Yinghui Xu

Orcid: 0009-0002-7346-2794

Affiliations:
  • INF Technology Co., Ltd., Shanghai, China


According to our database1, Yinghui Xu authored at least 40 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation.
CoRR, May, 2026

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits.
CoRR, May, 2026

DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding.
CoRR, March, 2026

AURORA: Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification.
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, 2026

2025
CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing.
CoRR, December, 2025

Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models.
CoRR, November, 2025

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling.
CoRR, July, 2025

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection.
CoRR, June, 2025

AURORA:Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification.
CoRR, February, 2025

SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain.
CoRR, January, 2025

Meta-Agent-Workflow: Streamlining Tool Usage in LLMs through Workflow Construction, Retrieval, and Refinement.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Prolog-Driven Rule-Based Diagnostics with Large Language Models for Precise Clinical Decision Support.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2025, 2025

MVP-LLMs: Optimizing Intervention Timing and Subsequent Decision Support for Mechanical Ventilation Parameter Control Using Large Language Models.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2025, 2025

Struct-X: Enhancing the Reasoning Capabilities of Large Language Models in Structured Data Scenarios.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, 2025

HeStIa: Asynchronous Embodied Dynamic Locomotion Learning for Walking Robots through Multimodal Large Language Models.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025

Leave the Bias in Bias: Mitigating the Label Noise Effects in Continual Visual Instruction Fine-Tuning.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2025

An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024
A bioactivity foundation model using pairwise meta-learning.
Nat. Mac. Intell., 2024

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models.
CoRR, 2024

LMGT: Optimizing Exploration-Exploitation Balance in Reinforcement Learning through Language Model Guided Trade-offs.
CoRR, 2024

Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory.
CoRR, 2024

Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Though.
CoRR, 2024

Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models.
CoRR, 2024

Struct-X: Enhancing Large Language Models Reasoning with Structured Data.
CoRR, 2024

MINDECHO: Role-Playing Language Agents for Key Opinion Leaders.
CoRR, 2024

AI2Apps: A Visual IDE for Building LLM-based AI Agent Applications.
CoRR, 2024

Enhancing Task Performance in Continual Instruction Fine-tuning Through Format Uniformity.
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024

Enhancing Personalized Headline Generation via Offline Goal-conditioned Reinforcement Learning with Large Language Models.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Hybrid Directional Graph Neural Network for Molecules.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

Robust Deep Hawkes Process Under Label Noise of Both Event and Occurrence.
Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023
InfMLLM: A Unified Framework for Visual-Language Tasks.
CoRR, 2023

FuXi: A cascade machine learning forecasting system for 15-day global weather forecast.
CoRR, 2023

Provably Invariant Learning without Domain Information.
Proceedings of the International Conference on Machine Learning, 2023

Self-Criticism: Aligning Large Language Models with their Understanding of Helpfulness, Honesty, and Harmlessness.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023, 2023

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023, 2023

SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), 2023


  Loading...