"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang.
☆35May 7, 2024Updated 2 years ago
Alternatives and similar repositories for Ms-PoE
Users that are interested in Ms-PoE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Jun 25, 2025Updated last year
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- ☆26Dec 12, 2025Updated 8 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆390Jan 4, 2024Updated 2 years ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆263Sep 12, 2025Updated 11 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆242Aug 2, 2024Updated 2 years ago
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆62Feb 13, 2024Updated 2 years ago
- ☆20Jan 16, 2024Updated 2 years ago
- ☆14Jun 13, 2025Updated last year
- Comparing retrieval abilities from GPT4-Turbo and a RAG system on a toy example for various context lengths☆35Dec 1, 2023Updated 2 years ago
- The repository for papaer "Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs"☆14Dec 16, 2024Updated last year
- Applies ROME and MEMIT on Mamba-S4 models☆16Apr 5, 2024Updated 2 years ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆116Oct 11, 2025Updated 10 months ago
- Official code for the paper "Attention as a Hypernetwork"☆59Feb 24, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Linux /proc data in a consistent, parsed format.☆10Mar 28, 2016Updated 10 years ago
- Code for paper: Long cOntext aliGnment via efficient preference Optimization☆26Oct 10, 2025Updated 10 months ago
- LongMIT: Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets☆43Sep 30, 2024Updated last year
- Python Implementation for Rethinking RAG based Decoding☆17Sep 10, 2025Updated 11 months ago
- Official implementation of the paper "Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories" (CVPR`25)☆15Apr 27, 2026Updated 3 months ago
- Fine-tune of Florence-2 for shot categorization.☆26Mar 6, 2025Updated last year
- agent skill as memory layer☆21Jan 30, 2026Updated 6 months ago
- 한국어 자연어 처리 모델 미세조정☆17Jan 26, 2021Updated 5 years ago
- ☆14May 9, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Simplified packaging for pybind11-based C++ extensions☆13Jun 3, 2022Updated 4 years ago
- Tinkering RL☆28Updated this week
- 北京交通大学本科毕业设计（论文）LaTeX 模板（非官方）｜Bachelor Thesis LaTeX Template for Beijing Jiaotong University (unofficial)☆13Jun 20, 2022Updated 4 years ago
- VQVAE for video prediction☆31Apr 22, 2022Updated 4 years ago
- KV cache compression for high-throughput LLM inference☆159Feb 5, 2025Updated last year
- Crawl & Visualize NeurIPS 2022 Data from OpenReview☆14Nov 8, 2022Updated 3 years ago
- IAI MovieBot☆10May 7, 2024Updated 2 years ago
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆253Jun 1, 2026Updated 2 months ago
- The HELMET Benchmark☆223Apr 17, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- DySCO: Dynamic Attention-Scaling Decoding for Long-Context LMs☆17May 30, 2026Updated 2 months ago
- Official pytorch code for "APP: Anytime Progressive Pruning" (DyNN @ ICML, 2022; CLL @ ACML, 2022, SNN @ ICML, 2022 and SlowDNN 2023)☆16Nov 22, 2022Updated 3 years ago
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- Code implementation for paper "On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals".☆17Dec 15, 2021Updated 4 years ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated last year
- ☆16Mar 3, 2024Updated 2 years ago
- ☆16Apr 4, 2026Updated 4 months ago