相关论文: RePOPE: Impact of Annotation Errors on the POPE Be…

Benchmarks for the evaluation of model performance play an important role in machine learning. However, there is no established way to describe and create new benchmarks. What is more, the most common benchmarks use performance measures…

Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…

Studies of the contextual and linguistic factors that constrain discourse phenomena such as reference are coming to depend increasingly on annotated language corpora. In preparing the corpora, it is important to evaluate the reliability of…

The Learning With Disagreements (LeWiDi) 2025 shared task aims to model annotator disagreement through soft label distribution prediction and perspectivist evaluation, which focuses on modeling individual annotators. We adapt DisCo…

Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are wrongly annotated as safe ones, the model fine-tuned on…

Recent advances in visual anomaly detection research have seen AUROC and AUPRO scores on public benchmark datasets such as MVTec and VisA converge towards perfect recall, giving the impression that these benchmarks are near-solved. However,…

Current foundation models have shown impressive performance across various tasks. However, several studies have revealed that these models are not effective for everyone due to the imbalanced geographical and economic representation of the…

Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive activation. We investigate the source of these instabilities via…

Learning with noisy labels is a vital topic for practical deep learning as models should be robust to noisy open-world datasets in the wild. The state-of-the-art noisy label learning approach JoCoR fails when faced with a large ratio of…

In the last year alone, a surge of new benchmarks to measure compositional understanding of vision-language models have permeated the machine learning ecosystem. Given an image, these benchmarks probe a model's ability to identify its…

Searching troves of videos with textual descriptions is a core multimodal retrieval task. Owing to the lack of a purpose-built dataset for text-to-video retrieval, video captioning datasets have been re-purposed to evaluate models by (1)…

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications,…

We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We…

Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully-understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have…

The reliability of supervised machine learning systems depends on the accuracy and availability of ground truth labels. However, the process of human annotation, being prone to error, introduces the potential for noisy labels, which can…

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…

Off-policy evaluation (OPE) estimates the value of a contextual bandit policy prior to deployment. As such, OPE plays a critical role in ensuring safety in high-stakes domains such as healthcare. However, standard OPE approaches are limited…

AffectNet is one of the most popular resources for facial expression recognition (FER) on relatively unconstrained in-the-wild images. Given that images were annotated by only one annotator with limited consistency checks on the data,…

NLP datasets may still contain annotation errors, even when they are manually annotated. Researchers have attempted to develop methods to automatically reduce the adverse effect of errors in datasets. However, existing methods are…

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…