13 papers
Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients
Aram Davtyan, Pablo Acuaviva, Sebastian Stapf +1
Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own weights,…
GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction
Chenrui Fan, Paolo Favaro
Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through static scenes. For these outputs,…
World Model Self-Distillation: Training World Models to Solve General Tasks
Sebastian Stapf, Pablo Acuaviva Huertos, Aram Davtyan +1
Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual descriptions limits their di…
Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
Aram Davtyan, Leello Tadesse Dadi, Volkan Cevher +1
Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image…
COMiT: Learning Structured Visual Tokens through Sequential Communication
Aram Davtyan, Yusuf Sahin, Yasaman Haghighi +4
Discrete image tokenizers provide a sequential interface for vision and multimodal models, but are typically optimized for reconstruction or compression and therefore tend to encod…
Rethinking Visual Intelligence: Insights from Video Pretraining
Pablo Acuaviva, Aram Davtyan, Mariam Hassan +4
Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This su…
From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
Pablo Acuaviva, Aram Davtyan, Mariam Hassan +4
Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere vide…
KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
Zixuan Xia, Aram Davtyan, Paolo Favaro
We propose KOALA++, a scalable Kalman-based optimization algorithm that explicitly models structured gradient uncertainty in neural network training. Unlike second-order methods, w…
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
Mariam Hassan, Sebastian Stapf, Ahmad Rahimi +17
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, ou…
CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation
Aram Davtyan, Sepehr Sameni, Björn Ommer +1
The field of video generation has expanded significantly in recent years, with controllable and compositional video generation garnering considerable interest. Most methods rely on…
Multi-View Unsupervised Image Generation with Cross Attention Guidance
Llukman Cerkezi, Aram Davtyan, Sepehr Sameni +1
The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-vi…
Sparse 3D Reconstruction via Object-Centric Ray Sampling
Llukman Cerkezi, Paolo Favaro
We propose a novel method for 3D object reconstruction from a sparse set of views captured from a 360-degree calibrated camera rig. We represent the object surface through a hybrid…
Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
Aram Davtyan, Paolo Favaro
We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-…