arXiv AI July 7, 2026 By Yiran Xiao, George Legrady

Attention Dynamics in Diffusion Models: A Visual Analytics Framework for Human-AI Collaboration

arXiv:2607. 02563v1 Announce Type: cross Abstract: Diffusion-based text-to-image models can synthesize complex and highly structured visual content, yet the emergence and evolution of semantic structure remain difficult to interpret.

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.

arXiv AI

Jul 7

Attending to Multimodal Generation One Token at a Time

arXiv:2607. 03738v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context.

By Varun Gupta, Vineet Gandhi, Makarand Tapaswi

llms multimodal safety

arXiv Machine Learning

Jul 7

Pathways of Visual Information Flow in Vision-Language Models

arXiv:2607. 03358v1 Announce Type: cross Abstract: We study how visual information is routed in vision-language models (VLMs).

By Israfel Salazar, Stella Frank, Dan Oneata, Desmond Elliott, Constanza Fierro

llms multimodal benchmarks

Hugging Face Trending Papers

Jul 2

InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

Text-conditioned human interaction generation must capture both long-range temporal causality within each individual and tightly coupled coordination between partners. Existing interaction diffusion models typically denoise full sequences using bidirectional attention, which obscures causality and hinders streaming and long-horizon generation.

llms diffusion benchmarks safety

arXiv AI

Jul 28

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.

By Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang

llms multimodal benchmarks safety

arXiv Computation and Language

Sep 7

From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

The study examines how Vision‑Language Models (VLMs) integrate visual evidence into language‑based decisions by applying layer‑wise causal interventions on video‑text attention pathways in a video‑based generative multiple‑choice setting. Findings reveal that visual information is primarily incorporated while processing candidate answer options, with nouns serving as key semantic anchors and verbs becoming important during temporal reasoning. The research also uncovers a distinct pattern in temporal reasoning, indicating that VLMs struggle to reconstruct sequential information across video frames, possibly due to linguistic biases in temporal expressions.

By Davide Testa, Hugh Mee Wong, Alessandro Lenci, Bernardo Magnini, Albert Gatt

llms multimodal

arXiv AI

Jun 4

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

arXiv:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.

By Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or

llms diffusion multimodal safety

One email a morning, machine-written

Related stories

Attending to Multimodal Generation One Token at a Time

Pathways of Visual Information Flow in Vision-Language Models

InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers