arXiv AI July 7, 2026 By Ifrat Ikhtear Uddin, Yang Zhou, KC Santosh, Longwei Wang

Explainable Novel Category Discovery in Semantic Concept Space

arXiv:2607. 04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaque latent feature spaces.

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 arXiv AI.

multimodal

arXiv AI

Jun 30

Low-cost concept-based localized explanations: How far can we get with training-free approaches?

arXiv:2606. 29069v1 Announce Type: new Abstract: Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic concepts, yet validation is limited by the scarcity of fine-grained concept annotations.

By Darian Fern\'andez-Guti\'errez, Rafael Bello, Marilyn Bello, Natalia D\'iaz-Rodr\'iguez

llms rag multimodal

Hugging Face Trending Papers

Jul 27

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection

Open-world object detection (OWOD) requires a detector to recognize known categories, discover unnamed objects from unseen categories, and incrementally learn newly annotated classes. PROB improves unknown discovery by modeling class-agnostic probabilistic objectness in the decoder-query space.

computer-vision multimodal

arXiv AI

Jul 28

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection

arXiv:2607. 23981v1 Announce Type: cross Abstract: Open-world object detection (OWOD) requires a detector to recognize known categories, discover unnamed objects from unseen categories, and incrementally learn newly annotated classes.

By Weijun Tian, Rui Liu

computer-vision multimodal

arXiv AI

Aug 18

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

arXiv:2608. 15731v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust.

By Haadia Amjad, Ronald Tetzlaff

agents computer-vision robotics safety

arXiv AI

Jun 9

A Geometric Unification of Concept Learning with Concept Cones

arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.

By Alexandre Rocchi, Thomas Fel, Gianni Franchi

efficiency safety

arXiv AI

Jun 30

On the Faithfulness of Post-Hoc Concept Bottleneck Models

arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.

By Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Low-cost concept-based localized explanations: How far can we get with training-free approaches?

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection

Multimodal Semantic-Probabilistic Objectness for Open World Object Detection

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

A Geometric Unification of Concept Learning with Concept Cones

On the Faithfulness of Post-Hoc Concept Bottleneck Models