Concept · 9 episode(s)

LoRA

← all concepts

Definition

LoRA (Low-Rank Adaptation) fine-tunes a model by training small low-rank update matrices on top of frozen base weights, slashing the compute and memory needed for adaptation. It’s the default way most teams customize a foundation model without doing full fine-tuning.

Episodes covering this

  1. 199
    Finding a Model's Hidden Behaviors Without Knowing What You're Looking For
    Mechanistically Eliciting Latent Behaviors in Language Models
    Mack, Panickssery, Turner · Principles of Intelligence·15 min·Jul 04, 2026
  2. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
    Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
    Zhang, Hu, Glentis et al. · University of Minnesota·22 min·Jul 02, 2026
  3. 192
    A 32B Open Model Matched Frontier Systems By Learning to Take Notes
    AutoMem: Automated Learning of Memory as a Cognitive Skill
    Wu, Zhu, Zhang et al. · Stanford University·22 min·Jul 02, 2026
  4. 158
    How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
    FloatDoor: Platform-Triggered Backdoors in LLMs
    Loose, Sander, Mächtle et al. · University of Luebeck·29 min·Jun 19, 2026
  5. 128
    How a Model Can Earn Full Reward and Still Resist Training
    Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization
    Xiao, Phuong · California Institute of Technology·29 min·Jun 11, 2026
  6. 114
    Agents That Rewrite Their Own Weights Instead of Just Taking Notes
    Scaling Self-Evolving Agents via Parametric Memory
    Ren, Luo, Yang et al. · Peking University / Alibaba Group·26 min·Jun 04, 2026
  7. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
    NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
    Lu, Fang, Zhong et al. · University of Georgia·26 min·May 20, 2026
  8. 026
    What RL Actually Does to Language Models, at the Token Level
    Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
    Akgül, Kannan, Neiswanger et al. · University of Southern California·24 min·May 08, 2026
  9. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
    Explaining and Preventing Alignment Collapse in Iterative RLHF
    Gauthier, Bach, Jordan · Inria·22 min·May 07, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.