Picture for Kevin Swersky

Kevin Swersky

University of Toronto

Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability

Add code
Aug 14, 2024
Viaarxiv icon

Exploring and Benchmarking the Planning Capabilities of Large Language Models

Add code
Jun 18, 2024
Viaarxiv icon

Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation

Add code
May 31, 2024
Viaarxiv icon

Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models

Add code
May 27, 2024
Viaarxiv icon

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Add code
Mar 08, 2024
Viaarxiv icon

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Add code
Dec 22, 2023
Viaarxiv icon

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

Add code
Nov 15, 2023
Viaarxiv icon

Directly Fine-Tuning Diffusion Models on Differentiable Rewards

Add code
Sep 29, 2023
Viaarxiv icon

Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single

Add code
Apr 21, 2023
Viaarxiv icon

Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks

Add code
Nov 01, 2022
Figure 1 for Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Figure 2 for Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Figure 3 for Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Figure 4 for Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Viaarxiv icon