CASAXR26 — Day 1 Program
Day 1
Monday, 1 June 2026
TimeRoom H8-01-C (Main)Room H8-01-D (Second)
09:00–09:15Welcome to CASAXR26 — Prof. Nadia Magnenat Thalmann—
09:15–10:00🎤 Keynote 1—
10:00–10:30☕ Coffee Break—
10:30–11:45Session 1-1Session 2-1
11:45–13:00Session 1-2Session 2-2
13:00–14:00🍽️ Lunch Break—
14:00–15:15Session 1-3Session 2-3
15:15–15:45☕ Coffee Break—
15:45–17:00Session 1-4Session 2-4
17:00–18:30🥂 Welcome Drink — Hall H8—
CASAXR26 — Day 2 Program
Day 2
Tuesday, 2 June 2026
TimeRoom H8-01-C (Main)Room H8-01-D (Second)
09:00–09:15Welcome to CASAXR26—
09:15–10:00🎤 Panel: Reinventing Computer Animation through Generative AI and Virtual Worlds—
10:00–10:30☕ Coffee Break—
10:30–11:45Session 1-5Session 2-5
11:45–13:00Session 1-6Session 2-6
13:00–14:00🍽️ Lunch Break—
14:00–15:15Session 1-7Session 2-7
15:15–15:45☕ Coffee Break—
14:45–17:00Session 1-8—
19:30–21:30🍽️ Conference Dinner — Café Papon, Old Town—
CASAXR26 — Day 3 Program
Day 3
Wednesday, 3 June 2026
TimeRoom H8-01-C (Main)Room H8-01-D (Second)
09:00–09:15Welcome to CASAXR26—
09:15–10:00🎤 Keynote 2—
10:00–10:30☕ Coffee Break—
10:30–11:45Session 1-9—
11:45–13:00Session 1-10—
13:00–14:00🍽️ Lunch Break—
14:00–15:15Session 1-11—
15:15–15:45☕ Coffee Break—
15:45–16:15🏆 Award Ceremony & Closing Session—

Day 1 — Monday, June 1

CASAXR26 First Day · Rooms H8-01-C & H8-01-D

TimeEvent
09:00 – 09:15Welcome to CASAXR26
Prof. Nadia Magnenat Thalmann, President of CGS
09:15 – 10:00🎤 CGI Keynote 1
Prof. Jean-Remy Chardonnet
Multi-modal Learning for Biomedical Image Analysis and Visualisation
Chair: Nadia Magnenat Thalmann, MIRALab, University of Geneva
10:00 – 10:30☕ Coffee Break
10:30 – 11:45 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW-1: Agents
Chair: Daniel Thalmann, EPFL
Evaluating The Viability of Foundation Models in Virtual Agent Perception
Rubens Montanha, Ana Carolina Passos, Julia Melgare, Victor Araujo and Soraia Raupp Musse
Effects of Embodied Agent Body Type on Perceptions and Dietary Intentions in Digital Health Counseling
Sagar Ashok Vankit, Nafisa Sabnam Shama, Jay Ashish Kadam, Carlos Toxtli Hernandez and Matias Volonte
MADECM: A Curiosity-Augmented Evolutionary Algorithm for Multi-Agent Policy Diversity Optimization
Jinpeng Bai, Yv Fu, Xinning Wang, Chenguang Wang, Erqin Ke, Ziming Guo and Xin Yang
Virtual Human for Police Training in Virtual Reality: A Dynamic Model of a Suspect with Modulated Resistance and Means
Yvain Tisserand, Séolane Bouchoucha, Ben Meuleman and David Sander
🏛 Room H8-01-D — LNCS 1: Medical
Chair: Despina Michael-Grigoriou, Cyprus University of Technology
Bone-Window Segmentation Based Trajectory Planning for Cranial Puncture Navigation
Xujie Zhao, Ziyi Chen, Peng Tang, Hongping Deng, Zhiyong Yuan and Jianhui Zhao
FASRNet: Frequency Adaptive Structure Restoration Network for Medical Image Segmentation
Xuan Zhang, Deheng Zhu, Jing Dong, Rui Liu and Xiaopeng Wei
FedGAU: Efficient and Data-Free Federated Class Unlearning for Privacy-Preserving Medical Systems
Hao Zhang, Pengfei Wang and Dongsheng Zhou
Causal Attention and Multi-Granularity Feature Fusion for Surgical Visual Question Localized-Answering
Jinkui Tao, Wanshu Fan and Dongsheng Zhou
11:45 – 13:00 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW-2: Geometry & Rendering
Chair: Daniel Thalmann, EPFL
FOSP: Feature Orientated Sand Painting Generation
Meng Yang, Mengting Zhu, Jianglang Kang, Weiliang Meng and Ping Li
Parameter-preserving Real-time BIM Rendering with GPU Acceleration
Jaehyuk Lim, Donggyu Lee, Junghyun Han and Seung-wook Kim
CIG-Diff: Clinical-Intent and Geometry-Aware Diffusion for Low-Light Endoscopic Image Enhancement
Hong Zou, Wanshu Fan, Zhongbin Han and Dongsheng Zhou
Weakly-Supervised Dynamic Point Cloud Saliency Prediction Network
Hongyang Lv, Bailin Yang, Fangzhe Nan and Zhaoyi Jiang
🏛 Room H8-01-D — LNCS 2: Virtual Humans
Chair: Despina Michael-Grigoriou, Cyprus University of Technology
A Human-Centric Design Approach for XR in Cultural Heritage
Nedjma Cadi-Yazli, Thiago Freitas, Nadia Magnenat Thalmann, Marinos Ioannides and Drew Baker
A physics-constrained long-range navigational motion generation approach for indoor virtual humans based on deep reinforcement learning
Yutong Liu, Libo Sun and Wenhu Qin
LLM-Driven Personalities for Decision Making in Emergency Simulations
Stefano Calzolari, Rubens Montanha, Gabriel Schneider, Gustavo Wide, Paulo Knob, Francesco Strada, Andrea Bottino and Soraia Raupp Musse
13:00 – 14:00🍽️ Lunch Break
14:00 – 15:15 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 3: Virtual Reality
Chair: Jean-Remy Chardonnet, Arts&Métiers Institute of Technology
Realistic Trail Following Behavior in a Dynamically Deformable Terrain using Terrain-Based Penalty Fields
Hamza Noor and Muhammad Usman
A Multimodal Neurophysiological Framework for Real-Time Evaluation of User Experience in Virtual Architectural Environments
Hui Liang and Longfei Yang
Eye-tracking in virtual reality: usability assessment of a regional heritage museum
Michał Magryt, Szymon Mikołajczuk, Marcin Barszcz, Krzysztof Dziedzic, Maria Skublewska-Paszkowska, Pawel Powroznik and Sylwester Korga
From SVG to DSVG: Leveraging Foveal Visual Cues to Mitigate Cybersickness in Redirected Walking
Xinda Liu, Yongbo Tang, Xiaoning Liu, Pengbo Zhou and Guohua Geng
🏛 Room H8-01-D — LNCS 3: Animation & Simulation
Chair: Luciana Nedel, Federal University of Rio Grande do Sul (UFRGS), Brazil
Animating Socially-Oriented Driving Styles via Deep Reinforcement Learning in Mixed Traffic
Bo-Cyuan Lin and Sai-Keung Wong
A Rule-Based Pose Optimization Framework for Camera-View Expressiveness in Stylized Characters
Siyao Du, Boyuan Cheng, Yi Wen and Xiaosong Yang
Prompt-to-Motion: Editable Motion Representations for Controllable 2D Text-to-Animation
Emre Yildirim and Selim Balcisoy
Improved SDFIBM: An Efficient FLIP Fluid-Structure Interaction Method Based on Locally Adaptive Grids
Yuanjin Mou, Chang Jun Zou and Chen Xi Zhong
15:15 – 15:45☕ Coffee Break
15:45 – 17:00 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 4: Avatars & Immersion
Chair: Jean-Remy Chardonnet, Arts&Métiers Institute of Technology
Understanding User Perceptions Towards Queue Cutting In Immersive VR Environments
Elza Ibragimov, Natasha Kholgade Banerjee, Sean Banerjee and Ashutosh Shivakumar
Making Faces: Evaluating facial control methods in VR for live conversations
Sangeeth Chandran Jayachandran Kala, Marisa Llorens Salvador and Cathy Ennis
A Semantic-to-Motion Digital Twin Framework for Expressive Industrial Avatars in Telepresence
Damien Mazeas, Anthony Foulonneau and Jérémy Lacoche
Effects of Immersion Fidelity and Multimodal Support on Cognitive Load, User Experience, and Behavioral Intentions in Embodied Conversational Agent Interactions
Sagar Ashok Vankit et al.
🏛 Room H8-01-D — LNCS 4: Agents
Chair: Luciana Nedel, Federal University of Rio Grande do Sul (UFRGS), Brazil
Do Looks Matter for Classroom Embodied Conversational Agents? Evidence from a Seven-Week Homework Study
Nafisa Sabnam Shama, Jing-Yin Hung, Bart Knijnenburg and Matias Volonte
Avatars and Agents appearance biases explained by the theory of Social Categorization: A Virtual Reality study
Eloise Minder, Sylvain Fleury, Christophe Guillet and Jean-Rémy Chardonnet
CaseDigital: A Godot-Based Tool for Structured 3D Crime Scene Reconstruction and Investigative Visualization
Willy Delling and Dirk Labudde
17:00 – 18:00🥂 Welcome Drink — Hall H8

Day 2 — Tuesday, June 2

CASAXR26 Second Day · Rooms H8-01-C & H8-01-D

TimeEvent
09:15 – 10:00🎤 Panel: Reinventing Computer Animation through Generative AI and Virtual Worlds
Chair: Nadia Magnenat Thalmann, MIRALab – University of Geneva
Panellists
  • Jean-Remy Chardonnet — Arts&Métiers Institute of Technology, Châlon sur Saône
  • Manyola Kavakli-Thorne — Aston University, Birmingham, UK
  • Ping Li — The Hong Kong Polytechnic University
  • Despina Michael-Grigoriou — Cyprus University of Technology
  • Luciana Nedel — Federal University of Rio Grande do Sul (UFRGS), Brazil
  • Nicolas Pronost — LIRIS-SAARA, University Lyon-1, France
  • Daniel Thalmann — EPFL
10:00 – 10:30☕ Coffee Break
10:30 – 11:45 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 5: Simulation & Reconstruction
Chair: Nicolas Pronost, LIRIS-SAARA, University Lyon-1, France
CPSN: Collision-Overlap and Physics-Based Self-Supervised Neural Cloth Simulation
Tao Peng, Zhi Gong, Zili Zhang, Li Li and Xinrong Hu
Controlling Dendritic Ice and Frost Crystal Growth Along User-Drawn Trajectories
Yudai Ichimura and Syuhei Sato
Obstacle-Aware Fluid Control via Vector Potential
Yizhang Chen and Takashi Kanai
3D Hair Reconstruction from Sketches using Strand and Depth Maps
Ritsuki Ishiwata, Syuhei Sato and Shun Tatsukawa
🏛 Room H8-01-D — LNCS 5: View Synthesis & Visualization
Chair: Ping Li, The Hong Kong Polytechnic University
PIGS4TS: Physics-Interactive Gaussian Splatting for Traffic Scenes
Dongyan Yuan, Zhiwei Ma, Youquan Liu, Shaohui Jiao, Zhengxiong Liu and Panfeng Huang
Design and Evaluation of Comparative Visualization Techniques in Open-Field VR Environments
Ran Li, Zhiqi Xiao, Hao Jiang, Shuqin Gao, Honglong Zhao, Yancong Wang and Zhaoqi Wang
TreeCompletionNet: Multi-Resolution Optimization Completion Network of ALS Point Clouds for 3D Tree Reconstruction
Leyuan Lu, Weiyi Huang, Huiyu Li, Yanan Duan, Jun Pi, Ping Zhang and Shaojun Hu
GDR-Gaussians: Generative Depth Regularization for Efficient Factorized 3D Gaussian Splatting
Haishan Lai and Xianguo Liu
11:45 – 13:00 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 6: LLM, Generative AI & Cognition
Chair: Nicolas Pronost, LIRIS-SAARA, University Lyon-1, France
Text-to-3D City: Plan-then-Execute Urban Generation with LLM Planners and Procedural Synthesis
Xiaohang Dong, Hualong Yu, Xu Zhang, Jianye Wang and Qicheng Li
LLM-based modeling of 3D joint kinematics of the Polonaise folk dance for motion-to-text generation for user-feedback capabilities
Emilia Stefania Wójcik, Maciej Alencynowicz, Maria Skublewska-Paszkowska and Pawel Powroznik
A Multimodal Neuro-Adaptive Tutoring Agent for Children’s Classical Chinese Poetry Learning in VR
Hui Liang and Xue Wang
When is Fake Real Enough? Evaluating StyleGAN2 and NVAE Face Realism Across Animation and Visual Contexts
Maha Almaimani, Xiang Li, Joseph Kider, Matias Volonte and Eric Patterson
🏛 Room H8-01-D — LNCS 6: Vision & Recognition
Chair: Ping Li, The Hong Kong Polytechnic University
TeLE-Net: A Texture-Enhanced Edge Extraction Network
Fangbo Lu, Wanchuang Luo, Xuanzhao Zhao, Yulin Feng, Ding Liang, Xiaokun Sun and Meili Wang
Computer Vision for Wildlife Monitoring: Detecting Brown Howler Monkeys using YOLO
Gabriel Ferri Schneider, Guido Luis Glufke Mainardi, Paulo Ricardo Knob, Patrícia Dias, Márcia Jardim, Júlio César Bicca-Marques and Soraia Raupp Musse
Road Region Recognition and Path Parsing Methods in Various Styles Automotive Factory Floorplans
Junxi Wang, Yutong Fang, Hongxin Zhang and Wei Chen
A.D.A.M.O.: Agent for Domain-general Actions with Multimodal Observations
Stefano Calzolari, Alessandro Emmanuel Pecora, Francesco Strada and Andrea Bottino
13:00 – 14:00🍽️ Lunch Break
14:00 – 15:15 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 7: Sound, Haptics & Vehicles
Chair: Manyola Kavakli-Thorne, Aston University, Birmingham, UK
Feeling the Flow: A Real-time Multimodal Visuo-Haptic Interface for Interactive Fluid Dynamics in XR
Guoqing Chen and Min Xiong
SonicRadiation: Ghost-Cell-Free Hybrid Acoustic Simulation via Consistent Boundary-Grid Coupling
Xutong Jin, Fei Zhu, Guoping Wang and Sheng Li
NeuroSonic: Instant Neural Impact Sound Synthesis with Learned Acoustic Transfer
Junhan Zhao, Yiming Huang, Xutong Jin, Fei Zhu, Meng Gai and Sheng Li
Risk-Aware Motorcycle Interaction in Mixed Traffic Flow via Deep Reinforcement Learning
Yu-Tsen Wei, Kuo-Wei Ma, Guan-Hao Chen and Sai-Keung Wong
🏛 Room H8-01-D — LNCS 7: Virtual Reality
Chair: Thiago Freitas, MIRALab, University of Geneva
Exploring Pressure and Sensory Incongruence in Short-Distance VR Interaction
Tristan Maiore, Joffrey Guilmet, Sebastien George, Jean-Rémy Chardonnet and Diego Monteiro
Multimodal, Interactive, and Immersive Exploration for Enhanced and Personalized User Experience
Shamima Yasmin
🏛 Room H8-01-D — CAVW 9: Animation 2 (14:40–15:15)
Chair: Thiago Freitas, MIRALab, University of Geneva
Diverse Locomotion Styles from Linear- and Angular-Velocity Phase Manifolds
Seungmoo Jung and Takashi Kanai
Dynamic Fatigue Feature Injection for Simulating Fatigue Effects in Animation
Iliana Loi and Konstantinos Moustakas
15:15 – 15:45☕ Coffee Break
15:45 – 17:00 Parallel Sessions Room H8-01-C & H8-01-D
🏛 Room H8-01-C — CAVW 8: Human Motion
Chair: Manyola Kavakli-Thorne, Aston University, Birmingham, UK
TM-Edit: Text Guided Diffusion-Transformer based Motion Editing with Temporal Soft Masks Learning
Yu Zheng, Xuesi Qiu, Nan Xiang, Yulin Zhou and Zhao Wang
XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction
Nathan Salazar, Emmanuel Dellandréa, Mathieu Lefort and Alexandre Meyer
VMR: Training-Free 3D Motion Retrieval from Video
Jaeho Im and Minhye Kang
Beauty and the Beat: Music-Driven Choral Conducting with Beat-Aware Diffusion
Boyuan Cheng, Shang Ni, Yingjie Xi, Siyao Du, Jian J Zhang and Xiaosong Yang
🏛 Room H8-01-D — CAVW 10: Animation
Chair: Thiago Freitas, MIRALab, University of Geneva
DESTalker: Disentangling Emotion and Style for Expressive 3D Facial Animation via Residual Generation
Xu Yang, Shiguang Liu and Qing Xu
Musculoskeletal Motion Control and Generation Based on Muscle Synergies
Libo Sun, Jiwei Wen and Wenhu Qin
Analysis of Robustness in Biped Locomotion Controllers
Gangrae Park, Seung-Wook Ko, Taesoo Kwon and Yejin Kim
Text2Blueprint2Motion: Synthesis of Human-Object Interaction with Limbs Motion from Text
Lin Li, Zhen Liu, Tingting Liu and Xuyao Dai
19:30 – 21:30🍽️ Conference Dinner

Day 3 — Wednesday, June 3

CASAXR26 Third Day · Room H8-01-C · Closing Day

TimeEvent
09:00 – 09:15Welcome to CASAXR26
09:15 – 10:00🎤 CGI Keynote 2
Luciana Nedel — Federal University of Rio Grande do Sul (UFRGS), Brazil
Designing Next-Generation Simulators: Real-Time Immersion for Real Learning
Chair: Daniel Thalmann, EPFL
10:00 – 10:30☕ Coffee Break
10:30 – 11:45 — Room H8-01-C CAVW 11: Recognition Methods & Modeling
Chair: Nadia Magnenat Thalmann, MIRALab – University of Geneva
A Gait Recognition Method via Graph Convolutional Networks with Local Mask
Jing Jiang, Hongyu Shi, Yueping Kong, Yingxuan Huang and Jie Yang
CameraVQ: Vector-Quantized Representations for Monocular Camera Calibration
Daeun Cheong and Junghyun Han
Modeling Animal Motion from Observation to Synthesis: A Review
Yutong Guo, Boyuan Cheng, Siyao Du, Yi Wen and Xiaosong Yang
Controlling Form through Intent: A BCI-VR System for Enhancing Cultural Presence in Chinese Shadow Puppetry
Hui Liang and Xinyu Ye
11:45 – 12:45🏆 Award Ceremony & Closing Session

🏆 Thank you for joining CASAXR26!

Geneva, Switzerland · June 1–3, 2026