Tootfinder

NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection
Krittin Chaowakarn, Paramin Sangwongngam, Nang Htet Htet Aung, Chalie Charoenlarpnopparut
https://arxiv.org/abs/2510.11632

NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection
Recent studies in 3D object detection for autonomous vehicles aim to enrich features through the utilization of multi-modal setups or the extraction of local patterns within LiDAR point clouds. However, multi-modal methods face significant challenges in feature alignment, and gaining features locally can be oversimplified for complex 3D object detection tasks. In this paper, we propose a novel model, NV3D, which utilizes local features acquired from voxel neighbors, as normal vectors computed p…

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
Tavor Z. Baharav, Spyros Dragazis, Aldo Pacchiano
https://arxiv.org/abs/2510.01020 https:/…

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
We study the problem of sequentially testing individuals for a binary disease outcome whose true risk is governed by an unknown logistic model. At each round, a patient arrives with feature vector $x_t$, and the decision maker may either pay to administer a (noiseless) diagnostic test--revealing the true label--or skip testing and predict the patient's disease status based on their feature vector and prior history. Our goal is to minimize the total number of costly tests required while guarante…

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Marco Bronzini, Carlo Nicolini, Bruno Lepri, Jacopo Staiano, Andrea Passerini
https://arxiv.org/abs/2509.25045

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods, such as direct logit attribution (DLA) and sparse autoencoders (SAEs), provide restricted insight due to limitations such as the model's output vocabulary or unclear feature names. This work introduces Hyperdimensional Probe, a novel paradigm for decoding information from the LLM vector space. It combines ideas from symbolic repre…

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
Zanwu Liu, Chao Yuan, Bo Li, Xiaowei Zhang, Guanglin Niu
https://arxiv.org/abs/2510.00936

Looking Alike From Far to Near: Enhancing Cross-Resolution Re-Identification via Feature Vector Panning
In surveillance scenarios, varying camera distances cause significant differences among pedestrian image resolutions, making it hard to match low-resolution (LR) images with high-resolution (HR) counterparts, limiting the performance of Re-Identification (ReID) tasks. Most existing Cross-Resolution ReID (CR-ReID) methods rely on super-resolution (SR) or joint learning for feature compensation, which increases training and inference complexity and has reached a performance bottleneck in recent s…

Consciousness As Entropy Reduction (Short Version)
Yifeng Chen, J. W. Sanders
https://arxiv.org/abs/2510.06297 https://arxiv.org/pdf/2510.06297

Consciousness As Entropy Reduction (Short Version)
A model of consciousness is proposed which, having a logical basis, lends itself to simulation using a simple mathematical model called Consciousness as Entropy Reduction (CER). The approach has been inspired by previous models such as GWT, IIT and an earlier less mainstream model called "Feature Map" in Psychology. CER considers the contents of consciousness and subconsciousness as \textit{scenarios}: a vector of patterns (or features) on various "channels" (or feature locations). In CER, a fe…

Primary Proca Hair and the Double-Peak Optics of Black Holes
R. A. Konoplya, D. Ovchinnikov, J. Schee
https://arxiv.org/abs/2510.05947 https://arxiv.org/pd…

Primary Proca Hair and the Double-Peak Optics of Black Holes
We study the optical properties of black holes endowed with primary Proca hair, focusing on the distinctive double-peak structure generated in the effective potential by the massive vector field. This novel feature drastically modifies the geodesic motion of both photons and massive particles, leading to qualitatively new dynamical and observational signatures. We derive and analyze the effective potentials, classify time-like and null geodesics, and identify the conditions for multiple circula…

Carrollian Lie Algebroids: Taming Singular Carrollian Geometries
Andrew James Bruce
https://arxiv.org/abs/2510.03877 https://arxiv.org/pdf/2510.03877

Carrollian Lie Algebroids: Taming Singular Carrollian Geometries
Developments in Carrollian gravity and holography necessitate the use of singular Carroll vector fields, a feature that cannot be accommodated within standard Carrollian geometry. We introduce Carrollian Lie algebroids as a framework to study such singular Carrollian geometries. In this approach, we define the Carroll distribution as the image of the kernel of the degenerate metric under the anchor map. The Carroll distribution is, in general, a singular Stefan--Sussmann distribution that will …

Interband optical conductivity in two-dimensional semi-Dirac bands tilting along the quadratic dispersion
Xin Chen, Jian-Tong Hou, Long Liang, Jie Lu, Hong Guo, Chang-Xu Yan, Hao-Ran Chang
https://arxiv.org/abs/2510.06591

Interband optical conductivity in two-dimensional semi-Dirac bands tilting along the quadratic dispersion
Two-dimensional (2D) semi-Dirac materials feature a unique anisotropic band structure characterized by quadratic dispersion along one spatial direction and linear dispersion along the other, effectively hybridizing ordinary and Dirac fermions. The anisotropy of energy dispersion can be further modulated through band tilting along either spatial direction of the wave vector. We propose a new definition of tilt parameter to characterize Lifshitz phases in 2D semi-Dirac bands tilting along the qua…

Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Mitchell Keren Taraday, Shahaf Wagner, Chaim Baskin
https://arxiv.org/abs/2510.06820 https://…

Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision--language rerankers are largely absent. We find that seminal joint encoders such as BLIP are severely bottlenecked by an expensive visual feature-extraction stage, preventing practical deployment at scale. Motivated by this bottleneck, we introduce EDJE, an Efficient Discriminativ…