AI
DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts
Researchers have proposed a new deepfake detection method called DF-MoE that can generalize across d...
AI
Adversarial Entropy Inflation Against Gumbel-Based Inference Verification
Researchers have found a weakness in a method used to prevent AI models from leaking sensitive infor...
AI
Cross-lingual Biography Enrichment via Claim Extraction and Alignment
Researchers have developed a method to enrich English-language biographies with information from non...
AI
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
Researchers have developed a method to convert structured data into text across multiple domains wit...
AI
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Researchers propose a 'Densing Law' to describe the relationship between data sc...
AI
Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep
Researchers have conducted a study on how to decompose work among agents in larg...
AI
Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation
Researchers have proposed a new framework called ANR-DiffRec for generative reco...
AI
ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation
Researchers have developed a new method called ChebBooster to speed up the infer...