MAC-AutoML / QuoTALinks
This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension"
☆70Updated last month
Alternatives and similar repositories for QuoTA
Users that are interested in QuoTA are comparing it to the libraries listed below
Sorting:
- MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models☆35Updated last month
- Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation☆30Updated 2 months ago
- Repo for paper "T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs"☆49Updated 2 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆64Updated last month
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆105Updated 2 months ago
- A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.☆62Updated 2 months ago
- The Next Step Forward in Multimodal LLM Alignment☆160Updated last month
- ☆84Updated 2 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆48Updated this week
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆34Updated 2 months ago
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning☆72Updated 2 weeks ago
- Collections of Papers and Projects for Multimodal Reasoning.☆105Updated last month
- ☆46Updated last month
- p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆35Updated 4 months ago
- Code release for VTW (AAAI 2025) Oral☆43Updated 4 months ago
- Official Repository: A Comprehensive Benchmark for Logical Reasoning in MLLMs☆30Updated this week
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆40Updated 6 months ago
- Envolving Temporal Reasoning Capability into LMMs via Temporal Consistent Reward☆35Updated 2 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆112Updated 2 weeks ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆61Updated 4 months ago
- R1-like Video-LLM for Temporal Grounding☆92Updated last week
- [ICLR 2025] TRACE: Temporal Grounding Video LLM via Casual Event Modeling☆97Updated 4 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆76Updated 5 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆82Updated 5 months ago
- The official repository for ACL2025 paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".☆46Updated 3 weeks ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆172Updated last week
- [Blog 1] Recording a bug of grpo_trainer in some R1 projects☆19Updated 3 months ago
- Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning☆44Updated 2 weeks ago
- Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆25Updated 2 weeks ago
- [LLaVA-Video-R1]✨First Adaptation of R1 to LLaVA-Video (2025-03-18)☆27Updated 3 weeks ago