- Working Effectively with AI Agents
More verified, useful outcomes—for less total human attention.
1 min - LOB-Bench: Orderbook Generative Model Evaluation Benchmark
A review of LOB-Bench, focusing on why generated order book models need rollout-level evaluation beyond one-step loss and stylized facts.
6 min - SFT Memorizes, RL Generalizes
A review of SFT Memorizes, RL Generalizes, focusing on how supervised finetuning and verifier-based reinforcement learning behave under shifted rules and visual inputs.
5 min - Post-Training of Modern LLMs
Modern LLM post-training, from preference learning to reinforcement learning with verifiable rewards.
6 min - One-step Generation in the Post Diffusion Era
Training-based routes toward one-step generation for diffusion and flow models, covering distillation, Consistency Models, CTM, MeanFlow, DMD, and Drifting Models.
12 min - Path Signature: Useful Feature for Timeseries
Study note on path signature in the literature of rough path theory. This post introduces the definition, algebraic structure, and probabilistic interpretation of signatures, bridging rough path theory and modern machine learning, based primarily on *A Primer on the Signature Method in Machine Learning*.
2 min - Beyond Defaults: Is Noise Conditioning Necessary for Diffusion Models?
A review of recent research that challenges the necessity of noise level conditioning in generative models, exploring alternative approaches to denoising and flow matching.
1 min - PinT algorithms for Diffusion Models
A review of researches that accelerate diffusion models in wall clock time by parallelization.
1 min
Back
Blog
Page 1 - Showing 8 of 13 posts
View all posts by years →