| Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity | Nov 7, 2024 | DiversityMeta Reinforcement Learning | CodeCode Available | 0 |
| Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli | Nov 3, 2024 | Optical Flow EstimationSemantic Segmentation | CodeCode Available | 0 |
| ZIM: Zero-Shot Image Matting for Anything | Nov 1, 2024 | Image InpaintingImage Matting | CodeCode Available | 3 |
| JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking | Oct 31, 2024 | Code CompletionOpen-Domain Question Answering | —Unverified | 0 |
| Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning | Oct 31, 2024 | Graph Neural Networkreinforcement-learning | —Unverified | 0 |
| Instruction-Tuning Llama-3-8B Excels in City-Scale Mobility Prediction | Oct 31, 2024 | Disaster ResponseLanguage Modeling | CodeCode Available | 1 |
| GHIL-Glue: Hierarchical Control with Filtered Subgoal Images | Oct 26, 2024 | Imitation LearningVideo Prediction | —Unverified | 0 |
| Random Policy Enables In-Context Reinforcement Learning within Trust Horizons | Oct 25, 2024 | In-Context LearningIn-Context Reinforcement Learning | —Unverified | 0 |
| Adversarial Environment Design via Regret-Guided Diffusion Models | Oct 25, 2024 | Deep Reinforcement LearningDiversity | —Unverified | 0 |
| BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning | Oct 24, 2024 | Instruction FollowingNatural Language Understanding | —Unverified | 0 |
