Tootfinder

Watermarking LLM-Generated Datasets in Downstream Tasks
Yugeng Liu, Tianshuo Cong, Michael Backes, Zheng Li, Yang Zhang
https://arxiv.org/abs/2506.13494 ht…

Watermarking LLM-Generated Datasets in Downstream Tasks
Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility, researchers and companies increasingly employ LLM-generated data to train their models. However, the inability to track content produced by LLMs poses a significant challenge, potentially leading to copyright infringement for the LLM owners. In this paper, we pr…

Modulating lipid membrane morphology by dynamic DNA origami networks
Juanjuan Yang, Kevin Jahnke, Ling Xin, Xinxin Jing, Pengfei Zhan, Andreas Peil, Alessandra Griffo, Marko \v{S}kugor, Donglei Yang, Sisi Fan, Kerstin G\"opfrich, Hao Yan, Pengfei Wang, Na Liu
https://arxiv.org/abs/2506.11522…

Modulating lipid membrane morphology by dynamic DNA origami networks
Membrane morphology and its dynamic adaptation regulate many cellular functions, which are often mediated by membrane proteins. Advances in DNA nanotechnology have enabled the realization of various protein-inspired structures and functions with precise control at the nanometer level, suggesting a viable tool to artificially engineer the membrane morphology. In this work, we demonstrate a DNA origami cross (DOC) structure that can be anchored onto giant unilamellar vesicles (GUVs) and subsequen…

Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
Craig Macdonald, Jinyuan Fang, Andrew Parry, Zaiqiao Meng
https://arxiv.org/abs/2506.10802

Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. O…

This https://arxiv.org/abs/2505.16652 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in the decoding strategy, we propose to leverage causal masks …

Laser Guided Microbubble Lithography for Multilayer Biophotonic Heterostructures
Anand Dev Ranjan, Suyash Narayan Amzare, Subhrokoli Ghosh, Ayan Banerjee
https://arxiv.org/abs/2506.10320

Laser Guided Microbubble Lithography for Multilayer Biophotonic Heterostructures
The fabrication of multilayered heterostructures is essential for advancing microelectronic and biosensing technologies. Conventional top-down manufacturing techniques are often cost-prohibitive and unsuitable for biomedical applications. Here, we present a bottom-up fabrication method, termed microbubble lithography, which enables the in situ construction of multilayered microstructures through layer-by-layer self-assembly. This technique allows diverse materials to be integrated into coherent…

#StarTrek without computers is inconceivable. Which makes advancements in computer science an important milestone; and also the subject of today's #TrekTriviaTuesday question.
As always no googling and no spoiling the answer for others. Please boost after voting! :BoostOK:
Vote…

Single Cu Atom Sites on Co3O4 Activate Interfacial Oxygen for Enhanced Reactivity and Selective Gas Sensing at Low Temperature
Hamin Shin, Matteo D'Andria, Jaehyun Ko, Dong-Ha Kim, Frank Krumeich, Andreas T. Guentner
https://arxiv.org/abs/2506.09761

Single Cu Atom Sites on Co3O4 Activate Interfacial Oxygen for Enhanced Reactivity and Selective Gas Sensing at Low Temperature
Controlling the redox landscape of transition metal oxides is central to advancing their reactivity for heterogeneous catalysis or high-performance gas sensing. Here we report single Cu atom sites (1.42 wt%) anchored on Co3O4 nanoparticles (Cu1-Co3O4) that dramatically enhance reactivity and molecular sensing properties of the support at low temperature. The Cu1 are identified by X-ray adsorption near edge structure and feature strong metal-support interaction between Cu2+ and Co3O4, as reveale…

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Ailin Huang, Bingxin Li, Bruce Wang, Boyong Wu, Chao Yan, Chengli Feng, Heng Wang, Hongyu Zhou, Hongyuan Wang, Jingbei Li, Jianjian Sun, Joanna Wang, Mingrui Chen, Peng Liu, Ruihang Miao, Shilei Jiang, Tian Fei, Wang You, Xi Chen, Xuerui Yang, Yechang Huang, Yuxiang Zhang, Zheng Ge, Zheng Gong, Zhewei Huang, Zixin Zhang, Bin Wang, Bo Li, Buyun Ma, Changxin Miao, Changyi Wan, Chen Xu, Dapeng Shi, Dingyuan Hu, Enle…

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter…

This https://arxiv.org/abs/2505.24718 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Reinforcing Video Reasoning with Focused Thinking
Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations persist: 1) they often produce unfocused, verbose reasoning chains that obscure salient spatiotemporal cues and 2) binary rewarding fails to account for partially correct answers, resulting in high reward variance and inefficient learning. In this paper, we propos…

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu
https://arxiv.org/abs/2506.06242

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse …