sangminwoo / awesome-token-redundancy-reductionLinks
π Awesome papers on token redundancy reduction
β11Updated 9 months ago
Alternatives and similar repositories for awesome-token-redundancy-reduction
Users that are interested in awesome-token-redundancy-reduction are comparing it to the libraries listed below
Sorting:
- β62Updated 7 months ago
- Code release for VTW (AAAI 2025 Oral)β65Updated last month
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.β77Updated 2 months ago
- [EMNLP 2025 main π₯] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"β96Updated 2 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Modelsβ159Updated 3 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Modelβ36Updated 11 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductionβ135Updated 9 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.β100Updated 5 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Modelsβ94Updated last month
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"β48Updated 2 months ago
- Latest open-source "Thinking with images" (O3/O4-mini) papers, covering training-free, SFT-based, and RL-enhanced methods for "fine-grainβ¦β107Updated 4 months ago
- [EMNLP 2024 Findingsπ₯] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inβ¦β104Updated last year
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationβ99Updated last year
- [TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Modelsβ145Updated 2 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "Spβ¦β213Updated this week
- Mitigating Shortcuts in Visual Reasoning with Reinforcement Learningβ41Updated 5 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"β67Updated last month
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Largβ¦β35Updated 3 weeks ago
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillationβ214Updated 8 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigationβ127Updated 3 months ago
- π Collection of token-level model compression resources.β187Updated 3 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelsβ77Updated last year
- R1-Vision: Let's first take a look at the imageβ48Updated 10 months ago
- [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMsβ157Updated last year
- β107Updated 11 months ago
- [ICLR2025] Ξ³ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Modelsβ41Updated 2 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Contβ¦β67Updated 3 months ago
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiencyβ135Updated 4 months ago
- β¨β¨[AAAI 2026] This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Viβ¦β73Updated 8 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visioβ¦β43Updated 8 months ago