3 papers
cs.AI2026
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
Xingbo Yao, Xiaoman Wang, Zhengwu Lei +11
Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially c…
cs.CL2026
Towards Communication-Efficient Social Intelligence in Language Agents
Linxiao Gong, Yijie Xu, Tianfu Wang +7
Socially intelligent language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and attention of both participants. Balancing these d…
cs.CV2026
Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation
Boyuan Cao, Xingbo Yao, Chenhui Wang +3
Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation, yet the quadratic cost of self-attention poses a major scalability bottlen…