arXiv subjects

Ji Yin

Publications and source records attributed to Ji Yin.

10 recordsLinked to original sources

arXiv2025

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture

While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The core challenge is effectively combining textual reasoning, coding, and search for diverse questions. In this paper, we propose Tool-Use Mixture (TUMIX), an ensemble framework that runs multiple agents in parallel, each employing distinct tool-use strategies and answer paths. Agents in TUMIX iteratively share and refine responses based on the question and previous answers. In experiments, TUMIX achieves significant gains over state-of-the-art tool-augmented and test-time scaling methods, delivering an average accuracy improvement of up to 3.55% over the best baseline on Gemini-2.5-Pro and Gemini-2.5-Flash across key reasoning benchmarks, with near-equal inference costs. We find that agent diversity and quality are crucial and can be enhanced by using LLMs to auto-optimize agent designs. Furthermore, TUMIX can halt refinement upon reaching sufficient confidence, preserving performance at only 49% of the inference cost. Further scaling can achieve higher performance, albeit at a greater cost.

cs.CL↗

arXiv2025

TianHui: A Domain-Specific Large Language Model for Diverse Traditional Chinese Medicine Scenarios

Domain-specific LLMs in TCM face limitations in research settings due to constrained adaptability, insufficient evaluation datasets, and limited computational resources. This study presents TianHui, a specialized TCM LLM built through contextual data integration and domain knowledge fusion. We constructed a large-scale TCM corpus (0.97GB unsupervised data + 611,312 QA pairs) and employed a two-stage training strategy with QLoRA, DeepSpeed Stage 2, and Flash Attention 2. Evaluation on 12 benchmarks showed TianHui ranked top-three in all metrics for six datasets (APQ, TCMCD, HFR, HCCA, DHPE, TLAW) and achieved top results in the other six (TCMEE, APR, GCPMI, TCMKQA, TCMRC, ADTG). Optimal configuration was identified as LoRA rank=128, alpha=256, epoch=4, dropout=0.2, max length=2048. TianHui enables systematic preservation and scalable application of TCM knowledge. All resources are open-sourced.

cs.CL↗

arXiv2025

Hybrid Compact Least-Squares and Central Weighted Essentially Non-Oscillatory Schemes for Hyperbolic Conservation Laws on Structured Curvilinear Grids

A series of third- and fifth-order hybrid compact least-squares central weighted essentially non-oscillatory schemes are proposed and applied to curvilinear structured grids for the finite volume method. In smooth regions, compact least-squares schemes based on interfacial differences of derivatives are utilized to keep the high resolution of multiscale structures, whereas in discontinuous regions, central weighted essentially non-oscillatory schemes are included to enable the oscillation free shock capturing capability of the hybrid schemes. Free parameters in the proposed compact least-squares schemes are firstly optimized to reach a broad range of resolved bandwidths with different levels of dissipation. In addition, a shock detector proposed in our previous work is introduced and validated to be not only able to detect smooth first-order extrema but also robust in detecting discontinuities. Through the solution of block tridiagonal reconstruction linear systems, the resulting schemes can give an explicit polynomial for each control volume and are efficient with an acceptable computational overhead when compared to the pure central weighted essentially non-oscillatory schemes. Eventually, benchmarks including one-dimensional and two-dimensional, linear and nonlinear, inviscid and viscous problems on uniform and nonuniform curvilinear grids demonstrate the proposed schemes' promising applicability in compressible flows which have both multiscale structures and discontinuities.

physics.flu-dyn↗

arXiv2025

Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions

A common problem when using model predictive control (MPC) in practice is the satisfaction of safety specifications beyond the prediction horizon. While theoretical works have shown that safety can be guaranteed by enforcing a suitable terminal set constraint or a sufficiently long prediction horizon, these techniques are difficult to apply and thus are rarely used by practitioners, especially in the case of general nonlinear dynamics. To solve this problem, we impose a tradeoff between exact recursive feasibility, computational tractability, and applicability to ``black-box'' dynamics by learning an approximate discrete-time control barrier function and incorporating it into a variational inference MPC (VIMPC), a sampling-based MPC paradigm. To handle the resulting state constraints, we further propose a new sampling strategy that greatly reduces the variance of the estimated optimal control, improving the sample efficiency, and enabling real-time planning on a CPU. The resulting Neural Shield-VIMPC (NS-VIMPC) controller yields substantial safety improvements compared to existing sampling-based MPC controllers, even under badly designed cost functions. We validate our approach in both simulation and real-world hardware experiments. Project website: https://mit-realm.github.io/ns-vimpc/.

cs.RO↗

arXiv2024

Safety on the Fly: Constructing Robust Safety Filters via Policy Control Barrier Functions at Runtime

Control Barrier Functions (CBFs) have proven to be an effective tool for performing safe control synthesis for nonlinear systems. However, guaranteeing safety in the presence of disturbances and input constraints for high relative degree systems is a difficult problem. In this work, we propose the Robust Policy CBF (RPCBF), a practical approach for constructing robust CBF approximations online via the estimation of a value function. We establish conditions under which the approximation qualifies as a valid CBF and demonstrate the effectiveness of the RPCBF-safety filter in simulation on a variety of high relative degree input-constrained systems. Finally, we demonstrate the benefits of our method in compensating for model errors on a hardware quadcopter platform by treating the model errors as disturbances. Website including code: www.oswinso.xyz/rpcbf/

math.OC↗

arXiv2024

Chance-Constrained Information-Theoretic Stochastic Model Predictive Control with Safety Shielding

This paper introduces a novel nonlinear stochastic model predictive control path integral (MPPI) method, which considers chance constraints on system states. The proposed belief-space stochastic MPPI (BSS-MPPI) applies Monte-Carlo sampling to evaluate state distributions resulting from underlying systematic disturbances, and utilizes a Control Barrier Function (CBF) inspired heuristic in belief space to fulfill the specified chance constraints. Compared to several previous stochastic predictive control methods, our approach applies to general nonlinear dynamics without requiring the computationally expensive system linearization step. Moreover, the BSS-MPPI controller can solve optimization problems without limiting the form of the objective function and chance constraints. By multi-threading the sampling process using a GPU, we can achieve fast real-time planning for time- and safety-critical tasks such as autonomous racing. Our results on a realistic race-car simulation study show significant reductions in constraint violation compared to some of the prior MPPI approaches, while being comparable in computation times.

cs.RO↗

arXiv2023

Shield Model Predictive Path Integral: A Computationally Efficient Robust MPC Approach Using Control Barrier Functions

Model Predictive Path Integral (MPPI) control is a type of sampling-based model predictive control that simulates thousands of trajectories and uses these trajectories to synthesize optimal controls on-the-fly. In practice, however, MPPI encounters problems limiting its application. For instance, it has been observed that MPPI tends to make poor decisions if unmodeled dynamics or environmental disturbances exist, preventing its use in safety-critical applications. Moreover, the multi-threaded simulations used by MPPI require significant onboard computational resources, making the algorithm inaccessible to robots without modern GPUs. To alleviate these issues, we propose a novel (Shield-MPPI) algorithm that provides robustness against unpredicted disturbances and achieves real-time planning using a much smaller number of parallel simulations on regular CPUs. The novel Shield-MPPI algorithm is tested on an aggressive autonomous racing platform both in simulation and using experiments. The results show that the proposed controller greatly reduces the number of constraint violations compared to state-of-the-art robust MPPI variants and stochastic MPC methods.

cs.RO↗

arXiv2022

Risk-Aware Model Predictive Path Integral Control Using Conditional Value-at-Risk

In this paper, we present a novel Model Predictive Control method for autonomous robots subject to arbitrary forms of uncertainty. The proposed Risk-Aware Model Predictive Path Integral (RA-MPPI) control utilizes the Conditional Value-at-Risk (CVaR) measure to generate optimal control actions for safety-critical robotic applications. Different from most existing Stochastic MPCs and CVaR optimization methods that linearize the original dynamics and formulate control tasks as convex programs, the proposed method directly uses the original dynamics without restricting the form of the cost functions or the noise. We apply the novel RA-MPPI controller to an autonomous vehicle to perform aggressive driving maneuvers in cluttered environments. Our simulations and experiments show that the proposed RA-MPPI controller can achieve about the same lap time with significantly fewer collisions compared to the baseline MPPI controller. The proposed controller performs on-line computation at an update frequency of up to 80Hz, utilizing modern Graphics Processing Units (GPUs) to multi-thread the generation of trajectories as well as the CVaR values.

cs.RO↗

arXiv2022

Trajectory Distribution Control for Model Predictive Path Integral Control using Covariance Steering

This paper presents a novel control approach for autonomous systems operating under uncertainty. We combine Model Predictive Path Integral (MPPI) control with Covariance Steering (CS) theory to obtain a robust controller for general nonlinear systems. The proposed Covariance-Controlled Model Predictive Path Integral (CC-MPPI) controller addresses the performance degradation observed in some MPPI implementations owing to unexpected disturbances and uncertainties. Namely, in cases where the environment changes too fast or the simulated dynamics during the MPPI rollouts do not capture the noise and uncertainty in the actual dynamics, the baseline MPPI implementation may lead to divergence. The proposed CC-MPPI controller avoids divergence by controlling the dispersion of the rollout trajectories at the end of the prediction horizon. Furthermore, the CC-MPPI has adjustable trajectory sampling distributions that can be changed according to the environment to achieve efficient sampling. Numerical examples using a ground vehicle navigating in challenging environments demonstrate the proposed approach.

cs.RO↗

arXiv2020

Automatic Snake Gait Generation Using Model Predictive Control

In this paper, we propose a method for generating undulatory gaits for snake robots. Instead of starting from a pre-defined movement pattern such as a serpenoid curve, we use a Model Predictive Control approach to automatically generate effective locomotion gaits via trajectory optimization. An important advantage of this approach is that the resulting gaits are automatically adapted to the environment that is being modeled as part of the snake dynamics. To illustrate this, we use a novel model for anisotropic dry friction, along with existing models for viscous friction and fluid dynamic effects such as drag and added mass. For each of these models, gaits generated without any change in the method or its parameters are as efficient as Pareto-optimal serpenoid gaits tuned individually for each environment. Furthermore, the proposed method can also produce more complex or irregular gaits, e.g. for obstacle avoidance or executing sharp turns.

cs.RO↗