- Hi, this is Nemo speaking. I’m a senior undergraduate student at Yao Class, Tsinghua University, persuing a B.S. in Computer Science.
- My goal is to share a piece of my mind here. Topics may include but not limited to: Computer Science (especially AI-related subjects, e.g. Machine Learning, Reinforcement Learning, Generative Models,etc.), Mathematics, Physics, and Simply Thoughts on Life. Enjoy!
What Matters for Dexterous RL?
Reading notes on dexterous RL: reset distributions, goal-conditioned pretraining, structured exploration, motion tracking, contact priors and simulation.
How to train your Robo-centric VLMs
Reading notes on Robo-centric VLMs: data construction, spatial grounding, multi-task training, and closed-loop robot execution.
Fantastic Mega-Scale RL Recipes and where to find them
Reading notes on Mega-Scale RL: batches, multiple policies, reset distributions and off-policy methods.
Loops Inside the Denoiser
Reading notes on ELT, Looped-DiT and LiFT, with comparisons to hidden states across steps and DEQ.
A Hitchhiker's Guide To Diffusion RL
My reading notes on diffusion / flow post-training, comparing the approaches used in image/video generation and robotics.
AHEAD · Before Tomorrow
When the future can be watched in advance, what is left of living? A short science-fiction story about world models, hindsight, and the unknown.
Life Logging: The Quiet Shift Toward Giving AI All Your Context
A reflection on how my personal AI usage has evolved from pasting error messages to full-blown life logging, and why I believe this trajectory — giving agents ever more context about your life — is how the future will unfold.
Beyond the Hype: How I See World Models Evolving in 2025
A summary of my personal opinions on world models in 2025, covering their current state, future prospects, and implications for embodied AI. Discusses 3D modeling approaches, data challenges, research directions, and the role of JEPA-style architectures in the evolution of world models.
Algebra and Computation
Lecture notes and Cheat Sheet for Course: Algebra and Computation, which is a course offered to Freshman students at Yao Class.
Titans: Learning to Memorize at Test Time
This article introduces Titans, a novel architecture that as a meta in-context learner, learns to memorize at test time. Through designing a long-term memory module, and proposing three variants of Titans (MAC, MAG, MAL), the model achieves superior performance compared to Transformers and other baselines, especially in long-context tasks.