Related papers: DRoPE: Directional Rotary Position Embedding for E…
Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior…
Addressing the intricate challenge of modeling and re-rendering dynamic scenes, most recent approaches have sought to simplify these complexities using plane-based explicit representations, overcoming the slow training time issues…
Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation policies directly…
We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions of…
Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target…
In recent years, autonomous driving has become a popular field of study. As control at tire grip limit is essential during emergency situations, algorithms developed for racecars are useful for road cars too. This paper examines the use of…
We propose the concept of Action-Related Place (ARPlace) as a powerful and flexible representation of task-related place in the context of mobile manipulation. ARPlace represents robot base locations not as a single position, but rather as…
Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce…
Sequential recommendation (SR), which encodes user activity to predict the next action, has emerged as a widely adopted strategy in developing commercial personalized recommendation systems. A critical component of modern SR models is the…
This study provides a detailed analysis of current advancements in dynamic object tracking (DOT) and trajectory prediction (TP) methodologies, including their applications and challenges. It covers various approaches, such as feature-based,…
Robots must make and break contact with the environment to perform useful tasks, but planning and control through contact remains a formidable challenge. In this work, we achieve real-time contact-implicit model predictive control with a…
Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional…
Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works rely on…
With robots increasingly operating in human-centric environments, ensuring soft and safe physical interactions, whether with humans, surroundings, or other machines, is essential. While compliant hardware can facilitate such interactions,…
Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…
Driving scenario data play an increasingly vital role in the development of intelligent vehicles and autonomous driving. Accurate and efficient scenario data search is critical for both online vehicle decision-making and planning, and…
Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While prior works mainly address RoPE's limitations within attention, this paper uncovers the adverse effects on length…
Collision avoidance is a crucial task in vision-guided autonomous navigation. Solutions based on deep reinforcement learning (DRL) has become increasingly popular. In this work, we proposed several novel agent state and reward function…
Generating safety-critical scenarios in high-fidelity simulations offers a promising and cost-effective approach for efficient testing of autonomous vehicles. Existing methods typically rely on manipulating a single vehicle's trajectory…
Position encoding is the primary mechanism which induces notion of sequential order for input tokens in transformer architectures. Even though this formulation in the original transformer paper has yielded plausible performance for general…