Hugging Face Trending Papers October 13, 2026

A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization

Read the original on Hugging Face Trending Papers →

The paper evaluates a narrow implementation of domain‑specific curvature called HyperDG, which rescales Euclidean encoder features during training with learned positive scalars and uses a standard linear classifier at inference. Across six conditions on four benchmark datasets (PACS, VLCS, Office Home, TerraIncognita) and 384 runs, the method’s macro performance is 1.61 percentage points below native DomainBed ERM, with no statistically significant difference after adjustment. The study concludes that this scalar‑scaling approach does not provide evidence of improvement over ERM and offers a bounded negative result for this specific training package.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Oct 15

A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization

arXiv:2610.18227v1 Announce Type: cross Abstract: Domain-specific curvature is an appealing idea for domain generalization (DG), but curvature learning can denote substantially different computations...

By Sunny Gupta, Amit Sethi

arXiv Computer Vision

Oct 2

Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure

arXiv:2610.00680v1 Announce Type: cross Abstract: Curvature is often treated as an intrinsic property of a representation, although its empirical effect also depends on coordinate scale, learned logi...

By Athanasios Angelakis, Marta Gomez-Barrero

llms computer-vision safety

arXiv AI

Jun 12

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

arXiv:2606. 12629v1 Announce Type: cross Abstract: We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis.

By Varun Reddy Nalagatla

llms efficiency safety

arXiv Machine Learning

Sep 18

Cross-Architecture Foundation-Model Distillation for Edge Flood Segmentation

The paper presents a method for distilling a large 300‑million‑parameter geospatial foundation model (Prithvi‑EO‑2.0) into a compact 0.7‑million‑parameter EfficientViT‑B0 student for flood segmentation. By using the teacher to supervise additional unlabeled Sentinel‑2 imagery, the student’s training set expands without new manual labels, achieving competitive performance on Sen1Floods11 and STURM‑Flood while remaining smaller and faster. After quantization, the student runs as a 1.5‑MB INT8 TensorRT engine on a Jetson Xavier NX, processing 512×512 images in 5.57 ms with ~14 MB of memory.

By Fabian Schmalstieg, Karsten Mueller, Wojciech Samek

computer-vision fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 30

The Signed Geometry of One-Shot Recourse: On-Path Validity and the Signed-Curvature Criterion

arXiv:2609.36252v1 Announce Type: new Abstract: Closed-form recourse moves a rejected user along the unit gradient $\hat g$ of the classifier score $f$ by the promised distance $d_p=|f(x)|/\|\nabla f...

By Hazar Yueksel (Google)

arXiv AI

Aug 6

Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

arXiv:2608. 04190v1 Announce Type: new Abstract: Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures.

By Mario Leiva, Yue Ma, Qinru Qiu, Gerardo Simari, Paulo Shakarian

llms rag computer-vision benchmarks

One email a morning, machine-written

Related stories

A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization

Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

Cross-Architecture Foundation-Model Distillation for Edge Flood Segmentation

The Signed Geometry of One-Shot Recourse: On-Path Validity and the Signed-Curvature Criterion

Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models