Tuesday 18 November 2025
informatics.ed.ac.ukยท19h
๐data science
Flag this post
The model underlying R-hat and a Bayesian estimator
statmodeling.stat.columbia.eduยท11h
๐data science
Flag this post
A Deep Dive into the Morris Worm
๐ธsmall web
Flag this post
Quantifying the reasoning abilities of LLMs on clinical cases
nature.comยท19h
๐ฅPyTorch
Flag this post
Gated DeltaNet (Linear Attention variant in Qwen3-Next and Kimi Linear)
๐ง deep learning
Flag this post
How I Leverage LLMs
๐คllm
Flag this post
Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
arxiv.orgยท2h
๐คllm
Flag this post
Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance
arxiv.orgยท2d
๐คllm
Flag this post
REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs
arxiv.orgยท2h
๐ง deep learning
Flag this post
Writing an LLM from scratch, part 27 โ what's left, and what's next?
๐ง deep learning
Flag this post
When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning
arxiv.orgยท2d
๐คHugging Face
Flag this post
Decoupled Entropy Minimization
arxiv.orgยท1d
๐ง deep learning
Flag this post
LGCC: Enhancing Flow Matching Based Text-Guided Image Editing with Local Gaussian Coupling and Context Consistency
arxiv.orgยท2d
๐ง deep learning
Flag this post
Loading...Loading more...