10 accepted papers
Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-based agents to design collaborative AI systems autonomously. To explore this pro…
Multi-modal Large Language Models have shown remarkable progress in visual contexts, yet their ability to convert visual figures into executable code remains underexplored. To address this, we introduce Plot2Code, a comprehensive benchmark designed to assess MLLMs’ visual coding capabilities. Plot2C…
The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a scalable motion generation framework that includes the motion to…
In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically d…
Humans generally acquire new skills without compromising the old; however, the opposite holds for Large Language Models (LLMs), e.g., from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion of Transformer blocks. We tune the expanded blocks using onl…
Foundation models have achieved great advances in multi-task learning with a unified interface of unimodal and multimodal tasks. However, the potential of such multi-task learners has not been exploited during transfer learning. In this work, we present a universal parameter-efficient transfer learn…
The human sense of touch enables us to perform delicate tasks on deformable objects and/or in a vision-denied environment. To achieve similar desirable interactions for robots, such as administering a swab test, tactile information sensed beyond the tool-in-hand is crucial for contact state estimati
Photos serve as a way for humans to record what they experience in their daily lives, and they are often regarded as trustworthy sources of information. However, there is a growing concern that the advancement of artificial intelligence (AI) technology may produce fake photos, which can create confu…
Humans can use different grasping poses and forces for everyday objects of different shapes and sizes. Grasping and manipulating everyday objects have been longstanding challenges in robotics. Performing multiple grasping configurations is difficult for robotic end-effectors with limited degrees of
To function effectively in real-world environments, powered wearable robots such as exoskeletons and robotic prostheses must recognize the user's motion intent by detecting the user's locomotion modes such as walking, stair ascent and descent or ramp ascent and descent. Traditionally, intent detecti…