This is your work, valued
NextLat. Official codebase for "Next-Latent Prediction Transformers Learn Compact World Models"
144MORL-Generalization. Benchmark for evaluating the generalization capabilities of Multi-Objective Reinforcement Learning (MORL) algorithms.
31beyond-next-token-prediction. Curated collection of research on the limitations of next-token prediction and methods that go beyond it.
27CMU-15213-notes.
3ML-Research-Notes. 👨🏻🎓 Personal notes on Machine Learning research and mathematics
2Drone-Routing-WQMIX. 🚁💨 Drone Routing using Deep Reinforcement Learning (Weighted QMIX)
1traffic-LLM. 🚗 Enhancing Traffic Forecasting and Summarization with Small-Scale Language Models through Knowledge Distillation and Data Engineering
1