Skip to content

Category

diffusion models

2,370 papers

#artificial intelligence Open access Oct 2026

A Fine-Grained Image Dataset of Gold and Silver Artifacts from the Tomb of Prince Liangzhuang and Preliminary LoRA-Based Generation Experiments

The digital preservation of cultural heritage is evolving from static archiving towards intelligent creation. As representative examples of early Ming Dynasty gold and silver craftsmanship, the gold and silver artifacts from the Tomb of Prince Liangzhuang, with their complex craftsmanship and rich cultural significance...

Yelei Chen, Yifan Xu, Lei Shu et al. · 0 citations

A Model Coupled with Fractional-Derivative and Peridynamic Theory for Water Migration in Unsaturated Expansive Clay

Expansive clay exhibits multiple fissures and undergoes deterioration due to fluctuations in moisture levels. To guarantee the stability of earth structures built on expansive clay in semiarid regions, significant emphasis has been placed on studying the effects of water migration. This paper introduces an innovative...

Qiu-Yan Liu · 0 citations

Local coordination and migration-network topology shape Li-ion transport and delithiation in the low-energy ɛ-LiMnO2 polymorph

In rocksalt-derived oxide cathodes, the local Li-migration environment around an O 4 tetrahedral intermediate is commonly classified by the number of face-sharing transition-metal (TM) neighbors. In LiMnO 2 , the TM species is Mn, and 0-TM denotes the absence of face-sharing Mn neighbors. However, migration and delithi...

Fu-Kuan Wang, Bu-Sheng Wang, Yong Liu · 0 citations

ST-Policy: Encoding Spatiotemporal Continuity for Diffusion Policy

Diffusion-based visuomotor policies are a powerful paradigm for robotic imitation learning, yet their sequence models apply a uniform inductive bias at every position of the action sequence, ignoring the spatiotemporal continuity inherent in robotic motion. We identify a fundamental limitation of causal state space mod...

Ying-Zhao Li, Liang Zheng, Wu-Jie Chen et al. · 0 citations
#diffusion models Open access Nov 2026

DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model

This work proposes a novel method called DiffMove that harnesses crowd wisdom for trajectory recovery and integrates group mobility tendencies and individual preferences into the spatiotemporal distribution of the trajectory to recover high-quality trajectories.

Qing-Yue Long, Can Rong, Huan-Dong Wang et al. · 0 citations

FALCON: A Diffusion Model-Empowered Semantic Communication Framework for Low-Altitude Wireless Networks

The low-altitude wireless network (LAWN), characterized by reconfigurability and multi-functionality, is enabling diverse applications and fostering enhanced collaboration between uncrewed aerial vehicles (UAVs) and terrestrial nodes. Semantic communication, a transformative paradigm in sixth-generation (6G) networks,...

Xu-Peng Niu, Wei-Jie Yuan, Qing-Qing Cheng et al. · 0 citations
#generative ai Nov 2026

Generative AI Model Assisted Multimodal Semantic Vehicular Edge Computing for Collaborative Perception

Vehicular edge computing (VEC) plays a pivotal role in enabling cooperative perception for connected autonomous vehicles (CAVs), providing comprehensive environmental awareness for safe vehicle control and road safety. However, collaborative perception in VEC faces significant challenges arising from stringent bandwidt...

Wen-Qiang Ma, Wen Sun, Jian-Hua He et al. · 0 citations
#diffusion models Open access Oct 2026

Generative Data-Augmented Surrogate Modelling Framework for Field Quality Improvement in ReBCO Bulk Undulators Under Limited Data Constraints

Abstract High-temperature superconducting (HTS) bulk staggered-array undulators can generate record-breaking magnetic fields for compact light sources, but their performance is limited by non-uniform magnetic field profiles. This spatial inhomogeneity is directly related to variations in the critical current density am...

Mohsen Abdolahi, A. Larry Arsenault, Shahin Alipour Bonab et al. · 0 citations
#diffusion models Open access Oct 2026

An extended Taylor–Aris Framework for Thermal Front Propagation in Conjugate Pipe Flows: The Plug-Flow Limit

A reduced one-dimensional unsteady description of thermal-front propagation in conjugate pipe flows is developed here for the plug-flow limit. The starting point is the analytical advection–diffusion solution for an adiabatic fluid domain, with its characteristic exponential–error-function form. The plug-flow assumptio...

G. Cuccurullo, Carmela Concilio, Vincenzo Mario La Rocca et al. · 0 citations
#diffusion models Open access Oct 2026

Leveraging Imaging and Computational Modeling to Characterize Sex-Specific Musculoskeletal Form and Function

The organization of skeletal muscle influences how force is generated and transmitted to produce joint torque. However, isolating muscle morphology contributions to functional capacity remains difficult, as torque reflects interacting effects between muscle size, internal architecture, mechanical leverage, activation,...

Mario E. Garcia · 0 citations

Research on partial occluded face recognition based on diffusion models and deep feature completion

Partial facial occlusion caused by masks, sunglasses, scarves, and other objects significantly degrades the performance of conventional face recognition systems due to the loss of discriminative identity information. To address this challenge, this paper proposes a Diffusion-driven Deep Feature Completion Network (DDFC...

Shiguang Wang · 0 citations
#diffusion models Conference Oct 2026

Research on multiclass game image generation based on classifier-free diffusion guidance

Diffusion models have achieved remarkable progress in visual generation, yet their practical deployment for multi-class procedural scene synthesis still lacks standardized training schemes and comprehensive performance verification. This study adopts DDPM as the base architecture and introduces classifier-free guidance...

Jing-Yi Fan · 0 citations

From tech blogs

See all →
MIT News · Artificial Intelligence Oct 15, 2026

AI model decodes the language cells use to communicate

A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.

Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.