Category Latest News

Subject-Driven Image Evaluation Gets Simpler: Google Researchers Introduce REFVNLI to Jointly Score Textual Alignment and Subject Consistency Without Costly APIs

Text-to-image (T2I) generation has evolved to include subject-driven approaches, which enhance standard T2I models by incorporating reference images alongside text prompts. This advancement allows for more precise subject representation in generated images. Despite the promising applications, subject-driven T2I generation faces…

Training LLM Agents Just Got More Stable: Researchers Introduce StarPO-S and RAGEN to Tackle Multi-Turn Reasoning and Collapse in Reinforcement Learning

Large language models (LLMs) face significant challenges when trained as autonomous agents in interactive environments. Unlike static tasks, agent settings require sequential decision-making, cross-turn memory maintenance, and adaptation to stochastic environmental feedback. These capabilities are essential for developing effective planning…