相关论文: PEARL: Input-Agnostic Prompt Enhancement with Nega…

Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. Most of these methods organize these vectors in a pool of key-value pairs and use the input image as query…

3D point cloud semantic segmentation technology has been widely used. However, in real-world scenarios, the environment is evolving. Thus, offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes.…

Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While existing CL methods accomplish this to some extent, they are…

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (data…

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted…

Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring classes, making it prone to catastrophic forgetting and high false-positive rates (FPR). Extending CLIP to MLCIL is…

Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the…

Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…

Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output…

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models must continuously adapt to new data and emerging object categories, but retraining…

Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced…

Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without…

Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However,…

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods utilize scalar reward…

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…

Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge. It is common to see previous…

We present PEARL (Peer-Enhanced Adaptive Radio via On-Device LLM), a framework for cooperative cross-layer optimization in device-to-device (D2D) communication. Building on our previous work on single-device on-device LLMs, PEARL extends…