Tootfinder

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino
https://arxiv.org/abs/2507.03051

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an extensive study aimed at advancing recent RL-based finetuning techniques for LLMs in the context of vulnerability detection. We start by highlighting key limitations of commonly adopted LLMs, such as their tendency to over-predict certain types of vulnerabiliti…

Adaptive Gate-Aware Mamba Networks for Magnetic Resonance Fingerprinting
Tianyi Ding, Hongli Chen, Yang Gao, Zhuang Xiong, Feng Liu, Martijn A. Cloos, Hongfu Sun
https://arxiv.org/abs/2507.03369

Adaptive Gate-Aware Mamba Networks for Magnetic Resonance Fingerprinting
Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computational cost and memory usage as the number of parameters increases, limiting its scalability to multi-parametric mapping. To address this, recent work has explored deep learning-based approaches as alternatives to DM. We propose GAST-Mamba, an end-to-end framework that combines a du…

Continual Recommender Systems
Hyunsik Yoo, SeongKu Kang, Hanghang Tong
https://arxiv.org/abs/2507.03861 https://arxiv.org/pdf/2507.03…

Continual Recommender Systems
Modern recommender systems operate in uniquely dynamic settings: user interests, item pools, and popularity trends shift continuously, and models must adapt in real time without forgetting past preferences. While existing tutorials on continual or lifelong learning cover broad machine learning domains (e.g., vision and graphs), they do not address recommendation-specific demands-such as balancing stability and plasticity per user, handling cold-start items, and optimizing recommendation metrics…

"Instead of calculators, we could sit at exams with certain books on our desks, filled with logarithm and trigonometry tables, featuring formulae for algebra, calculus, and geometry. French-speaking Swiss students might remember the ubiquitous “Formulaire et Tables” of the “Commissions romandes de mathématiques, de physique et de chimie”, published by the Éditions du Tricorne, that many generations of Swiss students used during their exams."

Banning, Adopting, Reckoning
Last month, OpenAI, the company (in)famous for their ChatGPT product, released a course called "ChatGPT Foundations for K-12 Educators", an event that has raised more than a few eyebrows, and even some outrage. We must have a serious conversation about the value of a bullshit generator in the context of teaching programming skills to new generations.

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Tao Xiong, Xavier Hu, Wenyan Fan, Shengyu Zhang
https://arxiv.org/abs/2507.00606

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and efficiency. We introduce Mixture of Reasoning (MoR), a training framework that embeds diverse reasoning strategies into LLMs for autonomous, task-adaptive reasoning without external prompt engineering. MoR has two phases: Thought Generation, creating reasoning chain t…

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
Mohammad Ali Alomrani, Yingxue Zhang, Derek Li, Qianyi Sun, Soumyasundar Pal, Zhanguang Zhang, Yaochen Hu, Rohan Deepak Ajwani, Antonios Valkanas, Raika Karimi, Peng Cheng, Yunzhou Wang, Pengyi Liao, Hanrui Huang, Bin Wang, Jianye Hao, Mark Coates
https://

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of task complexity, often overthinking simple problems while underthinking hard ones. This survey presents a comprehensive review of efficient test-time compute (TTC) strategies, which aim to improve the computational efficiency of LLM reasoning. We introduce a tw…

This https://arxiv.org/abs/2501.18878 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Integrated Sensing and Communication System Based on Radio Frequency Resonance Beam
To address the complex beam control in traditional multiple-input multiple-output (MIMO) systems, researchers have proposed adaptive beam alignment using retro-directive antenna (RDA) arrays. This approach creates echo resonance between the base station (BS) and user equipment (UE), significantly reducing computational load. However, conventional resonant beam systems (RBS) suffer from echo interference due to the shared uplink and downlink frequency. Therefore, this paper proposes an innovativ…

Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks
Tri Kurniawan Wijaya, Xinyang Shao, Gonzalo Fiz Pontiveros, Edoardo D'Amico
https://arxiv.org/abs/2506.03391

Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks
Recommender systems are pivotal in delivering personalized experiences across industries, yet their adoption and scalability remain hindered by the need for extensive dataset- and task-specific configurations. Existing systems often require significant manual intervention, domain expertise, and engineering effort to adapt to new datasets or tasks, creating barriers to entry and limiting reusability. In contrast, recent advancements in large language models (LLMs) have demonstrated the transform…

This https://arxiv.org/abs/2502.13943 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the …

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
Zhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu Wan
https://arxiv.org/abs/2506.04083

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
Recent Continual Learning (CL)-based Temporal Knowledge Graph Reasoning (TKGR) methods focus on significantly reducing computational cost and mitigating catastrophic forgetting caused by fine-tuning models with new data. However, existing CL-based TKGR methods still face two key limitations: (1) They usually one-sidedly reorganize individual historical facts, while overlooking the historical context essential for accurately understanding the historical semantics of these facts; (2) They preserv…