• Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
• AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks
• MyVLM: Personalizing VLMs for User-Specific Queries
• InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding
• VidLA: Video-Language Alignment at Scale
• SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
• AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models
• DreamReward: Text-to-3D Generation with Human Preference
• Mora: Enabling Generalist Video Generation via A Multi-Agent Framework
• LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
• Evolutionary Optimization of Model Merging Recipes
• SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model
• When Do We Not Need Larger Vision Models?
• HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
• ZigMa: Zigzag Mamba Diffusion Model
• DepthFM: Fast Monocular Depth Estimation with Flow Matching
• mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
• AnimateDiff-Lightning: Cross-Model Diffusion Distillation
• Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers