New from Snorkel AI: Weaver combines weak verifiers to boost LLM output quality: no fine-tuning needed. +14.5% accuracy 98.2% of gains, 99.97% less compute (via distillation) Outperforms naive voting, rivals GPT-4o Read the full paper
MACHINE LEARNING
-
KL Divergence Measurement on Reinforcement Learning Outputs
By
–
no, because it's KL measured on the RL outputs
-
DreamScene: 3D Gaussian Text-to-3D Scene Generation
By
–
DreamScene
— AK (@_akhaliq) 31 juillet 2025
3D Gaussian-based End-to-end Text-to-3D Scene Generation pic.twitter.com/9fEDUEj0uRDreamScene 3D Gaussian-based End-to-end Text-to-3D Scene Generation
-
Building AutoRL: A Great Reinforcement Learning Achievement
By
–
It's really great. I built a lot of AutoRl w/ it 🙂
-
DeepSeek builds self-sufficient AI talent pipeline amid US-China competition
By
–
This @WSJ piece on China/US AI competition highlights research from @StanfordHAI Senior Fellow @AmyZegart and other scholars examining DeepSeek's increasingly self-sufficient pipeline of homegrown AI talent.
-
Pretraining Data and Gradient-Matching Training Approaches
By
–
oh cool, is it *pretraining* data? and they do the same gradient-matching thing? i wonder what the advantage is over just mixing in and doing supervised training on a few examples every now and again
-
RLHF Training: Avoiding Model Drift Through Gradient Mixing
By
–
here's some free alpha: if we do RL for too long after pretraining, we will surely overwrite parameters and start to forget things in the original instructGPT paper, their best model mixed RLHF with pretraining gradients to avoid exactly this model drift issue yet no one is
-
Efficient Differentially Private LLM Fine-Tuning via Reinforcement Learning
By
–
Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
-
MLX Model Requires 96GB RAM, Runs Space Invaders Game
By
–
This full precision MLX model needs 63.5GB of RAM while running (so likely needs a Mac with 96GB or 128GB) – but its space invaders is fully functional! https://t.co/0TVkYrAIxV
— Simon Willison (@simonw) 31 juillet 2025This full precision MLX model needs 63.5GB of RAM while running (so likely needs a Mac with 96GB or 128GB) – but its space invaders is fully functional!
-
Reasoning Model Generalization: Math to Creative Writing Transfer
By
–
i'm looking for good examples of reasoning model generalization for example, a model incentivized via RL to think for a while and solve math problems gets better at creative writing is this common?