Papers
-
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
-
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
-
DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object DynamicsAntGroup / Shenzhen University, State Key Laboratory of General Artificial Intelligence, Zhejiang University
-
OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
-
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer SelectionAntGroup / Cleveland Clinic Lerner Research Institution, Cornell University, Sichuan University, University of Liverpool
-
Learning Hierarchical Knowledge in Text-Rich Networks with Taxonomy-Informed Representation Learning
-
EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification
-
Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational ReadinessAntGroup / Carnegie Mellon University, Duke University, Emory University, Georgia Institute of Technology, Harvard Medical School, Harvard University, Oncode Institute, Qingdao City University, Shanghai Jiao Tong University, Sichuan University, Stanford University, Technische Universität Dresden, Tsinghua University, University of Chicago, University of Texas, University of Warwick
-
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured VisionAntGroup / East China Normal University, Hong Kong University of Science and Technology, Shanghai Jiao Tong University
MongoDB - Build AI That Scales
