Scaling diffusion transformers to 16 billion parameters
Unknown
This paper presents a methodology for scaling diffusion transformers to 16 billion parameters, including design choices for expert routing algorithms.
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper presents a methodology for scaling diffusion transformers to 16 billion parameters, including design choices for expert routing algorithms.
Unknown
This paper introduces algorithms for machine unlearning under storage constraints and demonstrates a strict separation between differential privacy and machine unlearning.
B. Sheth
Proposes a learning-based framework for personalized information filtering agents, implemented as 'Newt', using relevance feedback and genetic algorithms to adapt to user interests.
Zun Li, John Schultz, Daniel Hennes, et al.
This paper uses LLM-powered evolutionary agents to discover new MARL algorithms, distilling them into minimal solvers that outperform human-designed baselines.
Jonathan J. Heckman, Shani Meynet, Alessandro Mininno, et al.
This paper uses machine learning, including transformers and MLPs, to efficiently establish Seiberg dualities in supersymmetric quiver gauge theories, outperforming deterministic algorithms and suggesting a new benchmark for AI in theoretical physics
Unknown
This paper investigates in-context learning of regular languages generated by random finite automata, comparing architectures and algorithms.
Sagar Lekhak, Prasanna Reddy Pulakurthi, Emmett J. Ientilucci
This paper studies human-in-the-loop signature bootstrapping for UAV hyperspectral PFM-1 mine detection, comparing detection algorithms and showing ACE requires far fewer candidate inspections than SAM variants.
Patrick Bilic, Patrick Ferdinand Christ, Hongwei Li, et al.
The LiTS benchmark evaluates liver and tumor segmentation algorithms on a diverse CT dataset, finding no single algorithm excels at both tasks and highlighting the need for improved tumor detection.
Amina Adadi
This survey systematically categorizes data-efficient ML methods into four strategies: non-supervised learning, data augmentation, transfer learning, and algorithm modification.
Shuai Liu, Dongye Liu, Gautam Srivastava, et al.
Survey of correlation filter algorithms for real-time object tracking, covering background, key technologies, datasets, and reliability-based methods.
Dan Gusfield
A comprehensive textbook on string algorithms, suffix trees, and sequence alignment with applications in computational biology.
Tuan-Minh Pham, Thi-Thuy-Lien Nguyen
Proposes optimization models and approximation algorithms for joint gateway placement, service placement, and routing in NFV-enabled IoT edge cloud systems.