YD
Yi Dong
cs.AIcs.CLcs.LGcs.MAcs.ROcs.CVcs.SEcs.CRcs.SYeess.SY
On Valency
published · living versionsW_juer8c7q·v1 · currentpublished
Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
with Zhuoyun Li, Boxuan Wang, Jinwei Hu, Xiaowei Huang
1 version
W_bj8dmwe5·v1published
Preprints & journals
51 papers in the corpus · 2021–2026LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches2610.06647v3 · Shaokun Zhang, Yifan Zhang, Jian Hu et al.2026 · 0 citationsarXiv
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents2609.39982v1 · Minki Kang, Ryo Hachiuma, Shaokun Zhang et al.2026 · 0 citationsarXiv
Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts2609.26986v1 · Zhuoyun Li, Boxuan Wang, Xiaowei Huang et al.2026 · 0 citationsarXiv
Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate2609.27150v1 · Boxuan Wang, Zhuoyun Li, Xiaowei Huang et al.2026 · 0 citationsarXiv
OSWorld-Pro: Process-based Evaluation for Computer Use Agents2609.24890v1 · Zhilin Wang, Shaokun Zhang, Yifan Zhang et al.2026 · 0 citationsarXiv
WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation2608.22364v2 · Liuhaichen Yang, Zhengyang Zhong, Hanshang Zhu et al.2026 · 0 citationsarXiv
Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents2607.27484v1 · Jinwei Hu, Yi Qi, Xinmiao Huang et al.2026 · 0 citationsarXiv
Guided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies2607.02092v4 · Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng et al.2026 · 0 citationsarXiv
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces2607.02345v1 · Jinwei Hu, Yi Dong, Youcheng Sun et al.2026 · 0 citationsarXiv
SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings2606.29623v1 · Yingjie Wang, Yi Dong, Edmund Lau et al.2026 · 0 citationsarXiv
SCOPE: Sequential Conformal Probing for Reliable OOD Rejection in LLM Services2606.21255v2 · Zhuoyun Li, Boxuan Wang, Changshun Wu et al.2026 · 0 citationsarXiv
SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models2606.10617v1 · Zhengxuan Wei, Yi Dong, Zonghui Li et al.2026 · 0 citationsarXiv
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts2606.01441v1 · Boxuan Wang, Zhuoyun Li, Xiaowei Huang et al.2026 · 0 citationsarXiv
Responsible Agentic AI Requires Explicit Provenance2605.17169v1 · Jinwei Hu, Xinmiao Huang, Qisong He et al.2026 · 0 citationsarXiv
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation2605.14174v2 · Qisong He, Xinmiao Huang, Jinwei Hu et al.2026 · 0 citationsarXiv
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations2605.14175v3 · Qisong He, Jinwei Hu, Xinmiao Huang et al.2026 · 0 citationsarXiv
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness2605.08896v2 · Zhuoyun Li, Boxuan Wang, Jinwei Hu et al.2026 · 0 citationsarXiv
PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents2605.06455v2 · Xinmiao Huang, Jinwei Hu, Qisong He et al.2026 · 0 citationsarXiv
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models2605.01605v1 · Zhuoyun Li, Boxuan Wang, Jinwei Hu et al.2026 · 0 citationsarXiv
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence2604.24954v2 · NVIDIA: Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki et al.2026 · 1 citationarXiv
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing2601.14302v2 · Jinwei Hu, Shiyuan Meng, Yi Dong et al.2026 · 0 citationsICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 19842-19846, 2026
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage2601.01685v2 · Jinwei Hu, Xinmiao Huang, Youcheng Sun et al.2026 · 0 citationsProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5979-5996, San Diego, California, United States, July 2026
Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks2512.18094v1 · Boxuan Wang, Zhuoyun Li, Xiaowei Huang et al.2025 · 1 citationarXiv
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models2511.06168v3 · Boxuan Wang, Zhuoyun Li, Xinmiao Huang et al.2025 · 0 citationsarXiv
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models2510.13394v4 · Xinmiao Huang, Qisong He, Zhenglin Huang et al.2025 · 0 citationsarXiv
Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment2510.14008v2 · Jinwei Hu, Yi Dong, Shuang Ao et al.2025 · 0 citationsarXiv
BroRL: Scaling Reinforcement Learning via Broadened Exploration2510.01180v1 · Jian Hu, Mingjie Liu, Ximing Lu et al.2025 · 0 citationsarXiv
Distributed Nash Equilibrium Seeking Algorithm in Aggregative Games for Heterogeneous Multi-Robot Systems2509.15597v1 · Yi Dong, Zhongguo Li, Sarvapali D. Ramchurn et al.2025 · 0 citationsarXiv
Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments2508.11425v2 · Jinwei Hu, Yi Dong, Youcheng Sun et al.2025 · 0 citationsarXiv
Responsible and adaptive robots in care home settings: an implementation framework analysis of a workshop with public and professionals.40786654 · Boudouraki, Andriana, Waheed, Maria, Mestre, Rafael et al.2025 · 1 citationFrontiers in robotics and AI. 2025;12:1610329
Hierarchical Testing with Rabbit Optimization for Industrial Cyber-Physical Systems2507.04100v1 · Jinwei Hu, Zezhi Tang, Xin Jin et al.2025 · 3 citationsarXiv
Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing2507.04105v1 · Jinwei Hu, Yi Dong, Zhengtao Ding et al.2025 · 2 citationsarXiv
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs2506.18931v1 · Shuang Ao, Yi Dong, Jinwei Hu et al.2025 · 5 citationsarXiv
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models2505.24864v1 · Mingjie Liu, Shizhe Diao, Ximing Lu et al.2025 · 1 citationarXiv
TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models2503.10872v2 · Xiangyu Yin, Yi Qi, Jinwei Hu et al.2025 · 0 citationsarXiv
CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models2503.10661v2 · Xiangyu Yin, Jiaxu Liu, Zhen Chen et al.2025 · 0 citationsarXiv
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model2502.01472v3 · Jinwei Hu, Zhenglin Huang, Xiangyu Yin et al.2025 · 0 citationsarXiv
Position: Towards a Responsible LLM-empowered Multi-Agent Systems2502.01714v1 · Jinwei Hu, Yi Dong, Shuang Ao et al.2025 · 2 citationsarXiv
Safeguarding large language models: a survey.41114380 · Dong, Yi, Mu, Ronghui, Zhang, Yanghao et al.2026 · 117 citationsArtificial intelligence review. 2025;58(12):382
Trust-Oriented Adaptive Guardrails for Large Language Models2408.08959v3 · Jinwei Hu, Yi Dong, Xiaowei Huang2024 · 1 citationarXiv
Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting2402.01546v1 · Yi Dong, Yingjie Wang, Mariana Gama et al.2024 · 16 citationsarXiv
Building Guardrails for Large Language Models2402.01822v2 · Yi Dong, Ronghui Mu, Gaojie Jin et al.2024 · 22 citationsarXiv
Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach2401.15785v1 · Hongyu Zhao, Zezhi Tang, Zhenhong Li et al.2024 · 31 citationsarXiv
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation2305.11391v2 · Xiaowei Huang, Wenjie Ruan, Wei Huang et al.2023 · 165 citationsarXiv
STPA for Learning-Enabled Systems: A Survey and A New Practice2302.10588v2 · Yi Qi, Yi Dong, Siddartha Khastgir et al.2023 · 16 citationsarXiv
Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation2302.01728v1 · Yi Dong, Zhongguo Li, Xingyu Zhao et al.2023 · 5 citationsarXiv
Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems2210.14991v2 · Yi Dong, Xingyu Zhao, Sen Wang et al.2022 · 13 citationsarXiv
Short-term Load Forecasting with Distributed Long Short-Term Memory2208.01147v2 · Yi Dong, Yang Chen, Xingyu Zhao et al.2022 · 4 citationsarXiv
Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance2112.00646v2 · Yi Dong, Wei Huang, Vibhav Bharti et al.2021 · 29 citationsACM Transactions on Embedded Computing Systems; 2022
Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking2109.06523v3 · Yi Dong, Xingyu Zhao, Xiaowei Huang2021 · 9 citationsarXiv
Career total: 86 works. 51 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.