MCG-NJU / p-MoD
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
☆32Updated 2 months ago
Alternatives and similar repositories for p-MoD:
Users that are interested in p-MoD are comparing it to the libraries listed below
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆80Updated 2 weeks ago
- ☆67Updated 4 months ago
- The official repository for paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".☆34Updated last month
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆27Updated this week
- [CVPR2025] Number it: Temporal Grounding Videos like Flipping Manga☆65Updated 2 weeks ago
- [CVPR 2025] RAP: Retrieval-Augmented Personalization☆28Updated this week
- Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models☆91Updated this week
- [CVPR'25] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆61Updated 3 weeks ago
- ☆50Updated this week
- Official implement of MIA-DPO☆54Updated 2 months ago
- [Neurips 24' D&B] Official Dataloader and Evaluation Scripts for LongVideoBench.☆90Updated 7 months ago
- [NeurIPS 2024] Visual Perception by Large Language Model’s Weights☆41Updated 5 months ago
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆79Updated 2 weeks ago
- A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability☆90Updated 3 months ago
- [ICLR 2025] TRACE: Temporal Grounding Video LLM via Casual Event Modeling☆75Updated 2 months ago
- ☆40Updated 2 months ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆63Updated 6 months ago
- Official repository of DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models☆83Updated 6 months ago
- Official repository of "Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning"☆28Updated last month
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆152Updated 2 months ago
- Official implementation of HawkEye: Training Video-Text LLMs for Grounding Text in Videos☆38Updated 10 months ago
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models☆48Updated 8 months ago
- [ICME 2024 Oral] DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding☆20Updated 3 weeks ago