Author

Qi Dai

Observed name: Dai, Qi

Institutions: Microsoft (United States), Ningbo No. 2 Hospital, Microsoft Research Asia (China), Ningbo No.6 Hospital

Observed institutions: Microsoft (United States), Ningbo No. 2 Hospital, Microsoft Research Asia (China), Ningbo No.6 Hospital

OpenAlex ID: A5125951433

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

2026 · Yang, Yifan, Gong, Ziyang, et al. · arXiv (Cornell University) · 2

PDF

OfficeTown: Generative Organizations for Evolving Agent Intelligence

2026 · Wei, Hongchen, Ying, Daohong, et al. · arXiv (Cornell University)

PDF

ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation

2026 · Tian, Muzhao, Zeng, Zezi, et al. · arXiv (Cornell University)

PDF

XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding

2026 · Wei, Hongchen, Wang, Yuanzhe, et al. · arXiv (Cornell University)

PDF

Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation

2026 · Liu, Yungeng, Fang, Xuanzi, et al. · arXiv (Cornell University)

PDF

Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing

2026 · Yu, Yue, Jiao, Yang, et al. · arXiv (Cornell University)

PDF

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

2026 · Jin, Jiajie, Hu, Yuyang, et al. · arXiv (Cornell University)

PDF

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

2026 · Yoon, Hee Suk, Yoon, Eunseop, et al. · arXiv (Cornell University)

PDF

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

2026 · Huang, Zisu, Xu, Jingwen, et al. · arXiv (Cornell University)

PDF

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning

2026 · Yoon, Hee Suk, Yoon, Eunseop, et al. · arXiv (Cornell University)

PDF

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

2026 · Zhou, Ziwei, Lai, Zeyuan, et al. · arXiv (Cornell University)

PDF

DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

2026 · Jin, Wonjoon, Won, Jiyun, et al. · arXiv (Cornell University)

PDF

BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation

2026 · Li, Yan, Zeng, Zezi, et al. · arXiv (Cornell University)

PDF

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

2026 · Li, Quanhao, Xing, Zhen, et al. · arXiv (Cornell University)

PDF

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

2026 · Zhang, Miaosen, Liu, Yishan, et al. · arXiv (Cornell University)

PDF

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

2026 · Yang, Zihan, Tu, Shuyuan, et al. · arXiv (Cornell University)

PDF

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

2026 · Zhu, Jialiang, Zhang, Gongrui, et al. · arXiv (Cornell University)

PDF

GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning

2026 · Fengyi Wu, Yifei Dong, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

PDF

FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction

2025 · Tu, Shuyuan, Pan, Yueming, et al. · arXiv (Cornell University)

PDF

Works count: 19

Citation count: 2

H-index: 1

I10-index: