Tootfinder

Composition and Alignment of Diffusion Models using Constrained Learning
Shervin Khalafi, Ignacio Hounie, Dongsheng Ding, Alejandro Ribeiro
https://arxiv.org/abs/2508.19104 http…

Composition and Alignment of Diffusion Models using Constrained Learning
Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compliance with user requirements, two commonly used methods are: (i) Alignment, which involves fine-tuning a diffusion model to align it with a reward; and (ii) Composition, which combines several pre-trained diffusion models, each emphasizing a desirable attribute in the generated outputs. However, trade-offs often arise…

PRIMMDebug: A Debugging Teaching Aid For Secondary Students
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.18875 https://arxiv.org/pdf/2508.18875

PRIMMDebug: A Debugging Teaching Aid For Secondary Students
Debugging is often a challenging and infuriating experience for secondary school students learning their first text-based programming language. Many students resort to ineffective debugging strategies, making success with solving errors unlikely and emotional distress common. Developing tools that encourage students to adopt a more systematic and reflective approach to debugging is therefore an important, but lacking, area of research. This paper presents PRIMMDebug, a debugging teaching aid fo…

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo
https://arxiv.org/abs/2508.17868

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this limitation by distilling VoiceGrad into a one-step diffusion model. However, it still requires a computationally intensive content encoder to disentangle the speaker's identity and content, which slows conversion. Therefore, we propose FasterVoiceGrad, a novel one-step diffusion-b…

Unbiased Parameter Estimation of Partially Observed Diffusions using Diffusion Bridges
Miguel Alvarez, Ajay Jasra
https://arxiv.org/abs/2509.21015 https://…

Unbiased Parameter Estimation of Partially Observed Diffusions using Diffusion Bridges
In this article we consider the estimation of static parameters for partially observed diffusion processes with discrete-time observations over a fixed time interval. In particular, when one only has access to time-discretized solutions of the diffusions we build upon the works of \cite{ub_par,ub_grad} to devise a method that can estimate the parameters without time-discretization bias. We leverage an identity associated to the gradient of the log-likelihood associated to diffusion bridges, whi…

The Hands-Up Problem and How to Deal With It: Secondary School Teachers' Experiences of Debugging in the Classroom
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.18861

The Hands-Up Problem and How to Deal With It: Secondary School Teachers' Experiences of Debugging in the Classroom
Debugging is a vital but challenging skill for beginner programmers to learn. It is also a difficult skill to teach. For secondary school teachers, who may lack time or relevant knowledge, honing students' understanding of debugging can be a daunting task. Despite this, little research has explored their perspectives of debugging. To this end, we investigated secondary teachers' experiences of debugging in the classroom, with a focus on text-based programming. Through thematic analysis of nine …

Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning
Xuan Zhang, Zhijian Zhou, Weidi Xu, Yanting Miao, Chao Qu, Yuan Qi
https://arxiv.org/abs/2508.16524 https://

Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning
Enabling neural networks to learn complex logical constraints and fulfill symbolic reasoning is a critical challenge. Bridging this gap often requires guiding the neural network's output distribution to move closer to the symbolic constraints. While diffusion models have shown remarkable generative capability across various domains, we employ the powerful architecture to perform neuro-symbolic learning and solve logical puzzles. Our diffusion-based pipeline adopts a two-stage training strategy:…

Chiefs vs. Raiders: Key takeaways from the NFL’s fiercest division rivalry https://raiderramble.com/2025/10/23/chiefs-vs-raiders-key-takeaways-from-the-nfls-fiercest-division-rivalry/

Debiasing Multilingual LLMs in Cross-lingual Latent Space
Qiwei Peng, Guimin Hu, Yekun Chai, Anders S{\o}gaard
https://arxiv.org/abs/2508.17948 https://arx…

Debiasing Multilingual LLMs in Cross-lingual Latent Space
Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying these methods to LLM representations, revealing their limited effectiveness across languages. In this work, we therefore propose to perform debiasing in a joint latent space rather than directly on LLM representations. We construct a well-aligned cross-lingual latent space using an autoencoder trained on parallel TED…

DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
Qinyao Li, Xiaoyang Zheng, Qihang Zhao, Ke Xu, Zhongbo Sun, Chao Wang, Chenyi Lei, Han Li, Wenwu Ou
https://arxiv.org/abs/2508.17754

DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou
Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users' broad interests based on the filtered historical behaviors, they typically under-exploit explicit alignment between a user's real-time intent (represented by the user query) and their past actions. In this paper, we propose DiffusionGS, a novel and scalable approach powered by generative models. Our key insight is t…

🇺🇦 #NowPlaying on KEXP's #SeekAndDestroy
Division Speed:
🎵 The Iron Wings of Death
#DivisionSpeed
https://dyingvictimsproductions.bandcamp.com/track/the-iron-wings-of-death
https://open.spotify.com/track/4GXPvTMLDsyTtgSWThofs0