相关论文: YoCausal: How Far is Video Generation from World M…

Anomaly detection in surveillance videos remains a challenging task due to the diversity of abnormal events, class imbalance, and scene-dependent visual clutter. To address these issues, we propose a robust deep learning framework that…

Causal thinking enables humans to understand not just what is seen, but why it happens. To replicate this capability in modern AI systems, we introduce the task of visual causal discovery. It requires models to infer cause-and-effect…

Inferring the causal direction and causal effect between two discrete random variables X and Y from a finite sample is often a crucial problem and a challenging task. However, if we have access to observational and interventional data, it…

Video Question Answering is a challenging task, which requires the model to reason over multiple frames and understand the interaction between different objects to answer questions based on the context provided within the video, especially…

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. However, existing…

Inferring cause-effect relationships from observational data has gained significant attention in recent years, but most methods are limited to scalar random variables. In many important domains, including neuroscience, psychology, social…

Multimodal Large Language Models (MLLMs) have achieved impressive results on vision-language benchmarks, yet it remains unclear whether these benchmarks assess genuine global reasoning or allow success via localized visual cues. Existing…

Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without…

Complex systems with intricate causal dependencies challenge accurate prediction. Effective modeling requires precise physical process representation, integration of interdependent factors, and incorporation of multi-resolution…

Causal discovery aims to extract qualitative causal knowledge in the form of causal graphs from data. Because causal ground truth is rarely known in the real world, simulated data plays a vital role in evaluating the performance of the…

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken…

This thesis develops methods for causal inference and causal representation learning (CRL) in high-dimensional, time-varying data. The first contribution introduces the Causal Dynamic Variational Autoencoder (CDVAE), a model for estimating…

Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily…

Market generators using deep generative models have shown promise for synthetic financial data generation, but existing approaches lack causal reasoning capabilities essential for counterfactual analysis and risk assessment. We propose a…

Video anomaly understanding (VAU) aims to provide detailed interpretation and semantic comprehension of anomalous events within videos, addressing limitations of traditional methods that focus solely on detecting and localizing anomalies.…

Causal inference from observational data following the restricted structural causal model (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or nonlinearity.…

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping…

Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An active community of researchers develops and enhances…