相关论文: KAGE-Bench: Fast Known-Axis Visual Generalization …

We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and uses projection operators and iterative projection algorithms.…

Continuous perception, the ability to integrate visual observations over time in a continuous stream fashion, is essential for robust real-world understanding, yet remains largely untested in current multimodal models. We introduce…

Aligning large language models (LLMs) with human preferences is inherently multi-objective: different users and evaluation criteria impose heterogeneous and often conflicting requirements on model outputs. We propose CAGE (Common-Agency…

Variational autoencoders (VAEs) face a notorious problem wherein the variational posterior often aligns closely with the prior, a phenomenon known as posterior collapse, which hinders the quality of representation learning. To mitigate this…

Estimating the 6D pose of arbitrary unseen objects from a single reference image is critical for robotics operating in the long-tail of real-world instances. However, this setting is notoriously challenging: 3D models are rarely available,…

Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limited in the scope of assessed tasks and offer no overarching…

The autonomous driving (AD) industry is exploring the use of knowledge graphs (KGs) to manage the vast amount of heterogeneous data generated from vehicular sensors. The various types of equipped sensors include video, LIDAR and RADAR.…

Generative adversarial imitation learning (GAIL) has attracted increasing attention in the field of robot learning. It enables robots to learn a policy to achieve a task demonstrated by an expert while simultaneously estimating the reward…

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate…

Successfully solving long-horizon manipulation tasks remains a fundamental challenge. These tasks involve extended action sequences and complex object interactions, presenting a critical gap between high-level symbolic planning and…

Visual model-based reinforcement learning (MBRL) agents can perform well on the training distribution, but often break down once the test environment shifts. In visual MBRL, recognizing that a shift has occurred is often the easier part;…

With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation during execution based on visual observations rather than navigation or…

Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations. Nevertheless, it is time-consuming and expensive to collect and annotate real-world data, especially for V2X systems. In this…

Vision-Language-Action (VLA) models demonstrate promising generalization in robotic manipulation, driven by advances in large-scale vision and language pre-training. This progress can be misleading. Despite the zero-shot perception and…

Fine-grained recognition in everyday life is often not a closed-book classification problem: when encountering unfamiliar objects, humans actively search, compare visual details, and verify evidence before deciding. Existing benchmarks…

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense visual alignment problem. Inspired by the classic Congealing…

Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines,…

This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) has shown promising results for solving this issue. However,…

Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…