Jiachen Li

Bingsheng Yao, Guiming Chen, Ruishi Zou et al.

While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM's performance? In this work, we propose In-Context Sampling (ICS), a low-resource LLM prompting technique to produce confident predictions by optimizing the construction of multiple ICL prompt inputs. Extensive experiments with three open-source LLMs (FlanT5-XL, Mistral-7B, and Mixtral-8x7B) on four NLI datasets (e-SNLI, Multi-NLI, ANLI, and Contract-NLI) and one QA dataset (CommonsenseQA) illustrate that ICS can consistently enhance LLMs' performance. An in-depth evaluation with three data similarity-based ICS strategies suggests that these strategies can further elevate LLM's performance, which sheds light on a new yet promising future research direction.

Jiachen Li, Shihao Li, Soovadeep Bakshi et al.

When a controller is designed from an identified model, its performance ultimately depends on the trajectories used for identification, but pinpointing which ones help or hurt remains an open problem. We bring influence functions, a data attribution tool from machine learning, into this setting by chaining two closed form sensitivity analyses across a regularized least squares identification and an infinite horizon LQR pipeline. On the identification side, the quadratic loss admits an exact leave one trajectory out parameter shift and a reusable first order approximation with a Neumann series error bound. On the control side, we implicitly differentiate through the DARE via its discrete Lyapunov structure and compress the cost gradient to a single adjoint Lyapunov solve. The resulting scores track true LOTO retraining with Pearson correlations above 0.99 and speedups of 7 to 60 times on linear systems of dimension 2 to 10.

Jiachen Li, Shihao Li, Jian Chu et al.

Data Enabled Predictive Control (DeePC) is an established model free approach to predictive control, but it faces two open challenges: computational complexity that scales cubically with dataset size and performance degradation when data are corrupted. This paper introduces Robust Data Selection DeePC (RDS DeePC), a framework that addresses both obstacles through influence function analysis. We derive a sensitivity score quantifying the leverage each trajectory segment exerts on the optimization solution and prove that high sensitivity segments correspond to outliers while low sensitivity segments represent consistent data. Selecting low sensitivity segments thus yields both computational efficiency and automatic outlier filtering without requiring data quality labels. For nonlinear systems, we extend the framework via a two stage online selection approach accelerated by the LiSSA algorithm. Experiments on four systems of increasing complexity including a DC motor, an inverted pendulum, a planar quadrotor UAV tracking a figure 8 trajectory, and a kinematic bicycle vehicle following a figure 8 path demonstrate that RDS DeePC achieves 94 to 97 percent clean data selection and comparable or better tracking performance under 20 percent data corruption.

Jiachen Li, Xu Duan, Shihao Li et al.

We extend the Datamodels framework from supervised learning to Model Predictive Path Integral (MPPI) control. Whereas Datamodels estimate sample influence via regression on a fixed dataset, we instead learn to predict influence directly from sample cost features, enabling real-time estimation for newly generated samples without online regression. Our influence predictor is trained offline using influence coefficients computed via the Datamodel framework across diverse MPPI instances, and is then deployed online for efficient sample pruning and adaptive constraint handling. A single learned model simultaneously addresses efficiency and safety: low-influence samples are pruned to reduce computational cost, while monitoring the influence of constraint-violating samples enables adaptive penalty tuning. Experiments on path-tracking with obstacle avoidance demonstrate up to a $5\times$ reduction in the number of samples while maintaining control performance and improving constraint satisfaction.