TontaubeV1 is a streaming text‑to‑speech model that preserves natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream, utterance duration, and acoustic refinements. The system supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).
By Fritz Cremer, Jonathan Cremer
SocialRL is a multi-turn reinforcement learning framework that refines large language models’ social intelligence. It uses PPO to propagate delayed outcome rewards across turns, enabling long‑horizon planning, and introduces six process reward dimensions—such as goal advancement and relational attunement—to capture the goal‑relationship trade‑off. A reward model provides fine‑grained scoring and a stage‑aware weight schedule prioritizes relationship building early, goal pursuit mid‑way, and balanced closure later, yielding an average 9.2 percentage‑point improvement in goal achievement across multiple social‑dialogue benchmarks.
By Jianing Wang, Xintao Wang, Aili Chen, Jie Shi, Hongcheng Guo, Jun Gao, Wenxuan Zhao, Chengkun Lang, Yuanli Guo, Yanghua Xiao
5-Dialects-BN is a new Bangla dialect benchmark that aligns Romanized transliteration with dialectal text, Standard Bangla, English, and subjectivity labels across five regional varieties. The dataset contains 6,000 manually annotated entries from Chittagong, Barisal, Noakhali, Sylhet, and Rangpur, each enriched with five aligned annotations produced and cross‑validated by native speakers and linguistics students. It supports tasks such as dialect identification, normalization, translation, subjectivity classification, and efficient fine‑tuning of multilingual LLMs.
By Md Mahir Jawad, Galib Mahmud Jim, Rafid Ahmed, Mir Sazzat Hossain, Md Fahim, Md Farhad Alam Bhuiyan
arXiv:2609.10321v1 Announce Type: new
Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...
By Hongyuan Zhang, Xianda Guo, Yanlun Peng, Qianlong Yang, Yubin Guo, Pinhan Fu, Mulin Chen, Xiaozhen Qiao, Ping Luo
arXiv:2609.09662v1 Announce Type: cross
Abstract: Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased pr...
By Weisi Yang, Stephen Xia
arXiv:2609.10397v1 Announce Type: cross
Abstract: Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is...
By Linghan Zhong, Jiyang Zhang, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric
arXiv:2609.08399v1 Announce Type: new
Abstract: Universal machine-learning interatomic potentials (u-MLIPs) aim to generalize across diverse configurations. Benchmarks enable reproducible evaluation...
By Ryuhei Okuno, Nontawat Charoenphakdee, Kaoru Hisama, Yuta Tsuboi
arXiv:2609.06059v1 Announce Type: new
Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to a...
By Yu Liu, Zhilin Liu, Zhiwei Yang, Shaojie Zhang, Zheyuan Deng, Tingwei Huang, Zhenbo Luo, Lei Jiang, Yanbing Liu, Pei Fu
arXiv:2609.09482v1 Announce Type: new
Abstract: Critical infrastructure location data is often incomplete and unevenly distributed globally, especially in developing regions. Earth observation founda...
By Justin Guthrie, Edward Oughton, Konrad Wessels, Matthew Rice, Isaac Corley
arXiv:2609.09507v1 Announce Type: new
Abstract: Learned image matching has experienced significant progress in recent years, culminating in robust and accurate matchers such as RoMa, whose robustness...
By David Nordstr\"om, Xinyue Zhang, Thibaut Loiseau, Vincent Lepetit, Fredrik Kahl
arXiv:2609.09528v1 Announce Type: new
Abstract: Video large language models (Video-LLMs) are increasingly used as the perceptual front end of world models, a role that assumes they can read motion: h...
By Dhairya Bhatia, Bishoy Galoaa, Oliver Fritsche, Shahid Kamal, Muhammad Obaidullah Abdul Salam, Umer Saleem, Om Rastogi, Frania Felix Chettiar, Nesli Erdogmus, Sarah Ostadabbas
arXiv:2609.09705v1 Announce Type: new
Abstract: Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts. Un...
By Shuoyi Chen, Yuejia Li, Mang Ye
arXiv:2609.06188v1 Announce Type: new
Abstract: Multimodal sentiment analysis and emotion recognition in conversations demand effective modeling of heterogeneous interactions across textual, acoustic...
By Pengfei Shao, Jisheng Dang, Jiawen Fang, Ning Liu, Wencan Zhang, Bimei Wang, Jingwen Zhao, Jianhuang Lai, Qi Tian, Tat-Seng Chua
arXiv:2609.10540v1 Announce Type: new
Abstract: Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanisms for maintaining persistent w...
By Zheng-Hui Huang, Guixu Lin, Jiacheng Lin, Yi-Chuan Huang, Ruihan Yu, Muyao Niu, Siqi Yang, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang
arXiv:2608.25461v1 Announce Type: cross
Abstract: Using conditional image generators, texture artists can explore many single-view looks for an existing 3D shape. Despite impressive progress, state-o...
By Chenyue Cai, Anita Hu, James Lucas, Szymon Rusinkiewicz, Masha Shugrina
arXiv:2608.21244v2 Announce Type: replace
Abstract: Anomaly detection aims to identify observations that deviate from normal patterns. Recent work uses pretrained vision-language models (VLMs) for tr...
By Inpyo Song, Jangwon Lee
arXiv:2609.09945v1 Announce Type: cross
Abstract: Machine learning-based credit scoring is increasingly central to Peer-to-Peer (P2P) lending, yet its resilience to adversarial manipulation, where ap...
By Gijs A. F. Niewzwaag, Marijn G. S. Veth, Manuele Massei, Marcos R. Machado
arXiv:2508.10970v2 Announce Type: replace-cross
Abstract: Bioprocesses are central to modern biotechnology, enabling sustainable production of pharmaceuticals, specialty chemicals, cosmetics, and foo...
By Adrian Martens, Mathias Neufang, Alessandro Butt\'e, Moritz von Stosch, Antonio del Rio Chanona, Laura Marie Helleckes
FreqBLiMP is a frequency‑controlled extension of the BLiMP minimal‑pair benchmark that regenerates all 67 paradigms under explicit Zipf‑frequency regimes while preserving grammatical contrasts. The study evaluates multiple open‑weight LLM families and finds that lower lexical frequency consistently reduces sentence likelihood, yet overall contrastive acceptability accuracy drops only modestly. However, the stability in aggregate accuracy hides significant variability across linguistic phenomena, with models remaining robust on overt morphosyntactic generalization but degrading on lemma‑specific tasks.
By Tyrone White, Yuki Arase
The paper introduces SAFE, an SNR‑adaptive frequency estimator that combines a time‑frequency image neural network (TFINet) to enhance weak tone components at low SNR with an SNR‑based frequency selector (SFS) that chooses the appropriate estimator for each tone. SAFE achieves a 13.00% false negative rate across –10 dB to 0 dB SNR, improving over state‑of‑the‑art methods by 13.04% and reducing nearest‑neighbor RMSE by 56.67%. Real‑world experiments confirm its robustness in cluttered environments.
By Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung, Seung-Hyun Kong