Skip to content

@VILA-Lab VILA-Lab: Vision and Language Acceleration Lab

Change the repository type filter

All

    Repositories list

    17 repositories

    • Awesome-DLMs

      Public
      The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".
      34•749•1•0•Updated Feb 3, 2026Feb 3, 2026

    • M-Attack

      Public
      [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Model…
      attackadversarial-attacklvlmsmllms
      Python
      •
      MIT License
      •6•86•0•0•Updated Feb 3, 2026Feb 3, 2026

    • OD3

      Public
      [ICLR 2026] Optimization-free Dataset Distillation for Object Detection. Paper at: https://arxiv.org/abs/2506.01942
      object-detectiondataset-distillation
      Python
      •
      MIT License
      •1•22•1•0•Updated Jan 26, 2026Jan 26, 2026

    • Elastic-Cache

      Public
      [ICLR 2026 🔥] Official pytorch implementation for "Attention Is All You Need for KV Cache in Diffusion LLMs"
      Python
      •
      Apache License 2.0
      •3•36•0•0•Updated Jan 23, 2026Jan 23, 2026

    • elastic-cache-webpage

      Public
      HTML
      •0•0•0•0•Updated Jan 7, 2026Jan 7, 2026

    • PTTS

      Public
      P-TTS: inference-time reasoning data augmentation that scales prompt-space with principled instructions, matching/exceeding larger-data baselines.
      Python
      •
      Apache License 2.0
      •1•6•0•0•Updated Oct 17, 2025Oct 17, 2025

    • M-Attack-Website

      Public
      M-Attack-Website
      JavaScript
      •0•0•0•0•Updated Oct 15, 2025Oct 15, 2025

    • GBLM-Pruner

      Public
      Are gradient information useful for pruning of LLMs?
      Python
      •
      MIT License
      •12•47•1•0•Updated Aug 23, 2025Aug 23, 2025

    • DELT

      Public
      (CVPR 2025) Official implementation to DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation which outperforms SOTA top 1-acc by +1.3% and…
      image-synthesisdataset-distillationdataset-condensation
      Python
      •0•26•1•0•Updated Aug 23, 2025Aug 23, 2025

    • DRAG

      Public
      (ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
      nlpdistillationragllm
      Python
      •2•33•1•0•Updated Aug 23, 2025Aug 23, 2025

    • Mobile_MMLU

      Public
      HTML
      •0•0•0•0•Updated Mar 27, 2025Mar 27, 2025

    • Mobile-MMLU

      Public
      Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark. Paper at: https://arxiv.org/abs/2503.20786
      benchmarkmobileaillm
      Python
      •
      MIT License
      •1•11•0•0•Updated Mar 27, 2025Mar 27, 2025

    • SRe2L

      Public
      (NeurIPS 2023 spotlight) Large-scale Dataset Distillation/Condensation, 50 IPC (Images Per Class) achieves the highest 60.8% on original ImageNet-1K val set.
      image-synthesisdataset-distillationdataset-condensation
      Python
      •23•136•1•0•Updated Nov 15, 2024Nov 15, 2024

    • Open-LLM-Leaderboard

      Public
      Open-LLM-Leaderboard: Open-Style Question Evaluation. Paper at https://arxiv.org/abs/2406.07545
      leaderboardllmsopen-ended-question-markerllm-evaluationopen-ended-evaluationllm-leaderboard
      Python
      •
      Creative Commons Attribution 4.0 International
      •7•50•1•0•Updated Jun 27, 2024Jun 27, 2024

    • Open-LLM-Leaderboard-Website

      Public
      HTML
      •0•1•0•0•Updated Jun 15, 2024Jun 15, 2024

    • ATLAS

      Public
      A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171
      Python
      •
      Apache License 2.0
      •102•980•6•1•Updated May 28, 2024May 28, 2024

    • i-mae

      Public
      i-mae Pytorch Repo
      Python
      •3•20•1•0•Updated Apr 6, 2024Apr 6, 2024