Embodied AI2013
Open textbook for upper-level undergraduates that explains computational principles behind autonomous robots — mechanisms, sensors, actuators, perception, and planning — with exercises and simulation assets. Distributed as LaTeX source under a CC-BY-NC-ND license and accompanied by course materials and Webots examples.
AI Others2014
Provides a complete, university-level computer science curriculum assembled from free online courses and books. Curates degree-aligned course sequences (Intro / Core / Advanced) with community support, project guidance, and checklists to track progress for self-directed learners.
AI Others2021
Curated self-study roadmap and reading-list for learning computer science end-to-end — organizes open courses, textbooks, and project recommendations across programming languages, systems, algorithms, AI/ML and more; aimed at motivated learners planning a 2–3 year self-directed path.
Reduces object-driven shortcut learning in zero-shot compositional action recognition by enforcing temporal verb cues and regularizing against frequent object-verb co-occurrence priors. Proposes RCORE with Co-occurrence Prior Regularization (treats frequent co-occurrences as hard negatives) and Temporal Order Regularization. Evaluated on Sth-com and EK100-com with improved compositional generalization.
AI Dataset2026
Early-preview (≈1.2k rows) dataset of agentic coding prompts and unedited model responses generated by DeepSeek‑V4‑Pro, covering real-world programming tasks across many languages. Intended for research, filtering, and model evaluation rather than production training without review.
AI Dataset2026
Agentic coding evaluation dataset containing real-world, multi-step developer tasks and raw model responses across 20+ programming languages. Emphasizes challenging, persona-driven prompts for benchmarking and fine-tuning; users should filter and audit outputs before training.
Stabilizes on-policy policy distillation by dynamically constructing a proximal teacher that controls gradient variance. Provides theoretical global convergence and monotonic improvement bounds, and shows improved training stability, sample efficiency, and final performance on mathematical reasoning tasks with zero extra compute overhead.