Related papers: A3Rank: Augmentation Alignment Analysis for Priori…

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques…

In medical image processing, accurate diagnosis is of paramount importance. Leveraging machine learning techniques, particularly top-rank learning, shows significant promise by focusing on the most crucial instances. However, challenges…

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…

Compared to other language tasks, applying pre-trained language models (PLMs) for search ranking often requires more nuances and training signals. In this paper, we identify and study the two mismatches between pre-training and ranking…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

Recent breakthroughs in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values. However, current alignment metrics typically emphasize the post-hoc…

Class imbalance problems manifest in domains such as financial fraud detection or network intrusion analysis, where the prevalence of one class is much higher than another. Typically, practitioners are more interested in predicting the…

Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget…

Widespread applications of deep learning have led to a plethora of pre-trained neural network models for common tasks. Such models are often adapted from other models via transfer learning. The models may have varying training sets,…

Deep learning (DL) has achieved unprecedented success in a variety of tasks. However, DL systems are notoriously difficult to test and debug due to the lack of explainability of DL models and the huge test input space to cover. Generally…

With the increasing deployment of machine learning models in many socially sensitive tasks, there is a growing demand for reliable and trustworthy predictions. One way to accomplish these requirements is to allow a model to abstain from…

Given a deep neural network image classification model that we treat as a black box, and an unlabeled evaluation dataset, we develop an efficient strategy by which the classifier can be evaluated. Randomly sampling and labeling instances…

Classification and clustering algorithms have been proved to be successful individually in different contexts. Both of them have their own advantages and limitations. For instance, although classification algorithms are more powerful than…

Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given…

We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in research papers. For each concern, E3 reports its nature, its location, its bearing on the…

Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…

Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve…

Diffusion language models enable any-order generation and bidirectional conditioning, offering appealing flexibility for tasks such as infilling, rewriting, and self-correction. However, their formulation-predicting one part of a sequence…

Listwise reranking with large language models (LLMs) enhances top-ranked results in retrieval-based applications. Due to the limit in context size and high inference cost of long context, reranking is typically performed over a fixed size…

Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of…