TBD

This paper introduces Turbo-TTS, a novel diffusion-based model for text-to-speech (TTS) synthesis. Diffusion models leverage stochastic differential equations (SDEs) to generate high-fidelity speech. To enhance the sampling efficiency of the diffusion process, we propose a new ordinary differential equation (ODE) solver and integrate consistency modeling principles into the TTS framework, leading to significant improvements in synthesized speech quality. Our approach discretizes the underlying SDE describing diffusion into a probability flow ODE (PF ODE). This PF ODE shares the same marginal distribution as the original SDE but offers improved tractability for numerical solution. Experimental evaluations demonstrate that Turbo-TTS produces high-quality speech with substantially reduced computational requirements. The model achieves low-latency synthesis through single-step sampling (NFE = 1, RTF = 0.0074), indicating strong suitability for real-time applications.

Although Large Audio-Language Models (LALMs) have exhibited outstanding performance in auditory understanding, their performance in affective computing scenarios, particularly in emotion recognition, reasoning, and subtle sentiment differentiation, remains suboptimal. Recent advances in Reinforcement Learning (RL) have shown promise in improving LALMs’ reasoning abilities. However, two critical challenges hinder the direct application of RL techniques to Speech Emotion Recognition (SER) tasks (1) convergence instability caused by ambiguous emotional boundaries and (2) limited reasoning ability when using relatively small models (e.g., 7B-parameter architectures). To overcome these limitations, we introduce EMO-RL, a novel framework incorporating reinforcement learning with two key innovations Emotion Similarity-Weighted Reward (ESWR) and Explicit Structured Reasoning (ESR). Built upon pretrained LALMs, our method employs group-relative policy optimization with emotion constraints. Comprehensive experiments demonstrate that our EMO-RL training strategies can significantly enhance the emotional reasoning capabilities of LALMs, attaining state-of-the-art results on both the MELD and IEMOCAP datasets, and cross-dataset experiments prove the strong superiority of generalization.

TBD

Prompt learning has become an efficient paradigm for adapting CLIP to downstream tasks. Compared with traditional fine-tuning, prompt learning optimizes a few parameters yet yields highly competitive results, especially appealing in federated learning for computational efficiency. engendering domain shift among clients and posing a formidable challenge for downstream-task adaptation. Existing federated domain generalization (FDG) methods based on prompt learning typically learn soft prompts from training samples, replacing manually designed prompts to enhance the generalization ability of federated models. However, these learned prompts exhibit limited diversity and tend to ignore information from unknown domains. We propose a novel and effective method from a generative perspective for handling FDG tasks, namely federated domain generalization with domain-specific soft prompts generation (FedDSPG). Specifically, during training, we introduce domain-specific soft prompts (DSPs) for each domain and integrate content and domain knowledge into the generative model among clients. In the inference phase, the generator is utilized to obtain DSPs for unseen target domains, thus guiding downstream tasks in unknown domains. Comprehensive evaluations across several public datasets confirm that our method outperforms existing strong baselines in FDG, achieving state-of-the-art results.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

The International Conference on Neural Information Processing (ICONIP) is an annual conference of the Asia Pacific Neural Network Society (APNNS). ICONIP brings together attendees from around the world, diverse disciplines and professions including researchers, academics, and industry experts, all working collaboratively to tackle real-world challenges and to contribute to the society.

The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) is set to be a major event for researchers, practitioners, and enthusiasts in the field of natural language processing (NLP). Taking place from November 5th to 9th in Suzhou, China, this conference promises to showcase cutting-edge research, innovative applications, and thought-provoking discussions.

ICCV is hosted by the Institute of Electrical and Electronics Engineers (IEEE). It is the premier international computer vision event, and its proceedings represent the latest development trends and highest level in the field of computer vision. It is highly regarded in the industry and is the top - level conference with the lowest acceptance rate among the three major computer vision conferences.

The 21st International Conference on Information Security and Cryptology (INSCRYPT 2025) will be held in Xi’an from October 19th to October 21st, 2025, organized by the State Key Laboratry of Integrated Services Networks (ISN) of Xidian University and the State Key Laboratory of Cyberspace Security Defense (SKLCSD) of the Institute of Information Engineering of Chinese Academy of Science. Inscrypt 2025 seeks high-quality research contributions in the form of well developed papers. Topics of interest encompass research advances in ALL areas of information security, cryptology, and their applications. The conference proceedings will be published by Springer-Verlag in LNCS series.