4 papers
Vela: User Behavior as Supervision Sparks LLM Intelligence
Yang Xiao, Yusong Sun, Haoyi Wu +17
Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems.…
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Haoyi Wu, Yang Xiao, Yusong Sun +4
Real-world tasks often require large language models (LLMs) to learn from complex task-specific context rather than pretrained parametric knowledge. This capability remains a weakn…
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Yang Xiao, Yusong Sun, Haoyi Wu +7
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends,…
LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving
Yongzhi Liu, Yang Xiao, Zhong Cao +5
Autonomous driving requires long-horizon closedloop decision making in dynamic traffic environments. Latent world models offer an effective framework for this problem by enabling i…