Roger Zimmermann

Causal Time Series Generation via Diffusion Models

Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection

Semantic Embedding-Driven Topology Extraction with Correlation Lag Awareness

Make Your LVLM KV Cache More Lightweight

OpenAVS: Training-Free Open-Set Audio Visual Segmentation with Foundational Models

Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection

Generalized Video Moment Retrieval

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models

Grounding is All You Need? Dual Temporal Grounding for Video Dialog

Robust Video Moment Retrieval with Introspective Knowledge Distillation