Researchers conducted semi-structured interviews with 22 software developers and AI practitioners to understand their decision-making process when int...
Researchers have explored post-training alignment in AI systems, but the effectiveness of constitutional midtraining interventions has not been extens...
Researchers have developed WAM-Diff2, a framework for transforming pre-trained autoregressive models into parallel diffusion models. This allows for e...
Researchers have developed Eigenius, an open-source database system designed to manage and verify complex knowledge graphs. The system uses a unified ...
Researchers have developed an AI system for triaging eye-related medical issues over the phone without requiring human annotation. The system, called ...
Researchers have proposed a new framework called Search-G1 to improve the performance of search-augmented language agents. These agents are designed t...
Researchers have developed a framework for conversational systems to provide follow-up edit suggestions in image-creation tasks. The system uses real ...
Researchers have developed FUSE (Frame-Unified Stress Estimation), a framework for detecting stress from facial video without breaking it down into sh...
Researchers have developed a new method for creating a double qubit excitation gate using only 12 CNOT operations. This is an improvement over previou...
Researchers have developed AQuA, a system that uses language models to improve quantitative trading research. It consists of two separate systems: one...
Researchers explored how a specific AI model, Gemma 3 4B IT, represents language related to truth and impossibility. They found that the model conflat...
Researchers have developed a new framework called NaviDC-OCR for parsing documents. The system addresses two major challenges in document parsing: acc...