Related papers: ZClip: Adaptive Spike Mitigation for LLM Pre-Train…
Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…
In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…
Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first…
Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying…
Zero-shot anomaly detection (ZSAD) targets the identification of anomalies within images from arbitrary novel categories. This study introduces AdaCLIP for the ZSAD task, leveraging a pre-trained vision-language model (VLM), CLIP. AdaCLIP…
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number of parameters and complex transformer-based architectures result in significant resource…
Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…
Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…
Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT)…
Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…
Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been…
Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…
Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…
Accurately estimating the normalization term (also known as the partition function) in the contrastive loss is a central challenge for training Contrastive Language-Image Pre-training (CLIP) models. Conventional methods rely on large…
We introduce a new supervised learning algorithm based to train spiking neural networks for classification. The algorithm overcomes a limitation of existing multi-spike learning methods: it solves the problem of interference between…
Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to update at inference time without labeled data, typically via…
Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed augmentations, which…
Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…
LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…
In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its…