Efstratios Gavves

Associate Professor@University of Amsterdam·荷兰·OpenReview

研究方向

Dynamical Deep Learning · Causal Representation Learning · Physics-informed Deep Learning · Video Understanding · Deep Learning · Fine-grained Classification · Computer Vision · Geometry in Vision

Efstratios Gavves

Grounding Continuous Representations in Geometry: Equivariant Neural Fields

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Mechanistic PDE Networks for Discovery of Governing Equations

Language Agents Meet Causality -- Bridging LLMs and Causal World Models

Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes

CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

Geometric Neural Process Fields

From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields

Benchmark for Temporal, Ambiguous, and Grounded Embodied Question-Answering

PowerNet: Truncated Matrix Power Series as Quasi-Equivariant Layers

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Mechanistic Neural Networks

Motion Flow Matching for Efficient Human Motion Synthesis and Editing

Latent Lie Group Representations

Contrastive Implicit Representation Learning