Related papers: TAPS : Frustratingly Simple Test Time Active Learn…

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to…

While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…

Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency, limiting them to low-frequency batch-and-execute paradigm. This frequency mismatch creates an execution blind spot,…

Many real-world machine learning applications involve several learning tasks which are inter-related. For example, in healthcare domain, we need to learn a predictive model of a certain disease for many hospitals. The models for each…

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively…

Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…

Encountering shifted data at test time is a ubiquitous challenge when deploying predictive models. Test-time adaptation (TTA) methods address this issue by continuously adapting a deployed model using only unlabeled test data. While TTA can…

With the rise of large language models, neural text summarization has advanced significantly in recent years. However, even state-of-the-art models continue to rely heavily on high-quality human-annotated data for training and evaluation.…

We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data. We…

Fault detection is essential in complex industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. With the growing availability of condition monitoring data, data-driven…

Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use…

One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a…

Multi-Task Learning (MTL) is a powerful technique that has gained popularity due to its performance improvement over traditional Single-Task Learning (STL). However, MTL is often challenging because there is an exponential number of…

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning. However, prompting-based methods often remain shallow and unstable, while fine-tuned medical LLMs…

Online Continual Learning (OCL) studies learning over a continuous data stream without observing any single example more than once, a setting that is closer to the experience of humans and systems that must learn "on-the-wild". Yet,…

A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the…

Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained…