Xinyu Wang

Orcid: 0009-0004-0521-2077

Affiliations:
  • McGill University, Montreal, Quebec, Canada


According to our database1, Xinyu Wang authored at least 30 papers between 2025 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
SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation.
CoRR, May, 2026

Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling.
CoRR, May, 2026

From Table to Cell: Attention for Better Reasoning with TABALIGN.
CoRR, May, 2026

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering.
CoRR, April, 2026

Co-Evolution of Policy and Internal Reward for Language Agents.
CoRR, April, 2026

InfMem: Learning System-2 Memory Control for Long-Context Agent.
CoRR, February, 2026

Enhancing TableQA through Verifiable Reasoning Trace Reward.
CoRR, January, 2026

Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing.
CoRR, January, 2026

Dynamic Quantization Error Propagation in Encoder-Decoder ASR Quantization.
CoRR, January, 2026

VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering.
Proceedings of the ACM Web Conference 2026, 2026

R<sup>2</sup> R: A Post-training Framework for Multi-domain Decoder-Only Rerankers.
Proceedings of the Advances in Knowledge Discovery and Data Mining, 2026

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
R<sup>2</sup>R: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers.
CoRR, November, 2025

InteractComp: Evaluating Search Agents With Ambiguous Queries.
CoRR, October, 2025

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing.
CoRR, October, 2025

Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving.
CoRR, October, 2025

It Takes Two: Your GRPO Is Secretly DPO.
CoRR, October, 2025

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents.
CoRR, September, 2025

Mamba Modulation: On the Length Generalization of Mamba.
CoRR, September, 2025

An Entity Linking Agent for Question Answering.
CoRR, August, 2025

PoTPTQ: A Two-step Power-of-Two Post-training for LLMs.
CoRR, July, 2025

STRICT: Stress Test of Rendering Images Containing Text.
CoRR, May, 2025

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering.
CoRR, April, 2025

Resona: Improving Context Copying in Linear Recurrence Models with Retrieval.
CoRR, March, 2025

STRICT: Stress-Test of Rendering Image Containing Text.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Improving Context Fidelity via Native Retrieval-Augmented Reasoning.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Boosting Data Utilization for Multilingual Dense Retrieval.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

PoT-PTQ: Two-Step Power-of-Two Post-Training for LLMs.
Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

An Interpretable Quantum-Inspired Model for Multi-Task Natural Language Understanding.
Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering.
Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025


  Loading...