Tootfinder

How Far Do Time Series Foundation Models Paint the Landscape of Real-World Benchmarks ?
Lujun Li, Lama Sleem, Yiqun Wang, Yangjie Xu, Niccol\`o Gentile, Radu State
https://arxiv.org/abs/2509.26347

How Far Do Time Series Foundation Models Paint the Landscape of Real-World Benchmarks ?
Recent evaluations of time-series foundation models (TSFMs) have emphasized synthetic benchmarks, leaving real-world generalization less thoroughly examined. This work proposes a novel benchmarking approach that bridges synthetic and realistic data by extracting temporal signals from real-world video using optical flow and curating datasets reflecting everyday temporal dynamics. Building upon this pipeline, we introduce REAL-V-TSFM, a novel dataset designed to capture rich and diverse time seri…

Code is a confusing engineering object for our human brains. It is a bit like building a bridge or a kitchen utensil: it’s an object without a mind, it has a function, it can fail, people do unexpected things with it. But it can also feel a bit like a person given a task: it has behavior, it •decides•, it •acts•, it •causes•.
(All arguably true of a bridge too, but most of us don’t think of bridges that way!)
The lay understanding of code leans heavily on the idea that programs are anthropomorphic, little homunculi with agency.
2/

VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos, Vassilis Katsouros
https://arxiv.org/abs/2509.15667

VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
We present a multimodal fusion framework that bridges pre-trained decoder-based large language models (LLM) and acoustic encoder-decoder architectures such as Whisper, with the aim of building speech-enabled LLMs. Instead of directly using audio embeddings, we explore an intermediate audio-conditioned text space as a more effective mechanism for alignment. Our method operates fully in continuous text representation spaces, fusing Whisper's hidden decoder states with those of an LLM through cros…

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Zekang Liu, Wei Feng, Fanhua Shang, Lianyu Hu, Jichao Feng, Liqing Gao
https://arxiv.org/abs/2509.14036

SSL-SSAW: Self-Supervised Learning with Sigmoid Self-Attention Weighting for Question-Based Sign Language Translation
Sign Language Translation (SLT) bridges the communication gap between deaf people and hearing people, where dialogue provides crucial contextual cues to aid in translation. Building on this foundational concept, this paper proposes Question-based Sign Language Translation (QB-SLT), a novel task that explores the efficient integration of dialogue. Unlike gloss (sign language transcription) annotations, dialogue naturally occurs in communication and is easier to annotate. The key challenge lies i…

Port-Hamiltonian Neural Networks: From Theory to Simulation of Interconnected Stochastic Systems
Luca Di Persio, Matthias Ehrhardt, Youness Outaleb, Sofia Rizzotto
https://arxiv.org/abs/2509.06674

Port-Hamiltonian Neural Networks: From Theory to Simulation of Interconnected Stochastic Systems
This work introduces a new framework integrating port-Hamiltonian systems (PHS) and neural network architectures. This framework bridges the gap between deterministic and stochastic modeling of complex dynamical systems. We introduce new mathematical formulations and computational methods that expand the geometric structure of PHS to account for uncertainty, environmental noise, and random perturbations. Building on these advances, we introduce stochastic port-Hamiltonian neural networks (pHNNs…