Skip to content

@princeton-pli Princeton Language and Intelligence (PLI)

Change the repository type filter

All

    Repositories list

    20 repositories

    • hal-harness

      Public
      Python
      •47•226•22•2•Updated Feb 18, 2026Feb 18, 2026

    • STAT

      Public
      Skill-Targeted Adaptive Training
      synthetic-datadata-selectionlarge-language-modelssupervised-finetuning
      Python
      •2•15•1•0•Updated Jan 27, 2026Jan 27, 2026

    • exrm-vs-imrm

      Public
      [ICLR 2026] Why is Your Language Model a Poor Implicit Reward Model?
      Python
      •
      MIT License
      •0•3•0•0•Updated Jan 26, 2026Jan 26, 2026

    • QRHead

      Public
      QRHead: Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
      Python
      •
      MIT License
      •1•34•3•0•Updated Jan 20, 2026Jan 20, 2026

    • compute_tools

      Public
      Tools for analyzing cluster usage, etc.
      Python
      •0•0•0•0•Updated Dec 31, 2025Dec 31, 2025

    • retaining-by-doing

      Public
      Python
      •2•35•3•0•Updated Dec 25, 2025Dec 25, 2025

    • RL-skill-comp

      Public
      Codebase for the paper "How Does RL Post-training Induce Skill Composition? A Case Study Using Countdown"
      Python
      •0•4•0•0•Updated Dec 2, 2025Dec 2, 2025

    • RLMT

      Public
      [R]einforcement [L]earning from [M]odel-rewarded [T]hinking - code for the paper "Language Models That Think, Chat Better"
      Python
      •
      MIT License
      •6•124•0•0•Updated Oct 27, 2025Oct 27, 2025

    • impossibility-unlearning

      Public
      Python
      •
      MIT License
      •0•3•0•0•Updated Oct 23, 2025Oct 23, 2025

    • LongProc

      Public
      LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation
      HTML
      •
      Apache License 2.0
      •1•33•0•1•Updated Oct 11, 2025Oct 11, 2025

    • what-makes-good-rm

      Public
      [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective
      Python
      •
      MIT License
      •3•42•0•0•Updated Sep 18, 2025Sep 18, 2025

    • compute_examples

      Public
      Examples for distributed model training on the cluster.
      Python
      •0•3•0•0•Updated Sep 17, 2025Sep 17, 2025

    • PruLong

      Public
      Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"
      Python
      •
      MIT License
      •4•48•1•0•Updated Jul 29, 2025Jul 29, 2025

    • AdaptMI

      Public
      [COLM 2025] Adaptive Skill-based In-context Math Instruction for Small Language Models
      test-time-adaptationin-context-learninglarge-language-modelsinference-time-scaling
      Python
      •
      Other
      •4•8•0•0•Updated Jul 10, 2025Jul 10, 2025

    • MeCo

      Public
      Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"
      Python
      •2•49•5•0•Updated Jun 30, 2025Jun 30, 2025

    • MixiT

      Public
      Disentangling the transformer.
      Python
      •0•7•0•0•Updated Jun 9, 2025Jun 9, 2025

    • VLM_S2H

      Public
      Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
      Python
      •
      MIT License
      •0•15•0•0•Updated Jun 3, 2025Jun 3, 2025

    • Context-Enhanced-Learning

      Public
      Code for Preprint "On the Power of Context-Enhanced Learning"
      Jupyter Notebook
      •
      MIT License
      •0•3•0•0•Updated Mar 7, 2025Mar 7, 2025

    • Instruct-SkillMix

      Public
      Python
      •0•8•0•0•Updated Feb 11, 2025Feb 11, 2025

    • agentslack

      Public
      Python
      •
      MIT License
      •0•3•5•0•Updated Feb 4, 2025Feb 4, 2025