Weida Wang
YOU?
Author Swipe
View article: Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning Open
Large language models (LLMs) have demonstrated remarkable reasoning abilities in complex tasks, often relying on Chain-of-Thought (CoT) reasoning. However, due to their autoregressive token-level generation, the reasoning process is largel…
View article: Control-R: Towards controllable test-time scaling
Control-R: Towards controllable test-time scaling Open
This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning Control Fields (RCF)--a novel test-time approach that inje…
View article: Real-time aircraft bracket junction point detection for split flying vehicle module docking
Real-time aircraft bracket junction point detection for split flying vehicle module docking Open
The split flying car is composed of a flight module, a passenger capsule and an intelligent chassis module. The autonomous docking between these modules enables the split flying car to switch between flight mode and driving mode. The posit…
View article: A quadratic-programming-free-based energy-saving scheme for heavy-duty vehicle platoons experiencing time-delays
A quadratic-programming-free-based energy-saving scheme for heavy-duty vehicle platoons experiencing time-delays Open
View article: An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system
An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system Open
View article: An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system
An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system Open
View article: An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system
An energy-saving oriented control technique for heavy-duty vehicle platoon experiencing communication delays based on quadratic programming-free algorithm with optimized Type-II fuzzy system Open
View article: Enhancing Cr(Vi) Removal by Regulating Fe/Al Bimetal Adsorption and Reduction Properties: Kinetic and Mechanistic Studies
Enhancing Cr(Vi) Removal by Regulating Fe/Al Bimetal Adsorption and Reduction Properties: Kinetic and Mechanistic Studies Open
View article: Extreme-Environment-Aware Adaptive Energy Management Strategy for Heavy-Duty Series Hybrid Electric Vehicles Based on Data-Driven Method
Extreme-Environment-Aware Adaptive Energy Management Strategy for Heavy-Duty Series Hybrid Electric Vehicles Based on Data-Driven Method Open
View article: Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction Open
The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant …
View article: Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning Open
Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoni…
View article: Does ecological accountability restrain the financialization of heavily polluting enterprises? Evidence from China
Does ecological accountability restrain the financialization of heavily polluting enterprises? Evidence from China Open
Ecological accountability is an important means for the Chinese government to promote the development of green policies. In this study, a central environmental protection inspection was used as an exogenous shock event, China’s A-share-lis…
View article: H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer
H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer Open
Multi-source transfer learning is an effective solution to data scarcity by utilizing multiple source tasks for the learning of the target task. However, access to source data and model details is limited in the era of commercial models, g…
View article: FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio Open
In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking fa…
View article: Online legal driving behavior monitoring for self-driving vehicles
Online legal driving behavior monitoring for self-driving vehicles Open
View article: Online Legal Driving Behavior Monitoring for Self-driving Vehicles
Online Legal Driving Behavior Monitoring for Self-driving Vehicles Open
In source data folder, we provide the source data of figures in manuscript. In Supplementary Data folder, we provide the explanatory document about the dataset, along with some dataset segments of SIND dataset. In addition, we have provide…
View article: Characteristics of Physical Parameters and Predictive Modeling of Mechanical Properties in Loess-Like Silty Clay for Engineering Geology
Characteristics of Physical Parameters and Predictive Modeling of Mechanical Properties in Loess-Like Silty Clay for Engineering Geology Open
View article: Law Compliance Decision Making for Autonomous Vehicles on Highways
Law Compliance Decision Making for Autonomous Vehicles on Highways Open
View article: Energy system and resource utilization in space: A state-of-the-art review
Energy system and resource utilization in space: A state-of-the-art review Open
Deep space exploration expands our understanding about the evolution history of solar system, while the future development heavily relies on the construction of energy systems and utilization of resources on the planet. This paper systemat…
View article: An Efficient Energy Management Strategy of a Hybrid Electric Unmanned Aerial Vehicle Considering Turboshaft Engine Speed Regulation: A Deep Reinforcement Learning Approach
An Efficient Energy Management Strategy of a Hybrid Electric Unmanned Aerial Vehicle Considering Turboshaft Engine Speed Regulation: A Deep Reinforcement Learning Approach Open
View article: Nonsingular Fast Terminal Sliding Mode Fault-Tolerant Control Scheme for Four-Wheel-Independent-Drive Electric Vehicles with Fault Observer
Nonsingular Fast Terminal Sliding Mode Fault-Tolerant Control Scheme for Four-Wheel-Independent-Drive Electric Vehicles with Fault Observer Open
View article: A Physics-Informed Learning Algorithm in Dynamic Speed Prediction Method for Series Hybrid Electric Powertrain
A Physics-Informed Learning Algorithm in Dynamic Speed Prediction Method for Series Hybrid Electric Powertrain Open
View article: Face to Planning Risk: A Hierarchical Risk-Aware Prediction Module for the Safe Planning System
Face to Planning Risk: A Hierarchical Risk-Aware Prediction Module for the Safe Planning System Open
View article: H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer
H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer Open
Multi-source transfer learning is an effective solution to data scarcity by utilizing multiple source tasks for the learning of the target task. However, access to source data and model details is limited in the era of commercial models, g…
View article: Legal Decision-making for Highway Automated Driving
Legal Decision-making for Highway Automated Driving Open
Compliance with traffic laws is a fundamental requirement for human drivers on the road, and autonomous vehicles must adhere to traffic laws as well. However, current autonomous vehicles prioritize safety and collision avoidance primarily …
View article: How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?
How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction? Open
An accurate trajectory prediction is crucial for safe and efficient autonomous driving in complex traffic environments. In recent years, artificial intelligence has shown strong capabilities in improving prediction accuracy. However, its c…
View article: Time-Delay-Aware Power Coordinated Control Approach for Series Hybrid Electric Vehicles
Time-Delay-Aware Power Coordinated Control Approach for Series Hybrid Electric Vehicles Open
View article: No driver, No Regulation? --Online Legal Driving Behavior Monitoring for Self-driving Vehicles
No driver, No Regulation? --Online Legal Driving Behavior Monitoring for Self-driving Vehicles Open
Defined traffic laws must be respected by all vehicles. However, it is essential to know which behaviors violate the current laws, especially when a responsibility issue is involved in an accident. This brings challenges of digitizing huma…
View article: Energy management of hybrid electric propulsion system: Recent progress and a flying car perspective under three-dimensional transportation networks
Energy management of hybrid electric propulsion system: Recent progress and a flying car perspective under three-dimensional transportation networks Open
View article: SIND: A Drone Dataset at Signalized Intersection in China
SIND: A Drone Dataset at Signalized Intersection in China Open
Intersection is one of the most challenging scenarios for autonomous driving tasks. Due to the complexity and stochasticity, essential applications (e.g., behavior modeling, motion prediction, safety validation, etc.) at intersections rely…