Talks
- 31-08-2023 Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
- 08-06-2023 Learning from Language Models for Visual Intelligence
- 25-05-2023 Unsolved ML Safety Problems
- 11-05-2023 3D Generation from Unstructured Single-view Data
- 28-04-2023 Vision-and-Language Alignment - Towards Universal Multimodal AI
- 13-04-2023 Advancing Semi-Supervised Learning: Methods and Benchmarks
- 06-04-2023 Customizing Large-Scale Generative Models
- 23-03-2023 The Case for Reasoning Beyond Recognition
- 16-03-2023 On the Gauge Transformation of Neural Fields
- 14-03-2023 Depth Estimation from Unstabilized Mobile Photography
- 02-03-2023 Adaptive and Trustworthy NLP with Retrieval for Information Access for Everyone
- 23-02-2023 Unknown-Aware Learning for Object Detection and Beyond
- 16-02-2023 MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
- 09-02-2023 Personalizing Text-to-image Generation
- 07-12-2022 Improving Robustness to Distribution Shifts: Methods and Benchmarks
- 01-12-2022 StyleGAN-Based Portrait Image and Video Style Transfer
- 24-11-2022 Principled Solutions for Efficient Artificial Neural Networks
- 17-11-2022 Prompting-based Continual Learning
- 13-10-2022 Finetuning Vision Models: Improving Robustness and Accuracy
- 06-10-2022 Architectures and Training for Visual Understanding