Related papers: A Ranking-based, Balanced Loss Function Unifying C…

Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work…

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output. Such cases occur in the aggregate loss, which combines individual losses of a learning model over each training sample, and in…

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Activation patching is a standard method in mechanistic interpretability for localizing the components of a model responsible for specific behaviors, but it is computationally expensive to apply at scale. Attribution patching offers a…

Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent…

Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data. However, the network decisions are often…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this…

Pairwise Ranking Prompting (PRP) elicits pairwise preference judgments from an LLM, which are then aggregated into a ranking, usually via classical sorting algorithms. However, judgments are noisy, order-sensitive, and sometimes…

In this paper we propose a new family of algorithms, ATENT, for training adversarially robust deep neural networks. We formulate a new loss function that is equipped with an additional entropic regularization. Our loss function considers…

Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern…

The success of Large Language Models (LLMs) has motivated a shift toward generative approaches to retrieval and ranking, aiming to supersede classical Dual Encoders (DEs) and Cross Encoders (CEs). A prominent paradigm is pointwise…

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

The Probability Ranking Principle (PRP) has been considered as the foundational standard in the design of information retrieval (IR) systems. The principle requires an IR module's returned list of results to be ranked with respect to the…

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…

Active learning (AL) has shown promise for being a particularly data-efficient machine learning approach. Yet, its performance depends on the application and it is not clear when AL practitioners can expect computational savings. Here, we…

Objects in aerial images are typically embedded in complex backgrounds and exhibit arbitrary orientations. When employing oriented bounding boxes (OBB) to represent arbitrary oriented objects, the periodicity of angles could lead to…

We consider the problem of active coarse ranking, where the goal is to sort items according to their means into clusters of pre-specified sizes, by adaptively sampling from their reward distributions. This setting is useful in many social…

Subspace segmentation assumes that data comes from the union of different subspaces and the purpose of segmentation is to partition the data into the corresponding subspace. Low-rank representation (LRR) is a classic spectral-type method…