activity
20242026
collaborators

8 papers

cs.LG2026

On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity

Andrei Liviu Nicolicioiu, Mohammad Pezeshki, Aaron Courville

On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide…

cs.LG2026

Tapered Language Models

Reza Bayat, Ali Behrouz, Aaron Courville

Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly…

cs.CV2026

Data Selection Through Iterative Self-Filtering for Vision-Language Settings

Andrei Liviu Nicolicioiu, Sarvjeet Singh Ghotra, Morgane M. Moss +1

The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, resulting in sizeable datasets…

cs.CV2026

Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models

Samuel Lavoie, Michael Noukhovitch, Aaron Courville

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation us…

cs.IR2025

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation

Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro +2

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world…

cs.LG2025

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

Shawn Tan, Songlin Yang, Aaron Courville +2

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current…