CR400AF-A / SparseMMLinks
[ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
☆74Updated 3 months ago
Alternatives and similar repositories for SparseMM
Users that are interested in SparseMM are comparing it to the libraries listed below
Sorting:
- [ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache☆42Updated last year
- Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Models☆96Updated last year
- 🚀 [NeurIPS24] Make Vision Matter in Visual-Question-Answering (VQA)! Introducing NaturalBench, a vision-centric VQA benchmark (NeurIPS'2…☆87Updated 3 months ago
- [NAACL 2025 Oral] 🎉 From redundancy to relevance: Enhancing explainability in multimodal large language models☆119Updated 7 months ago
- (ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator☆114Updated 6 months ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆180Updated 11 months ago
- [ICML 2025] Official repository for paper "Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation"☆177Updated last week
- A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI☆171Updated last month
- (ICCV 2025) Enhance CLIP and MLLM's fine-grained visual representations with generative models.☆72Updated 3 months ago
- ✨✨Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy☆293Updated 4 months ago
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆70Updated 3 months ago
- Multi-granularity Correspondence Learning from Long-term Noisy Videos [ICLR 2024, Oral]☆117Updated last year
- A Gaussian dense reward framework for GUI grounding training☆228Updated last month
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆42Updated 9 months ago
- Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"☆190Updated last month
- u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model