Cosine
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
What Cosine Similarity of Label Representations Can and Cannot Tell us
Announce Type: replace Abstract: Cosine similarity is often used to measure the similarity of vector representations of neural network models. However, the cosine similarity of representations is not guaranteed to tell us anything about model probabilities. In this paper we show that for a softmax classifier, be it an image classifier or an autoregressive language model, the cosine similarity between label representations (called unembeddings in the paper) does not give any information on...
Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents
arXiv:2606.05753v1 Announce Type: new Abstract: Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these latents and their visual targets, i.e., cosine similarity or mean squared error (MSE), as both the training loss and the quality metric, assuming that better alignment yields a better answer. We test this with a designed matrix of five LVR variants and find the...
Linear Cosine Palettes(2025)
Kind of a generative art thing, but mostly an attempt by the author to prove to herself that a she can write a short blog post without turning it into a goddamn monograph So. Looking back at my history on this blog I have noticed that I, ummmmmm, tend to write long posts. It is a character flaw of which I am acutely aware.
Adaptive Calibration for Fair and Performant Facial Recognition
arXiv:2606.04469v1 Announce Type: new Abstract: We introduce Adaptive Calibration (AC), a novel calibration strategy for facial recognition that maps cosine similarity between normalized embeddings to well-calibrated probabilities. By incorporating local context into calibration, Adaptive Calibration corrects for a fundamental mismatch in cosine similarity, whereby the same distance can correspond to different match probabilities in different embedding regions. Our approach improves both...
Meta's ships facial recognition on smart glasses
Meta's smart glasses companion app ships a complete, dormant face-recognition pipeline on a stock account. Stella is the companion app for Meta's smart glasses. Inspecting version 273.0.0.21 of the Android build (com.facebook.stella ), I found the entire computational and storage stack for on-device facial recognition: three face models, a local database schema, a cosine-similarity vector index dimensioned to match the models, a write path that stages biometric records to disk, a fully wired...
Show HN: We post-trained a model that pen tests instead of refusing your code
I'm Dimitrios at Cosine. Quick orientation first: the read-only scan is free and you can run it right now: that's the part to try. The pen-test mode is gated behind written authorisation, because it's live offensive testing against real systems; I'll explain that below, it's not a paywall thing.
Quantum Erasure Imaging: Complementary Modalities from Delayed-Choice Erasure
Announce Type: cross Abstract: Quantum Erasure Imaging (QEI) turns delayed-choice erasure into a practical imaging protocol. Entangled photon pairs encode two classical modalities, absorption $T(x,y)$ and a phase-sensitive cosine quadrature of $\phi(x,y)$, reconstructed from a single run of time-tagged coincidences by retrospective sorting on a remote ancilla. Measuring the ancilla in H/V yields $T$ via which-path information; D/A yields interference visibility $\propto...
Uncovering Turbulent Dynamics in Stenotic Flows from 4D-flow MRI Measurements via Resolvent Analysis and Data Assimilation
arXiv:2606.03838v1 Announce Type: new Abstract: This study presents a hybrid experimental and computational framework that couples in vitro 4D phase-contrast magnetic resonance imaging (4D-flow MRI) measurements with data assimilation and linear modeling to characterize the flow linear amplification mechanisms. We manufacture an idealized stenosis phantom with a cosine-shaped contraction and acquire three-dimensional (3D) mean velocity measurements at Reynolds number 3960 using 4D-flow MRI....
Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
arXiv:2605.31111v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) learn compact latent world models by predicting future embeddings, but no single coordinate of the latent is designated to encode task progression. We carve the JEPA latent into two orthogonal subspaces with disjoint roles: a low-dimensional progression subspace shaped by a cosine-margin triplet loss, and a high-dimensional content subspace regularised by the existing SIGReg objective of LeWM. We...
Improving Relative Representations with Learned Anchors and Whitened Inner Products
arXiv:2605.30596v1 Announce Type: new Abstract: Independently trained neural models typically converge to incompatible latent representations, creating a fundamental barrier to highly modular AI systems. While Relative Representations (RR) address this by mapping absolute coordinates to a shared space defined by similarities to common anchor points, traditional implementations rely on randomly sampled anchors and cosine similarity, which frequently fail to capture the anisotropic geometries...