AI
MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees
Researchers have developed an algorithm called MIL-BERT that can classify large text documents by se...
AI
Directional Contextual Representations for Dependency Relations: Why Cross-Direction Pairing Fails
Researchers have found that pairing forward and backward contextual representations in a bidirection...
AI
AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification
Researchers have developed AsmEvo, an agentic assembly-level optimizer for AMD GPU kernels. It optim...
AI
Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique
Researchers have developed a framework called Tree-of-Concerns to help identify unstated limitations...
AI
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields
Researchers have developed a new method for watermarking diffusion language mode...
AI
Ontology-Driven Structural Regularization for Document-Level Relation Extraction
Researchers have developed an ontology-driven framework to improve the accuracy ...
AI
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
Researchers have proposed a new AI framework called ForeDreamer for predicting f...
AI
Scaling Unsupervised Word Alignment to Documents via Structural Constraints
Researchers have developed two new methods for aligning words across entire docu...