Related papers: TADS: Task-Aware Data Selection for Multi-Task Mul…

Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…

Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving…

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring,…

We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance…

Multimodal visual language models are gaining prominence in open-world applications, driven by advancements in model architectures, training techniques, and high-quality data. However, their performance is often limited by insufficient…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…

With the rising number of machine learning competitions, the world has witnessed an exciting race for the best algorithms. However, the involved data selection process may fundamentally suffer from evidence ambiguity and concept drift…

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

Resource sharing between multiple workloads has become a prominent practice among cloud service providers, motivated by demand for improved resource utilization and reduced cost of ownership. Effective resource sharing, however, remains an…

In this paper, we introduce a discrete variant of the meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for meta-learning in…

Time series anomaly detection plays a critical role in many dynamic systems. Despite its importance, previous approaches have primarily relied on unimodal numerical data, overlooking the importance of complementary information from other…

Robust multimodal systems must remain effective when some modalities are noisy, degraded, or unreliable. Existing multimodal fusion methods often learn modality selection jointly with representation learning, making it difficult to…

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Unsupervised Domain Adaptation (UDA) is essential for adapting machine learning models to new, unlabeled environments where data distribution shifts can degrade performance. Existing UDA algorithms are designed for single-label tasks and…

Multimodal large language models (MLLMs) have shown strong potential for medical image reasoning, yet fairness across demographic groups remains a major concern. Existing debiasing methods often rely on large labeled datasets or…

Existing collision prediction methods often fail to distinguish between ego-vehicle threats and random accidents not involving the ego vehicle, leading to excessive false alerts in real-world deployment. We present BADAS, a family of…

Test-Time Optimization enables models to adapt to new data during inference by updating parameters on-the-fly. Recent advances in Vision-Language Models (VLMs) have explored learning prompts at test time to improve performance in downstream…

Supervised machine learning often encounters concept drift, where the data distribution changes over time, degrading model performance. Existing drift detection methods focus on identifying these shifts but often overlook the challenge of…

Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable translation systems. This paper presents a data selection…

With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effectively solved at an additional labeling cost by targeted data…