MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation
Research
Research News
New papers, breakthroughs and academic AI research
SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
Research
Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment
Research
ESCROW: Guarded and Dual-Objective Continual Maintenance for Agents in Policy-Governed Enterprise Workflows
Research
Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
Research
Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
Research
What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives
Research
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
Research
Greed Is Learned: Visible Incentives as Reward-Hacking Triggers
Research
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
Research
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
Research
Generalized Design Choices for Deepfake Detectors
Research