الباحثون

Shiwei Li

المنشورات 2

نسخة أولية وصول مفتوح

ChunkTrust: Adapting Execution Horizons for Robot Policies with Action-Expert Evidence

Fanding Huang, Jingyan Jiang, Shifeng Bao وآخرون · 2026

Robot foundation policies predict action chunks, but how many actions to execute before replanning depends on the current task phase. We introduce ChunkTrust, which treats the execution horizon as a latent variable inferred from action-expert evidence rather than a fixed hyperparameter. Its training-free Action-aware H …

نسخة أولية وصول مفتوح

Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition

Yihao Ouyang, Shiwei Li, Haozhao Wang وآخرون · 2026

Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT), yet a performance gap can remain relative to full fine-tuning (FFT). Many LoRA variants improve the initialization or optimization of low-rank factors. At each training step, however, their first-order weight-space direction …

المؤلفون المشاركون