相关论文: Entity-Centric World Models: Interaction-Aware Mas…

Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature". While effective at capturing local syntax, these generative paradigms prioritize token-level…

We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representation learning and future prediction ability of V-JEPA 2.1, JFAA uses a frozen encoder and…

A long-standing challenge in scene analysis is the recovery of scene arrangements under moderate to heavy occlusion, directly from monocular video. While the problem remains a subject of active research, concurrent advances have been made…

Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memory in predicting…

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues,…

Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a…

Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly…

Eye movements have long been studied as a window into the attentional mechanisms of the human brain and made accessible as novelty style human-machine interfaces. However, not everything that we gaze upon, is something we want to interact…

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision…

Manipulation tasks require robots to reason about cause and effect when interacting with objects. Yet, many data-driven approaches lack causal semantics and thus only consider correlations. We introduce COBRA-PPM, a novel causal Bayesian…

Joint visual attention (JVA) provides informative cues on human behavior during social interactions. The ubiquity of egocentric eye-trackers and large-scale datasets on everyday interactions offer research opportunities in identifying JVA…

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we…

Expressing and identifying emotions through facial and physical expressions is a significant part of social interaction. Emotion recognition is an essential task in computer vision due to its various applications and mainly for allowing a…

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…

For efficient human-agent interaction, an agent should proactively recognize their target user and prepare for upcoming interactions. We formulate this challenging problem as the novel task of jointly forecasting a person's intent to…

Knowledge bases, and their representations in the form of knowledge graphs (KGs), are naturally incomplete. Since scientific and industrial applications have extensively adopted them, there is a high demand for solutions that complete their…

Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly…

Reliable perception is essential for robots that interact with the world. But sensors alone are often insufficient to provide this capability, and they are prone to errors due to various conditions in the environment. Furthermore, there is…

Medical AI systems face catastrophic forgetting when deployed in clinical settings, where models must learn new imaging protocols while retaining prior diagnostic capabilities. This challenge is particularly acute for medical…

To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems. While recent pretrained models (such as…