Related papers: The Alignment Bottleneck in Decomposition-Based Cl…

Reliable data is a cornerstone of modern organizational systems. A notable data integrity challenge stems from label bias, which refers to systematic errors in a label, a covariate that is central to a quantitative analysis, such that its…

We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability. The generation of DecompSR allows users to…

In the context of fact-checking, claims are often repeated across various platforms and in different languages, which can benefit from a process that reduces this redundancy. While retrieving previously fact-checked claims has been…

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where test samples or their close variants leak into training…

Neural speech synthesis techniques have enabled highly realistic speech deepfakes, posing major security risks. Speech deepfake detection is challenging due to distribution shifts across spoofing methods and variability in speakers,…

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Modern science increasingly relies on ever-growing observational datasets and automated inference pipelines, under the implicit belief that accumulating more data makes scientific conclusions more reliable. Here we show that this belief can…

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Data association in SLAM is fundamentally challenging, and handling ambiguity well is crucial to achieve robust operation in real-world environments. When ambiguous measurements arise, conservatism often mandates that the measurement is…

Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this…

Misinformation can be countered with fact-checking, but the process is costly and slow. Identifying checkworthy claims is the first step, where automation can help scale fact-checkers' efforts. However, detection methods struggle with…

Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the provided evidence supports the target claim. In practice, this often fails because supervision…

Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible outputs. While prior work has developed benchmarks for…

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances…

Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor-…

We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in generating informed heatmaps while training, presumably due…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This…