arXiv AI

Anchor Divergence for Semantic Geometry in Contrastive Learning

The paper introduces Anchor Divergences, a technique that leverages contrastive learning, exponential families, and information geometry to define context‑specific semantic geometries on fixed vector representations. By establishing a correspondence between probability distributions over anchors and Bregman geometries, the method allows the geometry itself to be modeled through the anchor distribution. Experiments on retrieval tasks demonstrate that Anchor Divergences effectively and efficiently capture context‑dependent semantic similarity.

arXiv Machine Learning

Sep 11

Divergence-Based Similarity Function for Multi-View Contrastive Learning

The paper introduces a divergence-based similarity function (DSF) for multi-view contrastive learning, representing each set of augmented views as a distribution and measuring similarity via distribution divergence. DSF captures joint structure across all views, outperforming prior pairwise methods on tasks such as kNN classification, linear evaluation, transfer learning, and distribution shift. It also offers greater efficiency and eliminates the need for a temperature hyperparameter, unlike cosine similarity.

By Jaehyoung Jeon, Cheolsu Lim, Myungjoo Kang

fine-tuning

Hugging Face Trending Papers

Oct 7

Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs

Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation. However, these models still struggle to interpret multi-phenotype lesions whose diagnosis requi...

llms rag diffusion nlp efficiency multimodal safety

arXiv Computer Vision

Oct 8

Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs

The paper introduces PureVision, a geometry‑supervised framework for medical vision‑language models that tackles the challenge of interpreting multi‑phenotype lesions. It comprises PureEyes, which imposes geometric constraints to preserve anatomical hierarchies and phenotypic subclass relationships, and PureNeurons, which aggregates lesion‑specific anatomical and phenotypic evidence in a learned latent space. Experiments on LIDC‑IDRI, CBIS‑DDSM, and 3DReasonKnee show that PureVision enhances lesion grounding and phenotype characterization in visual question answering and radiology report generation.

By Hao Wang, Qiwei Zeng, Shuchang Ye, Jinghao Lin, Yuezhe Yang, Yige Peng, Jinman Kim, Lei Bi

llms rag diffusion nlp efficiency multimodal safety

arXiv Machine Learning

Jul 24

Semantics at an Angle: When Cosine Similarity Works Until It Doesn't

arXiv:2504. 16318v3 Announce Type: replace Abstract: Cosine similarity is a standard comparison rule for learned representations in information retrieval, natural language processing, computer vision, and multimodal learning.

By Kisung You

rag computer-vision nlp multimodal safety

arXiv AI

Jul 7

Language Models Represent and Transform Concepts with Shared Geometry

arXiv:2607. 04525v1 Announce Type: cross Abstract: How concepts are represented in neural networks is a fundamental question in machine learning.

By Zhimin Hu, Lanhao Niu, Sashank Varma

llms

arXiv AI

Jun 30

Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms

arXiv:2606. 30625v1 Announce Type: cross Abstract: Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignoring embedding magnitudes.

By Ziwei Su, Junyu Ren, Victor Veitch

rag

Hugging Face Trending Papers

Jul 5

Language Models Represent and Transform Concepts with Shared Geometry

How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as stationary geometric objects.

llms

arXiv AI

Jun 2

Global Geometry Is Not Enough for Vision Representations

arXiv:2602. 03282v2 Announce Type: replace-cross Abstract: A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations.

By Jiwan Chung, Seon Joo Kim

rag

arXiv Machine Learning

Jul 16

The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model

arXiv:2607. 13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry.

By Zijie Yu, Gaowen Liu, Ramana Rao Kompella, Philip S. Yu, Yue Song

rag diffusion multimodal

arXiv Computer Vision

Sep 17

Semantically Calibrated Evidence Composition for CT Vision-Language Learning

arXiv:2608.00239v2 Announce Type: replace Abstract: Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods...

By Guoliang You, Haifan Gong, Xiaomeng Chu

multimodal benchmarks safety

arXiv AI

Jun 2

Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training

arXiv:2601. 23220v2 Announce Type: replace-cross Abstract: Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical perceptual deficit: geometric blindness.

By Anglin Liu, Ruichao Chen, Yi Lu, Hongxia Xu, Jintai Chen

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 8

Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology

arXiv:2605. 18419v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology.

By Franciskus Xaverius Erick, Johanna Paula M\"uller, Bernhard Kainz

llms rag fine-tuning efficiency multimodal safety

Related stories