Amin Abyaneh

I’m a PhD candidate in AI and Robotics at McGill and Mila, advised by Prof. Hsiu-Chin Lin, where I work on robot learning, reinforcement learning, and world modeling. Early in my PhD, I focused on motion planning with provable stability guarantees grounded in the theory of dynamical systems. That foundation still shapes how I work: I’m especially drawn to diffusion-based methods and to grounding modern architectures in the same mathematics, which brings structure and reliability to learned behavior. More recently, I’ve turned toward multimodal learning as a way to give robots richer, more complete pictures of their surroundings, particularly by learning from tactile signals and contact forces.

Outside of research, I enjoy volleyball, Flamenco guitar, boxing, and the occasional run.

Papers Blog CV Misc

Latest Updates

Paper Jun 2026

Drift Q-Learning is out, a single-pass offline RL method that replaces denoising chains with a learned drift field.

Paper Jun 2026

QWM is out, a hardware-agnostic quadrupedal world model that transfers zero-shot to unseen robot morphologies.

Paper Mar 2026

TacFiLM is out, tactile modality fusion for vision-language-action models, in collaboration with NVIDIA Research.

Paper Mar 2026

VOCALoco accepted to IEEE Robotics and Automation Letters (RA-L).

Lecture Mar 2026

Guest lecture at COMP 765 (Robot Learning) on diffusion policies and contraction theory.

Paper Jan 2026

Contractive Diffusion Policies (CDP) accepted to ICLR 2026 — heading to Rio de Janeiro, Brazil.

Paper Jan 2025

Contractive Dynamical Imitation Policies accepted to ICLR 2025.

Publications

Drift Q-Learning overview

Drift Q-Learning

Anas Houssaini, Mohamad H. Danesh, Amin Abyaneh, Scott Fujimoto, Hsiu-Chin Lin, David Meger

QWM zero-shot locomotion transfer

Toward Hardware-Agnostic Quadrupedal World Models

Mohamad H. Danesh, Chenhao Li, Amin Abyaneh, Anas Houssaini, Kirsty Ellis, Glen Berseth, Marco Hutter, Hsiu-Chin Lin

TacFiLM overview comparing VLA baselines

Tactile Modality Fusion for Vision-Language-Action Models

Charlotte Morissette, Amin Abyaneh, Wei-Di Chang, Anas Houssaini, David Meger, Hsiu-Chin Lin, Jonathan Tremblay, Gregory Dudek

Contractive Diffusion Policies

Contractive Diffusion Policies

Amin Abyaneh, Charlotte Morissette, Mohamad Danesh, Anas Houssaini, David Meger, Gregory Dudek, Hsiu-Chin Lin

VOCALoco zero-shot locomotion

VOCALoco: Viability-Optimized Cost-Aware Adaptive Locomotion

Stanley Wu, Mohamad H. Danesh, Simon Li, Hanna Yurchyk, Amin Abyaneh, Anas El Houssaini, David Meger, Hsiu-Chin Lin

SCDS design overview

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery

Amin Abyaneh*, Mahrokh Boroujeni*, Hsiu-Chin Lin, Giancarlo Ferrari-Trecate

SNDS method overview

Globally Stable Neural Imitation Policies

Amin Abyaneh, Mariana Sosa Guzmán, Hsiu-Chin Lin

Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitation

Amin Abyaneh, Hsiu-Chin Lin

FedCDI framework design

Federated Causal Discovery From Interventions

Amin Abyaneh, Nino Scherrer, Patrick Schwab, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou