SILC: Improving Vision Language Pretraining with Self-Distillation
Paper
•
2310.13355
•
Published
•
8
Vision-Language
-
-
Woodpecker: Hallucination Correction for Multimodal Large Language Models
Paper • 2310.16045 • Published • 14 -
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Paper • 2201.12086 • Published • 3 -
ImageNetVC: Zero-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories
Paper • 2305.15028 • Published • 1 -
TiC-CLIP: Continual Training of CLIP Models
Paper • 2310.16226 • Published • 8 -
Segment Anything
Paper • 2304.02643 • Published • 3 -
MM-VID: Advancing Video Understanding with GPT-4V(ision)
Paper • 2310.19773 • Published • 19 -
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
Paper • 2310.19909 • Published • 20 -
Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?
Paper • 2311.00047 • Published • 8
OpenVLA: An Open-Source Vision-Language-Action Model
Paper • 2406.09246 • Published • 36Note OpenVLA作為一個開源的視覺-語言-行動模型，展示了在多任務機器人操控中的強大性能及泛化能力，並通過高效的微調和量化技術，使其能在消費級硬件上運行。這為未來的機器人研究和應用提供了一個強大的基礎。
-
TroL: Traversal of Layers for Large Language and Vision Models
Paper • 2406.12246 • Published • 34 -
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 58 -
Long Context Transfer from Language to Vision
Paper • 2406.16852 • Published • 32 -
Video-Infinity: Distributed Long Video Generation
Paper • 2406.16260 • Published • 28 -
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
Paper • 2406.16338 • Published • 25 -
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
Paper • 2408.04840 • Published • 32