Grounded in Time: A Multi-Source Dataset and Benchmark for Temporal Grounding in Robotic Manipulation
Research
Research News
New papers, breakthroughs and academic AI research
When Can Digital Personas Reliably Approximate Human Survey Findings?
Research
FloVMos: Optical Flow-based Medical Video Mosaicking
Research
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
Research
Asynchronous Tracking, Optical Communication and 3D Motion Capture using Event-based Sensors
Research
Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment
Research
ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies
Research
Measuring the Depth of LLM Unlearning via Activation Patching
Research
TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution
Research
Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
Research
Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco
Research
Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision
Research