相关论文: SwordBench: Evaluating Orthogonality of Steering I…

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this…

High-performing vision language models still produce incorrect answers, yet their failure modes are often difficult to explain. To make model internals more accessible and enable systematic debugging, we introduce VisualScratchpad, an…

We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. First, it evaluates analytical understanding rather than…

AI models make mistakes when recognizing images-whether in-domain, out-of-domain, or adversarial. Predicting these errors is critical for improving system reliability, reducing costly mistakes, and enabling proactive corrections in…

We study a sequential contextual decision-making problem in which certain covariates are missing but can be imputed using a pre-trained AI model. From a theoretical perspective, we analyze how the presence of such a model influences the…

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning…

The ability to locate an object in an image according to natural language instructions is crucial for many real-world applications. In this work we propose LocateBench, a high-quality benchmark dedicated to evaluating this ability. We…

The ability to steer AI behavior is crucial to preventing its long term dangerous and catastrophic potential. Representation Engineering (RepE) has emerged as a novel, powerful method to steer internal model behaviors, such as "honesty", at…

Mitigating the discrimination of machine learning models has gained increasing attention in medical image analysis. However, rare works focus on fair treatments for patients with multiple sensitive demographic ones, which is a crucial yet…

Image editing models are advancing rapidly, yet comprehensive evaluation remains a significant challenge. Existing image editing benchmarks generally suffer from limited task scopes, insufficient evaluation dimensions, and heavy reliance on…

Object orientation understanding represents a fundamental challenge in visual perception critical for applications like robotic manipulation and augmented reality. Current vision-language benchmarks fail to isolate this capability, often…

Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and…

The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in the development of deep learning. Although new deep learning…

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Over the past years, computer vision community has contributed to enormous progress in semantic image segmentation, a per-pixel classification task, crucial for dense scene understanding and rapidly becoming vital in lots of real-world…

Semantic understanding of 3D point clouds is important for various robotics applications. Given that point-wise semantic annotation is expensive, in this paper, we address the challenge of learning models with extremely sparse labels. The…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Humans judge perceptual similarity according to diverse visual attributes, including scene layout, subject location, and camera pose. Existing vision models understand a wide range of semantic abstractions but improperly weigh these…

Artificial neural networks have advanced the frontiers of reversible steganography. The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data. Residual modulation is recognised as…

We introduce the Stress-Guided Lightweight Design Benchmark (SGLDBench), a comprehensive benchmark suite for applying and evaluating material layout strategies to generate stiff, lightweight designs in 3D domains. SGLDBench provides a…