Latest

• MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
• SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
• LITA: Language Instructed Temporal-localization Assistant
• DoRA: Weight-decomposed Low-rank Adaptation
• FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
• Flextron: Many-in-One Flexible Large Language Model
• RegionGPT: Towards Region Understanding Vision Language Model
• VILA: On pretraining for vision language models
• FasterViT: Fast Vision Transformers with Hierarchical Attention
• Global Context Vision Transformers
• Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
• Global Vision Transformer Pruning with Hessian-Aware Saliency
• Heterogeneous Continual Learning
• Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models
• Structural Pruning via Latency-Saliency Knapsack
• LANA: Latency Aware Network Acceleration
• Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks
• A-ViT: Adaptive Tokens for Efficient Vision Transformer
• GradViT: Gradient Inversion of Vision Transformers
• When to Prune? A Policy towards Early Structural Pruning
• Do Gradient Inversion Attacks Make Federated Learning Unsafe?
• NViT: Vision Transformer Compression and Parameter Redistribution
• Optimal Quantization Using Scaled Codebook
• See through Gradients: Image Batch Recovery via GradInversion