 Learning to Sample Effective and Diverse Prompts for Text-to-Image GenerationComputer Vision and Pattern Recognition (CVPR), 2025 |
 Audiopedia: Audio QA with KnowledgeIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 |
 Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam
TimestepsNeural Information Processing Systems (NeurIPS), 2024 |
 Non-Stationary Learning of Neural Networks with Automatic Soft Parameter
ResetNeural Information Processing Systems (NeurIPS), 2024 |
 CALE: Continuous Arcade Learning EnvironmentNeural Information Processing Systems (NeurIPS), 2024 |
 Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control TasksInternational Conference on Learning Representations (ICLR), 2024 |
 Plastic Learning with Deep Fourier FeaturesInternational Conference on Learning Representations (ICLR), 2024 |
 Self-Normalized Resets for Plasticity in Continual LearningInternational Conference on Learning Representations (ICLR), 2024 |
 Prioritized Generative ReplayInternational Conference on Learning Representations (ICLR), 2024 |
 One Step Diffusion via Shortcut ModelsInternational Conference on Learning Representations (ICLR), 2024 |
 SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2024 |
 MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLInternational Conference on Learning Representations (ICLR), 2024 |
 Neuroplastic Expansion in Deep Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2024 |
 Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLInternational Conference on Learning Representations (ICLR), 2024 |
 Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model PretrainingInternational Conference on Learning Representations (ICLR), 2024 |
