Tootfinder

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Kathleen C. Fraser, Hillary Dawkins, Isar Nejadgholi, Svetlana Kiritchenko
https://arxiv.org/abs/2506.17209

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the fine-tuning data does not contain any harmful content. We consider this to be a critical failure mode of LLMs due to the widespread uptake of fine-tuning, combined with the benign nature of the "attack". Most well-intentioned developers are likely unaware that th…

Model fine-tuning without compromising information access controls.
"Copilot Tuning" attaches fine-tuning datasets to LLMs while respecting your permissions. See how:
youtu.be/6udJzJAyT5I
#CopilotTuning #copilot

The Indian Pulsar Timing Array Data Release 2: I. Dataset and Timing Analysis
Prerna Rana, Pratik Tarafdar, Nobleson K, Churchil Dwivedi, Bhal Chandra Joshi, Debabrata Deb, Sushovan Mondal, M. A. Krishnakumar, Adya Shukla, Jaikhomba Singha, Himanshu Grover, Hemanga Tahbildar, Abhimanyu Susobhanan, Mayuresh Surnis, Shantanu Desai, Neelam Dhanda Batra, Aman Srivastava, Vinay Bharambe, Jibin Jose, Vaishnavi Vyasraj, Shebin Jose Jacob, Amarnath, Manpreet Singh, Zenia Zuraiq, Sarbartha Sen…

The Indian Pulsar Timing Array Data Release 2: I. Dataset and Timing Analysis
The Indian Pulsar Timing Array (InPTA) employs unique features of the upgraded Giant Metrewave Radio Telescope (uGMRT) to monitor dozens of the International Pulsar Timing Array (IPTA) millisecond pulsars (MSPs), simultaneously in the 300-500 MHz and the 1260-1460 MHz bands. This dual-band approach ensures that any frequency-dependent delays are accurately characterized, significantly improving the timing precision for pulsar observations, which is crucial for pulsar timing arrays. We present d…

TD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning
Jie He, Vincent Theo Willem Kenbeek, Zhantao Yang, Meixun Qu, Ezio Bartocci, Dejan Ni\v{c}kovi\'c, Radu Grosu
https://arxiv.org/abs/2507.16844

TD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning
We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual question-answer environment which allows engineers to input a set of TDs and ask design and verification queries regarding these TDs. We implemented TD-Interpreter with multimodal learning by fine-tuning LLaVA, a lightweight 7B Multimodal Large Language Model (MLLM). To a…

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Feng He, Zhenyang Liu, Marco Valentino, Zhixue Zhao
https://arxiv.org/abs/2506.18428

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual correction and bias mitigation. Despite this common practice, it remains unknown whether edits persist after fine-tuning or whether they are inadvertently reversed. This question has fundamental practical implications. For example, if fine-tuning removes prior edits, it could serve as a defence mechanism against hidden …

Micro-variations in timing and loudness affect music-evoked mental imagery https://www.nature.com/articles/s41598-025-12604-4 "repetitive quasi-isochronous drumming enhanced mental imagery vividness, with a stronger effect observed when the drumming contained random micro-variat…

Micro-variations in timing and loudness affect music-evoked mental imagery - Scientific Reports
Music can shape the vividness, sentiment, and content of directed mental imagery. Yet, the role of specific musical features in these effects remains elusive. One important aspect of human musical performances is the presence of micro-variations—small deviations in timbre, pitch, and timing, driven by motor and attentional processes. These variations enhance perceived “naturalness” compared to mechanical playing without such variations. Here, we investigated whether random micro-variation…

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
Boheng Li, Junjie Wang, Yiming Li, Zhiyang Hu, Leyi Qi, Jianshuo Dong, Run Wang, Han Qiu, Zhan Qin, Tianwei Zhang
https://arxiv.org/abs/2507.16329

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
Despite the integration of safety alignment and external filters, text-to-image (T2I) generative models are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to proactively identify diverse prompts that can elicit unsafe outputs from the T2I system (including the core generative model as well as potential external safety filters and other processing components), …

Dependent Dirichlet processes via thinning
Laura D'Angelo, Bernardo Nipoti, Andrea Ongaro
https://arxiv.org/abs/2506.18223 https://

Dependent Dirichlet processes via thinning
When analyzing data from multiple sources, it is often convenient to strike a careful balance between two goals: capturing the heterogeneity of the samples and sharing information across them. We introduce a novel framework to model a collection of samples using dependent Dirichlet processes constructed through a thinning mechanism. The proposed approach modifies the stick-breaking representation of the Dirichlet process by thinning, that is, setting equal to zero a random subset of the beta ra…

Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Zhihao Xu, Bixin Li, Lulu Wang
https://arxiv.org/abs/2507.16808 https://

Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization methods often rely on manual tuning and heuristics, which can be time-consuming and error-prone. Recent studies proposed to leverage Large Language Models(LLMs) to assist in RTL code optimization. LLMs can generate optimized code snippets based on natural language descriptions, potentially speeding up the optimization pro…

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
Yejing Wang, Shengyu Zhou, Jinyu Lu, Qidong Liu, Xinhang Li, Wenlin Zhang, Feng Li, Pengjie Wang, Jian Xu, Bo Zheng, Xiangyu Zhao
https://arxiv.org/abs/2506.16114

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks
Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily concentrate on developing powerful item tokenizers or advancing LLM decoding strategies to attain superior performance. However, the critical fine-tuning step in GR frameworks, which is essential for adapting LLMs to recommendation data, remains largely unexpl…