Tootfinder

Czas w końcu wziąć się za przenoszenie swoich projektów z LLM Torment Nexus, dawniej #GitHub. Projekty związane z #Gentoo trafią na naszą własną infrastrukturę, w najbliższym czasie GitHub dalej będzie służył jako serwer lustrzany / ścieżka przyjmowania łatek. W przyszłości prawdopodobnie te funkcje przejmie

Video Object Segmentation-Aware Audio Generation
Ilpo Viertola, Vladimir Iashin, Esa Rahtu
https://arxiv.org/abs/2509.26604 https://arxiv.org/pdf/2509.2660…

Video Object Segmentation-Aware Audio Generation
Existing multimodal audio generation models often lack precise user control, which limits their applicability in professional Foley workflows. In particular, these models focus on the entire video and do not provide precise methods for prioritizing a specific object within a scene, generating unnecessary background sounds, or focusing on the wrong objects. To address this gap, we introduce the novel task of video object segmentation-aware audio generation, which explicitly conditions sound synt…

On LLM-Assisted Generation of Smart Contracts from Business Processes
Fabian Stiehle, Hans Weytjens, Ingo Weber
https://arxiv.org/abs/2507.23087 https://ar…

On LLM-Assisted Generation of Smart Contracts from Business Processes
Large language models (LLMs) have changed the reality of how software is produced. Within the wider software engineering community, among many other purposes, they are explored for code generation use cases from different types of input. In this work, we present an exploratory study to investigate the use of LLMs for generating smart contract code from business process descriptions, an idea that has emerged in recent literature to overcome the limitations of traditional rule-based code generati…

Why Gen X women can’t stop eating ultra-processed foods #nutrition

Why Gen X women can’t stop eating ultra-processed foods
Researchers found that middle-aged adults, especially women, are far more likely to be addicted to ultra-processed foods than older generations. Marketing of diet-focused processed foods in the 1980s may have played a major role. Food addiction was linked to poor health, weight issues, and social isolation, highlighting long-term risks. Experts warn that children today could face even higher addiction rates in the future.

Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
Jinhao Liang, Yixuan Sun, Anirban Samaddar, Sandeep Madireddy, Ferdinando Fioretto
https://arxiv.org/abs/2509.25157

Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specifications. A common remedy is to project intermediate samples onto the feasible set; however, repeated projection can distort the learned distribution and induce a mismatch with the data manifold. Thus, recent multi-stage procedures attempt to defer projection to clean samples during sampling, but they increase algorithmic…

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
Yike Zhu (Audio, Speech and Language Processing Group), Boyi Kang (The Hong Kong University of Science and Technology, Hong Kong, China, Audio, Speech and Language Processing Group), Ziqian Wang (Audio, Speech and Language Processing Group), Xingchen Li (Audio, Speech and Language Processing Group, Huawei Technologies, China), Zihan Zhang (Huawei Technologies, China), Wenjie Li (Huawei Technologies, China), Longshuai Xiao …

MeanFlowSE: One-Step Generative Speech Enhancement via MeanFlow
Speech enhancement (SE) recovers clean speech from noisy signals and is vital for applications such as telecommunications and automatic speech recognition (ASR). While generative approaches achieve strong perceptual quality, they often rely on multi-step sampling (diffusion/flow-matching) or large language models, limiting real-time deployment. To mitigate these constraints, we present MeanFlowSE, a one-step generative SE framework. It adopts MeanFlow to predict an average-velocity field for on…

Cost-aware Photonic Graph State Generation: A Graphical Framework
Sobhan Ghanbari, Hoi-Kwong Lo
https://arxiv.org/abs/2509.22777 https://arxiv.org/pdf/2509…

Cost-aware Photonic Graph State Generation: A Graphical Framework
Photonic graph states are essential resources for quantum computation and communication. Deterministic emitter-based generation of graph states overcomes the scalability issues of probabilistic approaches, but their experimental realization is constrained by technological demands, often expressed by the number of two-qubit gates and the depth and/or width of the quantum circuits used to model the generation process. We introduce a cost-aware framework for the generation of photonic graph states…

In-between Motion Generation Based Multi-Style Quadruped Robot Locomotion
Yuanhao Chen, Liu Zhao, Ji Ma, Peng Lu
https://arxiv.org/abs/2507.23053 https://a…

In-between Motion Generation Based Multi-Style Quadruped Robot Locomotion
Quadruped robots face persistent challenges in achieving versatile locomotion due to limitations in reference motion data diversity. To address these challenges, this approach introduces an in-between motion generation based multi-style quadruped robot locomotion framework, integrating synergistic advances in motion generation and imitation learning. Our approach establishes a unified pipeline addressing two fundamental aspects: First, we propose a CVAE based motion generator, synthesizing mult…

LST-1 observations of GRB 221009A: Insights into its late-time VHE afterglow
Arnau Aguasca-Cabot (for the CTAO-LST Project), Susumu Inoue (for the CTAO-LST Project), Monica Seglar-Arroyo (for the CTAO-LST Project), Kenta Terauchi (for the CTAO-LST Project), Pol Bordas (for the CTAO-LST Project), Marc Rib\'o (for the CTAO-LST Project)
https://

LST-1 observations of GRB 221009A: Insights into its late-time VHE afterglow
Gamma-ray bursts (GRBs) originate from explosions at cosmological distances, generating collimated jets. GRB 221009A, exploded on 9 October 2022, has been established as the brightest GRB to date. Its bright and long emission was extensively followed up from radio to gamma rays. LHAASO firmly detected the onset of the afterglow emission at energies up to $\sim$13 TeV within about an hour after the burst, starting just a few minutes after the trigger. While this VHE emission component can be acc…

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
Aryan Yazdan Parast, Parsa Hosseini, Hesam Asadollahzadeh, Arshia Soltani Moakhar, Basim Azam, Soheil Feizi, Naveed Akhtar
https://arxiv.org/abs/2509.25178

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the image. This weakness of MLLMs is currently studied using static benchmarks with fixed visual scenarios, which preempts the possibility of uncovering model-specific or unanticipated hallucination vulnerabilities. We introduce GHOST (Generating Hallucinations via Optimizing Stealth Tokens), a method designed to stress-test MLLMs by actively generati…