Related papers: Understanding and Mitigating Dataset Corruption in…

Contrastive learning has emerged as a competitive pretraining method for object detection. Despite this progress, there has been minimal investigation into the robustness of contrastively pretrained detectors when faced with domain shifts.…

To address the shortcomings of real-world datasets, robust learning algorithms have been designed to overcome arbitrary and indiscriminate data corruption. However, practical processes of gathering data may lead to patterns of data…

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect.…

Online learning to rank sequentially recommends a small list of items to users from a large candidate set and receives the users' click feedback. In many real-world scenarios, users browse the recommended list in order and click the first…

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach,…

In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…

In recent years, multimodal anomaly detection methods have demonstrated remarkable performance improvements over video-only models. However, real-world multimodal data is often corrupted due to unforeseen environmental distortions. In this…

This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain. In this paper, we present a novel method for fine-tuning neural rankers that can significantly improve…

Numerous modern optimization and machine learning algorithms rely on subgradient information being trustworthy and hence, they may fail to converge when such information is corrupted. In this paper, we consider the setting where subgradient…

Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often correlates with high…

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily. In this paper, we…

Road network and trajectory representation learning are essential for traffic systems since the learned representation can be directly used in various downstream tasks (e.g., traffic speed inference, and travel time estimation). However,…