2 papers
cs.AI2026
Inducing Reasoning Primitives from Agent Traces
Zhihan Lei, Jiarui Yan, Joshua Momo +1
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Ind…
cs.CV2024
Beyond Color and Lines: Zero-Shot Style-Specific Image Variations with Coordinated Semantics
Jinghao Hu, Yuhe Zhang, GuoHua Geng +5
Traditionally, style has been primarily considered in terms of artistic elements such as colors, brushstrokes, and lighting. However, identical semantic subjects, like people, boat…