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 proposes a recipe for scaling text-to-video generation by leveraging widely accessible text-free videos, studying the scaling trend and enabling compositional video synthesis.
Wenyi Hong, Ming Ding, Wendi Zheng, et al.
CogVideo is the first large-scale pretrained transformer for text-to-video generation, leveraging a pretrained text-to-image model to achieve state-of-the-art results.
Unknown
Controlvideo introduces a training-free framework for controllable text-to-video generation by leveraging pre-trained text-to-image models.
Unknown
Proposes Adversarial Representation Engineering (ARE), a general model editing framework that efficiently edits large language models by leveraging representation engineering.
Unknown
This paper reflects on the AI alignment problem, discussing the challenges of ensuring AGI conforms to human values and remains under human control.
Unknown
HaloScope harnesses unlabeled LLM generations to improve hallucination detection accuracy by formalizing the problem and leveraging unlabeled data.
Unknown
First systematic study of benchmark contamination in large reasoning models, structured around two stages where contamination can occur.
Unknown
Freeprm trains process reward models without ground truth process labels by leveraging outcome labels and a novel self-supervised objective, improving LLM reasoning performance.
Georgios Kaissis, Marcus R. Makowski, Daniel Rückert, et al.
This paper reviews federated, secure, and privacy-preserving AI methods for medical imaging, addressing data protection and utilization challenges.
Unknown
GraphRAG enhances LLM-driven RAG for finance by using graph-based retrieval to reduce hallucinations and improve contextual coherence.
Unknown
This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance LLM-based automated requirement traceability and compliance che
Unknown
This paper surveys the status, challenges, and future directions of foundation models in medical imaging, contextualizing their shift from task-specific models.