Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

3 Mar 2025 · Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, Weizhen Bian, Zhen Ye, Sitong Cheng, Ruibin Yuan, Zhixian Zhao, Xinfa Zhu, Jiahao Pan, Liumeng Xue, Pengcheng Zhu, Yunlin Chen, Zhifei Li, Xie Chen, Lei Xie, Yike Guo, Wei Xue ·

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Paper: https://arxiv.org/pdf/2503.01710v1.pdf

Code: https://github.com/sparkaudio/spark-tts

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://xn--r1a.website/DataScienceT

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

26 Mar 2025 · Salaheddin Alzubi, Creston Brooks, Purva Chiniya, Edoardo Contente, Chiara von Gerlach, Lucas Irwin, Yihan Jiang, Arda Kaz, Windsor Nguyen, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath ·

We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and completes it by orchestrating a sequence of actions that includes calling tools, one of which is the Open Search Tool. Open Search Tool is a novel web search tool that outperforms proprietary counterparts. Together with powerful open-source reasoning LLMs, such as DeepSeek-R1, ODS nearly matches and sometimes surpasses the existing state-of-the-art baselines on two benchmarks: SimpleQA and FRAMES. For example, on the FRAMES evaluation benchmark, ODS improves the best existing baseline of the recently released GPT-4o Search Preview by 9.7% in accuracy. ODS is a general framework for seamlessly augmenting any LLMs -- for example, DeepSeek-R1 that achieves 82.4% on SimpleQA and 30.1% on FRAMES -- with search and reasoning capabilities to achieve state-of-the-art performance: 88.3% on SimpleQA and 75.3% on FRAMES.

Paper: https://arxiv.org/pdf/2503.20201v1.pdf

Code: https://github.com/sentient-agi/opendeepsearch

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://xn--r1a.website/DataScienceT

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

10 Feb 2025 · Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, Yan-Pei Cao ·

Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.

Paper: https://arxiv.org/pdf/2502.06608v3.pdf

Codes:
https://github.com/VAST-AI-Research/TripoSG
https://github.com/tencent/flashvdm

Dataset: 100poisonMpts

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://xn--r1a.website/DataScienceT

🤖🧠 Ling-1T by inclusionAI: The Future of Smarter, Faster and More Efficient AI Models

🗓️ 09 Oct 2025
📚 AI News & Trends

Artificial Intelligence is evolving at lightning speed and inclusionAI’s Ling-1T is one of the most exciting innovations leading the charge. Built on the advanced Ling 2.0 architecture, Ling-1T is a trillion-parameter model designed to combine incredible reasoning power, speed and scalability in one open-source system. Image Source : Hugging Face Unlike many AI models that ...

#Ling1T #inclusionAI #ArtificialIntelligence #OpenSourceAI #LargeLanguageModels #AIArchitecture

🤖🧠 Quivr AI: Building Your Second Brain with Open-Source Generative Intelligence

🗓️ 12 Oct 2025
📚 AI News & Trends

In the rapidly evolving landscape of artificial intelligence, developers and businesses are seeking solutions that merge flexibility, power, and simplicity. Enter Quivr — an open-source framework designed to help you build your own “second brain” powered by Generative AI. Whether you’re an indie developer, startup founder or enterprise engineer, it makes it possible to integrate ...

#QuivrAI #SecondBrain #GenerativeAI #OpenSourceAI #AIFramework #AIProductivity

🤖🧠 HunyuanWorld-Mirror: Tencent’s Breakthrough in Universal 3D Reconstruction

🗓️ 03 Nov 2025
📚 AI News & Trends

The race toward achieving universal 3D understanding has reached a significant milestone with Tencent’s HunyuanWorld-Mirror, a cutting-edge open-source model designed to revolutionize 3D reconstruction. In an era dominated by visual intelligence and immersive digital experiences, this new model stands out by offering a feed-forward, geometry-aware framework that can predict multiple 3D outputs in a single ...

#HunyuanWorld #Tencent #3DReconstruction #UniversalAI #GeometryAware #OpenSourceAI

✨WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

📝 Summary:
WebSailor is a post-training method that teaches open-source AI models to systematically reduce uncertainty in complex information-seeking tasks. Using synthetic high-uncertainty tasks and an RL algorithm, it enables open-source agents to match the performance of proprietary systems.

🔹 Publication Date: Published on Sep 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.13305
• PDF: https://arxiv.org/pdf/2509.13305
• Project Page: https://tongyi-agent.github.io/blog/
• Github: https://tongyi-agent.github.io/blog/

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #ReinforcementLearning #OpenSourceAI #AIAgents #MachineLearning

✨InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

📝 Summary:
InternVL3 introduces a native multimodal pre-training paradigm, jointly learning from multimodal and text data to overcome conventional alignment challenges. This unified approach, combined with advanced techniques, achieves state-of-the-art performance on multimodal tasks, rivaling proprietary m...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.10479
• PDF: https://arxiv.org/pdf/2504.10479
• Project Page: https://internvl.github.io/blog/2025-04-11-InternVL-3.0/

🔹 Models citing this paper:
• https://huggingface.co/OpenGVLab/InternVL3-78B
• https://huggingface.co/OpenGVLab/InternVL3_5-241B-A28B
• https://huggingface.co/OpenGVLab/InternVL3-8B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/OpenGVLab/MMPR-v1.2-prompts

✨ Spaces citing this paper:
• https://huggingface.co/spaces/AntResearchNLP/ViLaBench
• https://huggingface.co/spaces/TIGER-Lab/MEGA-Bench
• https://huggingface.co/spaces/prithivMLmods/Tiny-VLMs-Lab

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MultimodalAI #DeepLearning #AIResearch #OpenSourceAI #GenerativeAI

🤖🧠 vLLM Semantic Router: The Next Frontier in Intelligent Model Routing for LLMs

🗓️ 11 Nov 2025
📚 AI News & Trends

As large language models (LLMs) continue to evolve, organizations face new challenges in optimizing performance, accuracy and cost across various AI workloads. Running multiple models efficiently – each specialized for specific tasks has become essential for scalable AI deployment. Enter vLLM Semantic Router, an open-source innovation that introduces a new layer of intelligence to the ...

#vLLMSemanticRouter #LargeLanguageModels #AIScaling #ModelRouting #OpenSourceAI #LLMOptimization

🤖🧠 Plandex AI: The Future of Autonomous Coding Agents for Large-Scale Development

🗓️ 11 Nov 2025
📚 AI News & Trends

As software development becomes increasingly complex, developers are turning to AI tools that can manage, understand and automate large portions of the coding workflow. Among the most promising innovations in this space is Plandex AI, an open-source terminal-based coding agent designed for real-world, large-scale projects. Unlike simple AI coding assistants that handle small snippets, Plandex ...

#PlandexAI #AutonomousCoding #LargeScaleDevelopment #AICoding #OpenSourceAI #CodeAutomation

🤖🧠 Bytebot: The Future of AI Desktop Automation

🗓️ 12 Nov 2025
📚 AI News & Trends

In the era of rapid digital transformation, automation is the driving force behind business efficiency and innovation. While most AI agents are limited to browsers or APIs, a groundbreaking open-source project called Bytebot has redefined what AI can achieve. Bytebot introduces a self-hosted AI desktop agent — a virtual computer that performs complex, multi-step tasks ...

#Bytebot #AIDesktopAutomation #SelfHostedAI #OpenSourceAI #AIAgents #TaskAutomation

✨MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

📝 Summary:
MiroThinker v1.0 is an open-source research agent introducing 'interactive scaling.' It trains models with reinforcement learning for deeper agent-environment interactions, performing up to 600 tool calls per task. This achieves state-of-the-art performance and establishes interaction depth as a ...

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11793
• PDF: https://arxiv.org/pdf/2511.11793
• Project Page: https://dr.miromind.ai/
• Github: https://github.com/MiroMindAI/MiroThinker

🔹 Models citing this paper:
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-72B
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-8B
• https://huggingface.co/miromind-ai/MiroThinker-v1.0-30B

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MiroThinker #ResearchAgents #ReinforcementLearning #OpenSourceAI #LLM

✨Mobile-Agent-v3: Foundamental Agents for GUI Automation

📝 Summary:
GUI-Owl and Mobile-Agent-v3 are open-source GUI agent models achieving state-of-the-art performance on GUI benchmarks. GUI-Owl introduces large-scale environment infrastructure, diverse agent capabilities, and scalable reinforcement learning, with Mobile-Agent-v3 further improving these results.

🔹 Publication Date: Published on Aug 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.15144
• PDF: https://arxiv.org/pdf/2508.15144
• Project Page: https://github.com/X-PLUG/MobileAgent
• Github: https://github.com/X-PLUG/MobileAgent

🔹 Models citing this paper:
• https://huggingface.co/mPLUG/GUI-Owl-7B
• https://huggingface.co/mPLUG/GUI-Owl-32B
• https://huggingface.co/mPLUG/GUI-Owl-7B-Desktop-RL

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#GUIAgent #Automation #ReinforcementLearning #AIResearch #OpenSourceAI

✨Scaling Open-Ended Reasoning to Predict the Future

📝 Summary:
This work trains language models for open-ended future prediction using a new dataset synthesized from news. Their OpenForecaster 8B model matches larger proprietary models in accuracy, calibration, and consistency. All resources are open-sourced.

🔹 Publication Date: Published on Dec 31, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.25070
• PDF: https://arxiv.org/pdf/2512.25070
• Project Page: https://www.openforecaster.github.io
• Github: https://github.com/OpenForecaster/scaling-forecasting-training

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLMs #FuturePrediction #AI #OpenSourceAI #MachineLearning

✨BitNet b1.58 2B4T Technical Report

📝 Summary:
BitNet b1.58 2B4T is the first open-source 1-bit Large Language Model with 2 billion parameters. It matches full-precision LLM performance while offering significant improvements in computational efficiency like reduced memory and energy. The model weights are openly released for research.

🔹 Publication Date: Published on Apr 16, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.12285
• PDF: https://arxiv.org/pdf/2504.12285
• Github: https://github.com/microsoft/bitnet

🔹 Models citing this paper:
• https://huggingface.co/microsoft/bitnet-b1.58-2B-4T
• https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-gguf
• https://huggingface.co/microsoft/bitnet-b1.58-2B-4T-bf16

✨ Spaces citing this paper:
• https://huggingface.co/spaces/suayptalha/Chat-with-Bitnet-b1.58-2B-4T
• https://huggingface.co/spaces/aizip-dev/SLM-RAG-Arena
• https://huggingface.co/spaces/Tonic/Native_1-bit_LLM

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #AI #Quantization #OpenSourceAI #DeepLearning

✨FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning

📝 Summary:
Chroma 1.0 is the first open-source real-time end-to-end spoken dialogue model with personalized voice cloning. It achieves low-latency interaction and high-fidelity voice synthesis, improving speaker similarity by 10.96% over a human baseline.

🔹 Publication Date: Published on Jan 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.11141
• PDF: https://arxiv.org/pdf/2601.11141
• Project Page: https://www.flashlabs.ai/flashai-voice-agents
• Github: https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma

🔹 Models citing this paper:
• https://huggingface.co/FlashLabs/Chroma-4B

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#ConversationalAI #VoiceCloning #RealTimeAI #OpenSourceAI #TTS

✨dLLM: Simple Diffusion Language Modeling

📝 Summary:
dLLM is an open-source framework standardizing core components of diffusion language modeling. It addresses the issue of scattered, hard-to-reproduce DLM implementations, enabling easy reproduction, customization, and development of both small and large diffusion language models.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22661
• PDF: https://arxiv.org/pdf/2602.22661
• Project Page: https://github.com/ZHZisZZ/dllm
• Github: https://github.com/ZHZisZZ/dllm

🔹 Models citing this paper:
• https://huggingface.co/dllm-hub/ModernBERT-large-chat-v0.1
• https://huggingface.co/dllm-hub/Qwen3-0.6B-diffusion-mdlm-v0.1
• https://huggingface.co/dllm-hub/Qwen3-0.6B-diffusion-bd3lm-v0.1

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#DiffusionModels #LanguageModeling #LLMs #OpenSourceAI #AIResearch

✨EXAONE 4.5 Technical Report

📝 Summary:
EXAONE 4.5 is LG AI Research's first open-weight vision language model, integrating a visual encoder into EXAONE 4.0. It enhances document understanding and general language capabilities through targeted data and extended context, outperforming similar models in document tasks.

🔹 Publication Date: Published on Apr 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.08644
• PDF: https://arxiv.org/pdf/2604.08644
• Github: https://github.com/LG-AI-EXAONE/EXAONE-4.5

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisionLanguageModel #AI #DocumentUnderstanding #MultimodalAI #OpenSourceAI

✨Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

📝 Summary:
Nemotron 3 Nano Omni is a new efficient, open multimodal AI model. It natively supports audio, text, images, and video inputs, improving accuracy and efficiency over previous versions. It excels in document understanding and long audio-video comprehension.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24954
• PDF: https://arxiv.org/pdf/2604.24954

🔹 Models citing this paper:
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

✨ Spaces citing this paper:
• https://huggingface.co/spaces/akhaliq/Nemotron-3-Nano-Omni
• https://huggingface.co/spaces/developerjeremylive/Nemotron-3-Nano-Omni-etheroi

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #MultimodalAI #DeepLearning #OpenSourceAI #AIResearch

🔥 Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation

💡 The paper introduces Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family that delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual text rendering. The model family consists of Base, Turbo, Edit, and Edit-Turbo variants.

The problem addressed in the paper is that closed-source multimodal systems achieve strong performance through system-level integration rather than a single model, yet their internal practices remain largely undisclosed. The authors demonstrate that targeted improvements in model understanding, data quality, and training pipelines, coupled with genetic inference-time scaling, can substantially enhance generation and editing performance even under highly constrained compute budgets.

The method used to achieve this involves making improvements in model understanding, data quality, and training pipelines. The authors also use genetic inference-time scaling to enhance performance. The model is trained on a dataset of 208.62 million unique images, and the theoretical training cost is approximately 400,000 dollars.

The results show that Boogu-Image-0.1 consistently matches or surpasses other open-source models across standard benchmarks and achieves results approaching leading closed-source systems. The authors share practical discussions and release weights, code, and recipes under Apache 2.0 to advance the open ecosystem for unified multimodal understanding and generation. The code is available on GitHub.

Overall, the paper contributes to the development of open-source multimodal models that can achieve competitive performance with closed-source systems, and provides a valuable resource for the research community.

📅 Published on Jul 14

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.13125
• PDF: https://arxiv.org/pdf/2607.13125
• Project Page: https://boogu.org/

🤖 Models citing this paper:
• https://huggingface.co/Boogu/Boogu-Image-0.1-Edit
• https://huggingface.co/Boogu/Boogu-Image-0.1-Base
• https://huggingface.co/Boogu/Boogu-Image-0.1-Turbo

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/RioShiina/ImageGen
• https://huggingface.co/spaces/multimodalart/Boogu-Image
• https://huggingface.co/spaces/Tinchote/ImageGen

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#MultimodalUnderstanding #TextToImageGeneration #OpenSourceAI #MultimodalGeneration #InstructionBasedEditing