Tsinghua University · Research Paper
UniGenDet
CVPR 2026 framework that unifies image generation and authenticity detection so 'spear and shield' co-evolve, with detectors guiding more authentic synthesis and generators improving forensic interpretability. Uses Symbiotic Multi-modal Self-Attention and is evaluated on FakeClue, DMImage, and ARForensics.
Open the source ↗Similar Research & Safety releases
- PhotoGuard
MadryLab (Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry) · Image edit protection · Week 45, 2026
- WEB4
Dennis Palatov (dp-web4), co-authored with GPT-4o, DeepSeek, Grok, Claude, Gemini, and Manus · Research Paper · Week 30, 2026
- Teaching AI to See the World More Like Humans Do
Google DeepMind · Research Paper · Week 46, 2025
- Sleep framework for continual learning
Google Research (Ali Behrouz, Vahab Mirrokni) · Sleep-phase continual learning · Week 45, 2026
- Anthropic files for an IPO (Form S-1)
Anthropic, PBC · IPO Filing · Week 45, 2026
- OpenAI: working with academic communities on science
OpenAI · AI for science · Week 45, 2026
More from Tsinghua University
- TactileStep
Tsinghua University · Humanoid Tactile Locomotion · Week 41, 2026
- VoiceMem
Tsinghua University · Voice Memory · Week 35, 2026
- H-Neurons
Tsinghua University · Interpretability · Week 10, 2026
- DreamID-Omni
Tsinghua University · Video Editing · Week 9, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.