Peta
PulseAugur coverage of Peta — every cluster mentioning Peta across labs, papers, and developer communities, ranked by signal.
- 2026-08-21 research_milestone A new paper introduces PETA, a parameter-efficient framework for adapting AI models for virtual screening. source
2 day(s) with sentiment data
-
UniQuery unifies vision models for improved pedestrian attribute recognition
Researchers have developed UniQuery, a novel method for pedestrian attribute recognition that unifies vision models like DINOv3 and CLIP. Unlike traditional methods that combine models with fixed weights, UniQuery joint…
-
Alternatives to animal testing gain momentum with new tech and regulations
The use of alternatives to animal testing in scientific research is gaining significant traction, driven by regulatory changes and advancements in technology. Initiatives like the Food and Drug Administration Modernizat…
-
New PETA framework efficiently adapts AI models for drug discovery
Researchers have developed PETA, a parameter-efficient framework for adapting pretrained virtual screening models to specific protein pockets. This method addresses the computational cost of retraining entire models by …
-
Robotic elephants replace live animals in Indian temples, sparking debate
Robotic elephants are being introduced in some Indian temples as a replacement for live animals, a move supported by animal welfare groups like Peta. These life-size animatrons, constructed from materials like fiberglas…
-
New research identifies 'cheating trap' in AI pedestrian recognition
Researchers have identified a significant challenge in pedestrian attribute recognition (PAR) caused by extreme class imbalance in large datasets like PETA and PA-100K. This imbalance leads to a phenomenon termed the 'm…
-
PETA urges Malaysian prison to adopt vegan meals for inmates
The animal rights organization PETA has formally requested that Kajang Prison in Malaysia implement a vegan meal policy for all inmates, including former Prime Minister Najib Razak. PETA argues that such a policy would …
-
New framework uses Evidential Deep Learning for uncertainty-aware pedestrian attribute recognition
Researchers have developed UAPAR, a novel framework for pedestrian attribute recognition that incorporates Evidential Deep Learning (EDL) to assess prediction reliability. This approach aims to improve system robustness…