wujx2001 / QwTLinks
Official PyTorch implementation of QwT—“Quantization without Tears” (CVPR 2025): fast, accurate, and hassle-free post-training network quantization with lightweight linear compensation layers.
☆27Updated 2 months ago
Alternatives and similar repositories for QwT
Users that are interested in QwT are comparing it to the libraries listed below
Sorting:
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆201Updated 6 months ago
- [ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts☆257Updated last year
- This is a project about visual spatial reasoning.☆81Updated last week
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆92Updated 11 months ago
- MoH: Multi-Head Attention as Mixture-of-Head Attention☆299Updated last year
- VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model☆343Updated 7 months ago
- [AAAI-2025] The offical code for SiTo （Similarity-based Token Pruning for Stable Diffusion Models）☆40Updated 6 months ago
- [ICML2025] Official Code of From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection☆24Updated 5 months ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆132Updated last year
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆52Updated 2 months ago
- [ICCV 2025] MM-IFEngine: Towards Multimodal Instruction Following☆114Updated this week
- A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI☆246Updated last week
- [CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation☆385Updated last year
- [CVPR 2025] Official implementation of paper "MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders".☆47Updated 6 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆77Updated 2 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆98Updated 5 months ago
- 📚 Collection of token-level model compression resources.☆185Updated 3 months ago
- A curated list of research based on CLIP.☆290Updated last year
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆66Updated 3 weeks ago
- [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆65Updated 2 months ago
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆95Updated 2 months ago
- Official Repository of ACL 2025 paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference☆144Updated 9 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆133Updated 9 months ago
- [ICML 2025] This is the official PyTorch implementation of "🎵 HarmoniCa: Harmonizing Training and Inference for Better Feature Caching i…☆44Updated 5 months ago
- ☆132Updated 8 months ago
- ☆62Updated 7 months ago
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆42Updated this week
- 🚀 Daily AI Research Digest: Tracking breakthroughs in AI/NLP/CV/Robotics with dynamic updates and paper navigation.☆49Updated this week
- [CVPR 2025] VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification☆44Updated 8 months ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆51Updated 11 months ago