Tootfinder

TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation
Qianqi Lu, Yuxiang Xie, Jing Zhang, Shiwei Zou, Yan Chen, Xidao Luan
https://arxiv.org/abs/2509.13070

TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation
Referring Image Segmentation (RIS) is a task that segments image regions based on language expressions, requiring fine-grained alignment between two modalities. However, existing methods often struggle with multimodal misalignment and language semantic loss, especially in complex scenes containing multiple visually similar objects, where uniquely described targets are frequently mislocalized or incompletely segmented. To tackle these challenges, this paper proposes TFANet, a Three-stage Image-T…

Simulation-based inference using splitting schemes for partially observed diffusions in chemical reaction networks
Petar Jovanovski, Andrew Golightly, Umberto Picchini, Massimiliano Tamborrino
https://arxiv.org/abs/2508.11438

Simulation-based inference using splitting schemes for partially observed diffusions in chemical reaction networks
We address the problem of simulation and parameter inference for chemical reaction networks described by the chemical Langevin equation, a stochastic differential equation (SDE) representation of the dynamics of the chemical species. This is challenging for two main reasons. First, the (multi-dimensional) SDEs cannot be explicitly solved and are driven by multiplicative and non-commutative noise, requiring the development of advanced numerical schemes for their approximation and simulation. Sec…

Uncovering the Fourier Structure of Wavefunctions in Semiconductors
Yunfan Liang, Damien West, Shengbai Zhang
https://arxiv.org/abs/2508.11225 https://arxi…

Uncovering the Fourier Structure of Wavefunctions in Semiconductors
Symmetry dictates the physical properties of materials. The symmetry of the Bravais lattice defines the set of points, lines, and planes over which sets of planewaves are degenerate, upon which atomic symmetry determines the interaction potentials which may lift such degeneracies. This results in wavefunctions which are single planewaves throughout the BZ, except in the vicinity of the removed degeneracies. As optical transitions between any two planewaves are forbidden, only regions of the Bri…

Asymptotic Velocity Domination in quantized polarized Gowdy Cosmologies
Max Niedermaier, Mahdi Sedighi Jafari
https://arxiv.org/abs/2509.13162 https://arxi…

Asymptotic Velocity Domination in quantized polarized Gowdy Cosmologies
Asymptotic velocity domination (AVD) posits that when back-propagated to the Big Bang generic cosmological spacetimes solve a drastically simplified version of the Einstein field equations, where all dynamical spatial gradients are absent (similar as in the Belinski-Khalatnikov-Lifshitz scenario). Conversely, a solution can in principle be reconstructed from its behavior near the Big Bang. This property has been rigorously proven for the Gowdy class of cosmologies, both polarized and unpolarize…

Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
Hanpei Fang, Sijie Tao, Nuo Chen, Kai-Xin Chang, Tetsuya Sakai
https://arxiv.org/abs/2509.11353

Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
Large language models (LLMs) are increasingly deployed in information systems, including being used as second-stage rerankers in information retrieval pipelines, yet their susceptibility to recency bias has received little attention. We investigate whether LLMs implicitly favour newer documents by prepending artificial publication dates to passages in the TREC Deep Learning passage retrieval collections in 2021 (DL21) and 2022 (DL22). Across seven models, GPT-3.5-turbo, GPT-4o, GPT-4, LLaMA-3 8…

Dynamic Vulnerability Patching for Heterogeneous Embedded Systems Using Stack Frame Reconstruction
Ming Zhou, Xupu Hu, Zhihao Wang, Haining Wang, Hui Wen, Limin Sun, Peng Zhang
https://arxiv.org/abs/2509.10213

Dynamic Vulnerability Patching for Heterogeneous Embedded Systems Using Stack Frame Reconstruction
Existing dynamic vulnerability patching techniques are not well-suited for embedded devices, especially mission-critical ones such as medical equipment, as they have limited computational power and memory but uninterrupted service requirements. Those devices often lack sufficient idle memory for dynamic patching, and the diverse architectures of embedded systems further complicate the creation of patch triggers that are compatible across various system kernels and hardware platforms. To address…

End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI
Yihong Chen, Jiancheng Yang, Deniz Sayin Mercadier, Hieu Le, Juerg Schwitter, Pascal Fua
https://arxiv.org/abs/2509.12090

End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI
Reconstructing cardiac motion from cine CMR sequences is critical for diagnosis, prediction, and intervention. Existing methods rely on complete CMR stacks to infer full heart motion, limiting their utility in intra-procedural scenarios where only sparse observations are available. We present TetHeart, the first end-to-end framework that unifies full 4D multi-structure heart mesh recovery from both offline full-stack acquisitions and intra-procedural sparse-slice observations. Our method levera…

MSR-Codec: A Low-Bitrate Multi-Stream Residual Codec for High-Fidelity Speech Generation with Information Disentanglement
Jingyu Li, Guangyan Zhang, Zhen Ye, Yiwen Guo
https://arxiv.org/abs/2509.13068 …

MSR-Codec: A Low-Bitrate Multi-Stream Residual Codec for High-Fidelity Speech Generation with Information Disentanglement
Audio codecs are a critical component of modern speech generation systems. This paper introduces a low-bitrate, multi-scale residual codec that encodes speech into four distinct streams: semantic, timbre, prosody, and residual. This architecture achieves high-fidelity speech reconstruction at competitive low bitrates while demonstrating an inherent ability for information disentanglement. We construct a two-stage language model for text-to-speech (TTS) synthesis using this codec, which, despite…

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
Yifan Liu, Yaokun Liu, Zelin Li, Zhenrui Yue, Gyuseok Lee, Ruichen Yao, Yang Zhang, Dong Wang
https://arxiv.org/abs/2509.10468

Learning Decomposed Contextual Token Representations from Pretrained and Collaborative Signals for Generative Recommendation
Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via sequence-to-sequence modeling. However, these two stages are optimized for different objectives: semantic reconstruction during tokenizer pretraining versus user interaction modeling during recommender training. This objective misalignment leads to two key limitations: (i) …

Robustness and Diagnostic Performance of Super-Resolution Fetal Brain MRI
Ema Masterl, Tina Vipotnik Vesnaver, \v{Z}iga \v{S}piclin
https://arxiv.org/abs/2509.10257 https://

Robustness and Diagnostic Performance of Super-Resolution Fetal Brain MRI
Fetal brain MRI relies on rapid multi-view 2D slice acquisitions to reduce motion artifacts caused by fetal movement. However, these stacks are typically low resolution, may suffer from motion corruption, and do not adequately capture 3D anatomy. Super-resolution reconstruction (SRR) methods aim to address these limitations by combining slice-to-volume registration and super-resolution techniques to generate high-resolution (HR) 3D volumes. While several SRR methods have been proposed, their co…