arXiv Machine Learning June 25, 2026 By Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele, Andrea Dittadi, Simon Buchholz

Logit Distance Bounds Representational Similarity

Read the original on arXiv Machine Learning →

arXiv:2602. 15438v3 Announce Type: replace Abstract: For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations are equal up to an invertible linear transformation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 3

Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models

arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.

By Alexander Guha

llms rag diffusion

arXiv AI

Jun 30

Multimodal Representation Alignment for Cross-modal Information Retrieval

arXiv:2506. 08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways.

By Fan Xu, Luis A. Leiva

llms rag multimodal benchmarks safety

arXiv Machine Learning

1d ago

The Distributional View of Knowledge Distillation

arXiv:2608. 15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler gradient is blind to which wrong token receives probability mass.

By Gordei Verbii, Juho Lee

rag fine-tuning efficiency

arXiv Machine Learning

Jul 13

Similarity search generalisation in contrastive learning with InfoNCE loss

arXiv:2607. 09405v1 Announce Type: new Abstract: Similarity search is a primary application of embedding models trained by contrastive learning.

By Nick Whiteley

rag safety

arXiv Machine Learning

Aug 4

Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models

arXiv:2608. 01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories.

By Leyan Xue, Feng Xiong, Mingjun Ma, Changqing Zhang

llms efficiency multimodal benchmarks

arXiv AI

Aug 3

Guarantees on Dynamical System Distinguishability for LLM Token Generation

arXiv:2607. 28667v1 Announce Type: cross Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs.

By Mohamed Akrout, Dan Wilson

llms rag

Related stories

Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models

Multimodal Representation Alignment for Cross-modal Information Retrieval

The Distributional View of Knowledge Distillation

Similarity search generalisation in contrastive learning with InfoNCE loss

Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models

Guarantees on Dynamical System Distinguishability for LLM Token Generation