VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
Research
Research News
New papers, breakthroughs and academic AI research
Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation
Research
HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation
Research
Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy
Research
An automated pipeline for standardised speech-unit annotation in spontaneous dialogue
Research
Law And Order: Tax Law Autoformalization
Research
When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
Research
Dynamic LLM Routers are Often Misguided
Research
Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRS
Research
Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation
Research
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Research
TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Research