Related papers: The Geometric Canary: Predicting Steerability and …

Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over generation; however, they rely on model uncertainty, meaning an internal estimate of how likely…

Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict…

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Lane detection stands as a crucial perception task in autonomous driving and advanced driver assistance systems. However, existing methods still degrade in complex real scenarios due to two major limitations. First, classification…

Large language models increasingly operate under multiple instructions from heterogeneous sources with different authority levels, including system policies, user requests, tool outputs, and retrieved context. While prior work on…

Reproducibility is imperative for any scientific discovery. More often than not, modern scientific findings rely on statistical analysis of high-dimensional data. At a minimum, reproducibility manifests itself in stability of statistical…

Language and Vision-Language Models (LLMs/VLMs) have revolutionized the field of AI by their ability to generate human-like text and understand images, but ensuring their reliability is crucial. This paper aims to evaluate the ability of…

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical…

Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the…

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (RLVR) pipelines depend on costly supervision, specialized…

PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation artifact but a theorem-level consequence of…

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which…

Many supervised learning problems involve high-dimensional data such as images, text, or graphs. In order to make efficient use of data, it is often useful to leverage certain geometric priors in the problem at hand, such as invariance to…

Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in deep learning promise increased accuracy even for complex scenarios. While the challenge of…

We study the problem of linear feature selection when features are highly correlated. Such settings pose two fundamental challenges. First, how should model similarity be defined? Simply counting features in common can be misleading: two…

Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and safety concerns. To mitigate such risks, representation…

As large language models (LLMs) are increasingly deployed in high-stakes applications, robust uncertainty estimation is essential for ensuring the safe and trustworthy deployment of LLMs. We present the most comprehensive study to date of…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be…