Tootfinder

Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages
Andrea Nasuto, Stefano Maria Iacus, Francisco Rowe, Devika Jain
https://arxiv.org/abs/2508.06435

Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages
Large language models (LLMs) are transforming social-science research by enabling scalable, precise analysis. Their adaptability raises the question of whether knowledge acquired through fine-tuning in a few languages can transfer to unseen languages that only appeared during pre-training. To examine this, we fine-tune lightweight LLaMA 3.2-3B models on monolingual, bilingual, or multilingual data sets to classify immigration-related tweets from X/Twitter across 13 languages, a domain character…

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Kevin Rojas, Jiahe Lin, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Molei Tao, Wei Deng
https://arxiv.org/abs/2510.08554

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning to DLMs remains an open challenge because of the intractable likelihood. Pioneering work such as diffu-GRPO estimated token-level likelihoods via one-step unmasking. While computationally efficient, this approach is severely biased. A more principled foundat…

DiFlow-TTS: Discrete Flow Matching with Factorized Speech Tokens for Low-Latency Zero-Shot Text-To-Speech
Ngoc-Son Nguyen, Hieu-Nghia Huynh-Nguyen, Thanh V. T. Tran, Truong-Son Hy, Van Nguyen
https://arxiv.org/abs/2509.09631

DiFlow-TTS: Discrete Flow Matching with Factorized Speech Tokens for Low-Latency Zero-Shot Text-To-Speech
Zero-shot Text-to-Speech (TTS) aims to synthesize high-quality speech that mimics the voice of an unseen speaker using only a short reference sample, requiring not only speaker adaptation but also accurate modeling of prosodic attributes. Recent approaches based on language models, diffusion, and flow matching have shown promising results in zero-shot TTS, but still suffer from slow inference and repetition artifacts. Discrete codec representations have been widely adopted for speech synthesis,…

Constrained Natural Language Action Planning for Resilient Embodied Systems
Grayson Byrd, Corban Rivera, Bethany Kemp, Meghan Booker, Aurora Schmidt, Celso M de Melo, Lalithkumar Seenivasan, Mathias Unberath
https://arxiv.org/abs/2510.06357

Constrained Natural Language Action Planning for Resilient Embodied Systems
Replicating human-level intelligence in the execution of embodied tasks remains challenging due to the unconstrained nature of real-world environments. Novel use of large language models (LLMs) for task planning seeks to address the previously intractable state/action space of complex planning tasks, but hallucinations limit their reliability, and thus, viability beyond a research context. Additionally, the prompt engineering required to achieve adequate system performance lacks transparency, a…

Automated Program Repair of Uncompilable Student Code
Griffin Pitts, Aum Pandya, Darsh Rank, Tirth Bhatt, Muntasir Hoq, Bita Akram
https://arxiv.org/abs/2510.06187 https://

Automated Program Repair of Uncompilable Student Code
A significant portion of student programming submissions in CS1 learning environments are uncompilable, limiting their use in student modeling and downstream knowledge tracing. Traditional modeling pipelines often exclude these cases, discarding observations of student learning. This study investigates automated program repair as a strategy to recover uncompilable code while preserving students' structural intent for use in student modeling. Within this framework, we assess large language model…

Super-slowly rotating Ap (ssrAp) stars: New spectroscopic observations
Gautier Mathys, Daniel L. Holdsworth, Marina Giarrusso, Donald W. Kurtz. Giovanni Catanzaro, Francesco Leone
https://arxiv.org/abs/2509.05457

Super-slowly rotating Ap (ssrAp) stars: New spectroscopic observations
The rotation periods of Ap stars range over five to six orders of magnitude. The origin of their differentiation remains unknown. We carry out a systematic study of the longest period Ap stars to gain insight into their properties. We analyse newly obtained spectra of a sample of super-slowly rotating Ap (ssrAp) star candidates identified by a TESS photometric survey to confirm that their projected equatorial velocity v sin i is consistent with (very) long rotation periods, to obtain a first de…

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
Long Li, Jiaran Hao, Jason Klein Liu, Zhijian Zhou, Xiaoyu Tan, Wei Chu, Zhe Wang, Shirui Pan, Chao Qu, Yuan Qi
https://arxiv.org/abs/2509.07430

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance (Pass@k) despite improvements in single-attempt accuracy (Pass@1). This is often accompanied by catastrophic forgetting, where models lose previously acquired skills. While various methods have been proposed, the choice and function of the divergence term have been surprisingly unexamined as a proactive solution. We argu…

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Lee Kezar, Zed Sehyr, Jesse Thomason
https://arxiv.org/abs/2509.04745 https://

Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization
Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlations that hinder out-of-vocabulary performance. This work investigates two phonological inductive biases: Parameter Disentanglement, an architectural bias, and Phonological Semi-Sup…

MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding
Weifan Zhang, Tingguang Li, Yuzhen Liu
https://arxiv.org/abs/2508.05021 https://

MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding
Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs), enhanced with two human-inspired mechanisms: perspective-based active grounding, which dynamically adjusts the robot's viewpoint for improved visual inspection, and historical memory backtracking, which enables the system to retain and re-evaluate uncertain obser…

Improving Generalization of Language-Conditioned Robot Manipulation
Chenglin Cui, Chaoran Zhu, Changjae Oh, Andrea Cavallaro
https://arxiv.org/abs/2508.02405 https://

Improving Generalization of Language-Conditioned Robot Manipulation
The control of robots for manipulation tasks generally relies on visual input. Recent advances in vision-language models (VLMs) enable the use of natural language instructions to condition visual input and control robots in a wider range of environments. However, existing methods require a large amount of data to fine-tune VLMs for operating in unseen environments. In this paper, we present a framework that learns object-arrangement tasks from just a few demonstrations. We propose a two-stage f…