Related papers: IOTA: Corrective Knowledge-Guided Prompt Learning …

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained…

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning…

In August 2024, Bittensor's Subnet 9 (SN9) demonstrated that a distributed network of incentivized, permissionless actors could each pretrain large language models (LLMs) ranging from 700 million to 14 billion parameters, while surpassing…

Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The fundamental roadblock faced by deep learning methods is that…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely…

Recent work in mechanistic interpretability has shown that behaviors in language models can be successfully reverse-engineered through circuit analysis. A common criticism, however, is that each circuit is task-specific, and thus such…

Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighting and augmented inverse probability weighting are effective under favorable model…

Pretrained Large Language Models (LLM) such as ChatGPT, Claude, etc. have demonstrated strong capabilities in various fields of natural language generation. However, there are still many problems when using LLM in specialized…

There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained…

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks. However, prompt tuning requires a large training…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field of Continual Learning. Specifically, these approaches propose…

Prompt-tuning has emerged as a promising method for adapting pre-trained models to downstream tasks or aligning with human preferences. Prompt learning is widely used in NLP but has limited applicability to RL due to the complex physical…

Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…

Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by…

Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing…

Many modern software systems are highly configurable, allowing the user to tune them for performance and more. Current performance modeling approaches aim at finding performance-optimal configurations by building performance models in a…

Continual Test-Time Adaptation (CTTA) seeks to adapt source pre-trained models to continually changing, unseen target domains. While existing CTTA methods assume structured domain changes with uniform durations, real-world environments…