相关论文: CoachMe: Decoding Sport Elements with a Reference-…

Reinforcement learning method is extremely competitive in gait generation techniques for quadrupedal robot, which is mainly due to the fact that stochastic exploration in reinforcement training is beneficial to achieve an autonomous gait.…

A common assumption in machine learning is that training data are i.i.d. samples from some distribution. Processes that generate i.i.d. samples are, in a sense, uninformative---they produce data without regard to how good this data is for…

Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics)…

This work proposes Autonomous Iterative Motion Learning (AI-MOLE), a method that enables systems with unknown, nonlinear dynamics to autonomously learn to solve reference tracking tasks. The method iteratively applies an input trajectory to…

Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal…

Despite progress in video large language models (Video-LLMs), research on instructional video understanding, crucial for enhancing access to instructional content, remains insufficient. To address this, we introduce InstructionBench, an…

Human pose estimation has made significant advancement in recent years. However, the existing datasets are limited in their coverage of pose variety. In this paper, we introduce a novel benchmark FollowMeUp Sports that makes an important…

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal…

In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…

One-on-one tutoring is widely acknowledged as an effective instructional method, conditioned on qualified tutors. However, the high demand for qualified tutors remains a challenge, often necessitating the training of novice tutors (i.e.,…

Analyzing human motion is an active research area, with various applications. In this work, we focus on human motion analysis in the context of physical rehabilitation using a robot coach system. Computer-aided assessment of physical…

Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend. However, such exercises are hard to follow without expert guidance (which is impossible to scale for personalized…

Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in…

Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion…

Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by…

This paper introduces a new spreadsheet tool for adoption by high school or college level physics teachers who use common assessments in a pre-instruction/post-instruction mode to diagnose student learning and teaching effectiveness. The…

In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must…

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations…

While success in many robotics tasks can be determined by only observing the final state and how it differs from the initial state - e.g., if an apple is picked up - many tasks require observing the full motion of the robot to correctly…

Large language models (LLMs) substantially enhance developer productivity in repository-level code generation through interactive collaboration. However, as interactions progress, repository context must be continuously preserved and…