Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks147 from public data
- Vision-language navigation: a survey and taxonomy89
A comprehensive survey and an insightful taxonomy ofVision-language navigation tasks based on the different characteristics of language instructions is provided, including the incorporation of knowledge into VLN models and transferring them to the real physical world.
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model78
Multi-stage Token Dropping (MustDrop) is proposed to measure the importance of each token from the whole lifecycle, including the vision encoding stage, prefilling stage, and decoding stage, and can more precisely recognize the important and redundant tokens, thus achieving an optimal balance between performance and efficiency.
- Navigation in Unknown Dynamic Environments Based on Deep Reinforcement Learning72
Improvements of MK-A3C can efficiently navigate robots in unknown dynamic environments, and satisfy kinetic constraints while handling moving objects, and solve the non-convergence policies problems caused by sparse reward.
- FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity59
Experimental results show that FedHiSyn outperforms six baseline methods, e.g., FedAvg, SCAFFOLD, and FedAT, in terms of training accuracy and efficiency.
- Scheduling parallel jobs with tentative runs and consolidation in the cloud41
The algorithm employs tentative run and workload consolidation under such a two-tier virtual machines architecture to enhance the popular FCFS algorithm, and it can even produce comparable performance to the runtime-estimation-based EASY algorithm.
- Sensor Control in Anti-Submarine Warfare—A Digital Twin and Random Finite Sets Based Approach38
By combining digital twin theory and random finite sets (RFSs) closely, a new framework of sensor control in ASW is proposed and the RFS-based data-assimilation algorithm is proposed for online assimilating the sequence of real-time measurements.
- A Reinforcement Learning Behavior Tree Framework for Game AI27
Following this study, a QBot model is build based on the framework in the Raven platform, a popular test bed for game AI development, and the result proves that the framework is advanced.
- GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation26
GeoNav, a multi-modal agent for long-range aerial navigation with geospatial awareness, operates in three phases-landmark navigation, target search, and precise localization-mimicking human coarse-to-fine spatial reasoning patterns.
- Learning Behavior Trees for Autonomous Agents with Hybrid Constraints Evolution26
A novel idea of dynamic constraint based on frequent sub-trees mining, which can accelerate evolution by protecting preponderant behavior sub-Trees from undesired crossover, is proposed and introduced into the evolving BTs with hybrid constraints (EBT-HC).
- Dynamic Obstacle-Avoiding Path Planning for Robots Based on Modified Potential Field Method25
A new potential field method is proposed, whose new virtual force is deduced through introducing the restriction of collision angle with exponential form and both the information of angle and magnitude of relative velocity, to solve the problem of unnecessary obstacle avoidance in dynamic obstacle avoidance planning.
- 24
- 23
- 21
- 20
- Regarding Goal Bounding and Jump Point Search20
The combination of faster preprocessing and stronger online reasoning leads to three new and highly performant algorithms: JPS+BB+ and Two-Oracle Pathfinding Search (TOPS) based on search, and Topping+ based on path extraction.
- 19
- Integrating a Path Planner and an Adaptive Motion Controller for Navigation in Dynamic Environments18
Improvements make the IA3C controller converge faster and become more adaptive to incomplete, noisy information caused by partial observability and strengthen the robots’ temporal reasoning of the environments by a memory-based network.
- Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology17
This work introduces CityAVOS, the first benchmark dataset for autonomous search of static urban objects and proposes PRPSearcher (Perception-Reasoning-Planning Searcher), a novel agentic method powered by multi-modal large language models that enables a UAV agent to think and reason like humans on visual cues when searching for objects.
- DARA: Domain- and Relation-Aware Adapters Make Parameter-Efficient Tuning for Visual Grounding17
This paper proposes DARA, a novel PETL method comprising Domain-aware Adapters (DA Adapters) and Relation-aware Adapters (RA Adapters) for VG that achieves the best accuracy while saving numerous updated parameters compared to the full fine-tuning and other PETL methods.
- Question-aware memory network for multi-hop question answering in human–robot interaction16
This work proposes question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process and incorporates graph context information into knowledge graph embedding model to increase the ability to represent entities and relations.
- 16
- A Semi-Markov Decision Model for Recognizing the Destination of a Maneuvering Agent in Real Time Strategy Games16
A novel semi-Markov decision model (SMDM) is proposed that outperforms another extension of the MDP in terms of precision, recall, and -measure, and Destinations are recognized efficiently by the SMDM no matter whether they are changed or not.
- Formation Control of Robotic Swarm Using Bounded Artificial Forces16
A potential field control algorithm, navigating a swarm of robots into a predefined 2D shape while avoiding intermember collisions, and defines the bounded artificial forces in the form of exponential functions, which proves the stability and convergence properties of the algorithm.
- Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration14
In state value decoding stage, the model explores the hierarchical semantic of ontology and enhances the interrelation between slots with masked hierarchical attention and solves the out-of-vocabulary problem by combining generation method and extraction method together.
- Shortest Path Network Interdiction With Goal Threshold14
A new version of the network interdiction problem that optimizes the interdictor’s resource consumption while limiting network capacities to a specified threshold is considered and two basic algorithms to solve it based on Benders decomposition and Lagrange duality are proposed.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.