhua Yan, Ping Yang, Zhaohan Xi
https://arxiv.org/abs/2509.23573

Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident response. While recent work has shown that LLMs can support a wide range of CTI tasks such as threat analysis, vulnerability detection, and intrusion defense, significant performance gaps persist in practical deployments. In this paper, we investigate the intrins…