Related papers: One is Plenty: A Polymorphic Feature Interpreter f…
When planning for autonomous driving, it is crucial to consider essential traffic elements such as lanes, intersections, traffic regulations, and dynamic agents. However, they are often overlooked by the traditional end-to-end planning…
Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…
Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off…
Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies in jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement…
Interpretability is central to trustworthy machine learning, yet existing metrics rarely quantify how effectively data support an interpretive representation. We propose Interpretive Efficiency, a normalized, task-aware functional that…
3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, its effectiveness is inherently constrained in…
Cooperative perception enhances the individual perception capabilities of autonomous vehicles (AVs) by providing a comprehensive view of the environment. However, balancing perception performance and transmission costs remains a significant…
The paper introduces an extension of the proposal according to which conceptual representations in cognitive agents should be intended as heterogeneous proxytypes. The main contribution of this paper is in that it details how to reconcile,…
Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…
Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…
Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come with challenges…
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of…
Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in…
Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better…
Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons…
To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…
Trustworthy AI is mandatory for the broad deployment of autonomous vehicles. Although end-to-end approaches derive control commands directly from raw data, interpreting these decisions remains challenging, especially in complex urban…
We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier) to enable continual intelligence growth through self-supervised…
Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel,…
Autonomous Vehicles (AVs) rely on individual perception systems to navigate safely. However, these systems face significant challenges in adverse weather conditions, complex road geometries, and dense traffic scenarios. Cooperative…