We have 5 of 70 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert LoRA distributes learning across experts, updates to a dense low-rank expert can still affect many output features. We introduce Monarch-MoE, which replaces the dense f...
Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragi...
P predictive Prompting (PrePrompt) is proposed, a novel CIL framework that circumvents correlation-based limitations by leveraging the inherent classification ability of pre-trained models to predict task-specific prompts and decomposes CIL into a two-stage prediction process: task-specific prompt prediction followed b...
Prompt-based learning has emerged as a promising paradigm for Class Incremental Learning (CIL), enabling pre-trained models to adapt efficiently to open-world scenarios. Existing methods often employ correlation-based strategies, where an image's feature serves as a query to retrieve the most relevant key prompts, with...
RSIAT significantly outperforms state-of-the-art methods in both performance and parameter efficiency, achieving superior stability–plasticity trade-offs with minimal trainable parameters.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
