4 papers · 1 filter
Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
Zhilong Zheng, Letian Tao, Yang Guan +7
Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tu…
Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
Shiqi Liu, Zeyu He, Letian Tao +9
On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off between objective fidelity and op…
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
Bonan Wang, Letian Tao, Bin Shuai +7
Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates…
MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization
Dongcheng Zou, Senzhang Wang, Xuefeng Li +5
Traffic forecasting is a complex multivariate time-series regression task of paramount importance for traffic management and planning. However, existing approaches often struggle t…