Tootfinder

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddi…

GraSP: A Unified Graph-Based Framework for Scalable Generation, Quality Tagging, and Management of Synthetic Data for SFT and DPO
Bidyapati Pradhan, Surajit Dasgupta, Amit Kumar Saha, Omkar Anustoop, Sriram Puttagunta, Vipul Mittal, Gopal Sarda
https://arxiv.org/abs/2508.15432

GraSP: A Unified Graph-Based Framework for Scalable Generation, Quality Tagging, and Management of Synthetic Data for SFT and DPO
The advancement of large language models (LLMs) is critically dependent on the availability of high-quality datasets for Supervised Fine-Tuning (SFT), alignment tasks like Direct Preference Optimization (DPO), etc. In this work, we present a comprehensive synthetic data generation framework that facilitates scalable, configurable, and high-fidelity generation of synthetic data tailored for these training paradigms. Our approach employs a modular and configuration-based pipeline capable of model…

Open-Source LLMs Collaboration Beats Closed-Source LLMs: A Scalable Multi-Agent System
Shengji Tang, Jianjian Cao, Weihao Lin, Jiale Hong, Bo Zhang, Shuyue Hu, Lei Bai, Tao Chen, Wanli Ouyang, Peng Ye
https://arxiv.org/abs/2507.14200

Open-Source LLMs Collaboration Beats Closed-Source LLMs: A Scalable Multi-Agent System
This paper aims to demonstrate the potential and strengths of open-source collectives. It leads to a promising question: Can we harness multiple open-source LLMs to match or even beat the closed-source LLMs? To answer this, we propose SMACS, a scalable multi-agent collaboration system (MACS) framework with high performance. Specifically, for continuous integration of new LLMs and generalization to diverse questions, we first propose a Retrieval-based Prior Selection (RPS), which assigns a proxy…

Transformer-Gather, Fuzzy-Reconsider: A Scalable Hybrid Framework for Entity Resolution
Mohammadreza Sharifi, Danial Ahmadzadeh
https://arxiv.org/abs/2509.17470 https://

Transformer-Gather, Fuzzy-Reconsider: A Scalable Hybrid Framework for Entity Resolution
Entity resolution plays a significant role in enterprise systems where data integrity must be rigorously maintained. Traditional methods often struggle with handling noisy data or semantic understanding, while modern methods suffer from computational costs or the excessive need for parallel computation. In this study, we introduce a scalable hybrid framework, which is designed to address several important problems, including scalability, noise robustness, and reliable results. We utilized a pre…

From Local Interactions to Global Operators: Scalable Gaussian Process Operator for Physical Systems
Sawan Kumar, Tapas Tripura, Rajdip Nayek, Souvik Chakraborty
https://arxiv.org/abs/2506.15906

From Local Interactions to Global Operators: Scalable Gaussian Process Operator for Physical Systems
Operator learning offers a powerful paradigm for solving parametric partial differential equations (PDEs), but scaling probabilistic neural operators such as the recently proposed Gaussian Processes Operators (GPOs) to high-dimensional, data-intensive regimes remains a significant challenge. In this work, we introduce a novel, scalable GPO, which capitalizes on sparsity, locality, and structural information through judicious kernel design. Addressing the fundamental limitation of cubic computat…

Scalable FPGA Framework for Real-Time Denoising in High-Throughput Imaging: A DRAM-Optimized Pipeline using High-Level Synthesis
Weichien Liao
https://arxiv.org/abs/2508.14917 h…

Scalable FPGA Framework for Real-Time Denoising in High-Throughput Imaging: A DRAM-Optimized Pipeline using High-Level Synthesis
High-throughput imaging workflows, such as Parallel Rapid Imaging with Spectroscopic Mapping (PRISM), generate data at rates that exceed conventional real-time processing capabilities. We present a scalable FPGA-based preprocessing pipeline for real-time denoising, implemented via High-Level Synthesis (HLS) and optimized for DRAM-backed buffering. Our architecture performs frame subtraction and averaging directly on streamed image data, minimizing latency through burst-mode AXI4 interfaces. The…

TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation
Yongsheng Feng, Yuetonghui Xu, Jiehui Luo, Hongjia Liu, Xiaobing Li, Feng Yu, Wei Li
https://arxiv.org/abs/2509.15666

TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation
Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly large networks, inflating training and deployment costs. Motivated by recent advances in inference-time scaling for generative modeling, we propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS), a unified framework that…

Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems
Thorsten Hellert, Jo\~ao Montenegro, Antonin Sulc
https://arxiv.org/abs/2508.15066 https://

Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems
Coordinating workflows across heterogeneous control systems remains a central challenge in safety-critical environments such as scientific facilities, industrial plants, and energy infrastructures. Language-model-driven agents offer a natural interface for these tasks, but existing approaches often lack scalability, reliability, and human oversight. We introduce the Alpha Berkeley Framework, a production-ready architecture for scalable agentic systems that integrate conversational context with …

Scalable Estimation of Crossed Random Effects Models via Multi-way Grouping
Shota Takeishi, Shonosuke Sugasawa
https://arxiv.org/abs/2507.15593 https://

Scalable Estimation of Crossed Random Effects Models via Multi-way Grouping
Cross-classified data frequently arise in scientific fields such as education, healthcare, and social sciences. A common modeling strategy is to introduce crossed random effects within a regression framework. However, this approach often encounters serious computational bottlenecks, particularly for non-Gaussian outcomes. In this paper, we propose a scalable and flexible method that approximates the distribution of each random effect by a discrete distribution, effectively partitioning the rand…

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Jane Luo, Xin Zhang, Steven Liu, Jie Wu, Yiming Huang, Yangyu Huang, Chengyu Yin, Ying Xin, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qi Chen, Scarlett Li, Mao Yang
https://arxiv.org/abs/2509.16198

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies pr…