XQ
Xiaoye Qu
cs.CVcs.CLcs.AIcs.LGcs.MMcs.IRcs.MAcs.SDeess.AS
On Valency
published · living versionsW_v3na744u·v1 · currentpublished
WorldProbe: When Video World Models Fall Apart under Long-Horizon Spatial Exploration
with Minqi Wang, Jie Peng, Hejun Dong, Ruchang Yao +6
1 version
Preprints & journals
77 papers in the corpus · 2019–2026Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain2609.00788v1 · Daizong Liu, Junhao Dong, Zhiyuan Ma et al.2026 · 0 citationsarXiv
Benchmarking Clinical Decision Pathway Adherence in Large Language Models2608.26592v1 · Nuo Chen, Xinyang Jiang, Zilong Wang et al.2026 · 0 citationsarXiv
MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems2608.15006v1 · Penghao Yin, Haomin Wang, Qihong Tang et al.2026 · 0 citationsarXiv
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics2606.10479v1 · Shunkai Zhang, Haoran Zhang, Yun Luo et al.2026 · 0 citationsarXiv
Draft-OPD: On-Policy Distillation for Speculative Draft Models2605.29343v3 · Haodi Lei, Yafu Li, Haoran Zhang et al.2026 · 0 citationsarXiv
Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language2605.29812v1 · Xiang Fang, Wanlong Fang, Daizong Liu et al.2026 · 9 citationsarXiv
VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation2605.30317v1 · Xinyao Liao, Qiyuan He, Yicong Li et al.2026 · 0 citationsarXiv
Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective2605.26441v1 · Xiang Fang, Zeyu Xiong, Wanlong Fang et al.2026 · 11 citationsarXiv
-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows2605.14678v3 · Haoran Zhang, Luxin Xu, Zhilin Wang et al.2026 · 0 citationsarXiv
VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing2604.19412v1 · Yanbin Huang, Yisen Li, Guiyao Tie et al.2026 · 0 citations2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026, pp. 16657-16661
XSkill: Continual Learning from Experience and Skills in Multimodal Agents2603.12056v3 · Guanyu Jiang, Zhaochen Su, Xiaoye Qu et al.2026 · 0 citationsarXiv
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning2602.11748v1 · Futing Wang, Jianhao Yan, Yun Luo et al.2026 · 0 citationsarXiv
New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR2602.08281v1 · Zhilin Wang, Yafu Li, Shunkai Zhang et al.2026 · 0 citationsarXiv
Characterizing, Evaluating, and Optimizing Complex Reasoning2602.08498v2 · Haoran Zhang, Yafu Li, Zhi Wang et al.2026 · 0 citationsarXiv
LatentMem: Customizing Latent Memory for Multi-Agent Systems2602.03036v2 · Muxin Fu, Xiangyuan Xue, Yafu Li et al.2026 · 0 citationsarXiv
FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization2602.03507v2 · Runquan Gui, Yafu Li, Xiaoye Qu et al.2026 · 0 citationsarXiv
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model2601.15892v2 · Chenghao Fan, Wen Heng, Bo Li et al.2026 · 0 citationsarXiv
Toward Efficient Agents: Memory, Tool learning, and Planning2601.14192v2 · Xiaofang Yang, Lijun Li, Heng Zhou et al.2026 · 0 citationsarXiv
DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models2512.24165v1 · Zefeng He, Xiaoye Qu, Yafu Li et al.2025 · 0 citationsarXiv
VA-: Variational Policy Alignment for Pixel-Aware Autoregressive Generation2512.19680v1 · Xinyao Liao, Qiyuan He, Kai Xu et al.2025 · 1 citationarXiv
VideoSSR: Video Self-Supervised Reinforcement Learning2511.06281v1 · Zefeng He, Xiaoye Qu, Yafu Li et al.2025 · 0 citationsarXiv
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends.40824980 · Liu, Daizong, Yang, Mingyu, Qu, Xiaoye et al.2025 · 44 citationsIEEE transactions on neural networks and learning systems. 2025;36(11):19525-19545
Spotlight on Token Perception for Multimodal Reinforcement Learning2510.09285v2 · Siyuan Huang, Xiaoye Qu, Yafu Li et al.2025 · 0 citationsarXiv
ExGRPO: Learning to Reason from Experience2510.02245v2 · Runzhe Zhan, Yafu Li, Zhi Wang et al.2025 · 0 citationsarXiv
Diversity-Incentivized Exploration for Versatile Reasoning2509.26209v2 · Zican Hu, Shilin Zhang, Yafu Li et al.2025 · 0 citationsICLR 2026
A Survey of Reinforcement Learning for Large Reasoning Models2509.08827v3 · Kaiyan Zhang, Yuxin Zuo, Bingxiang He et al.2025 · 3 citationsarXiv
Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval2508.04273v3 · Junan Lin, Daizong Liu, Xianke Chen et al.2025 · 4 citationsarXiv
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning2506.04207v2 · Shuang Chen, Yue Guo, Zhaochen Su et al.2025 · 0 citationsarXiv
SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring2505.19094v2 · Chuming Shen, Wei Wei, Xiaoye Qu et al.2025 · 0 citationsarXiv
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models2505.14810v2 · Tingchen Fu, Jiawei Gu, Yafu Li et al.2025 · 1 citationarXiv
SEE: Continual Fine-tuning with Sequential Ensemble of Experts2504.06664v1 · Zhilin Wang, Yafu Li, Xiaoye Qu et al.2025 · 1 citationarXiv
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond2503.21614v2 · Xiaoye Qu, Yafu Li, Zhao-Chen Su et al.2025 · 2 citationsarXiv
From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration2503.12821v4 · Mingyang Song, Xiaoye Qu, Jiawei Zhou et al.2025 · 1 citationarXiv
Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think2503.00948v1 · Jie Tian, Xiaoye Qu, Zhenyi Lu et al.2025 · 4 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment2502.16894v4 · Chenghao Fan, Zhenyi Lu, Sichen Liu et al.2025 · 0 citationsarXiv
LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid2502.07563v1 · Weigao Sun, Disen Lan, Yiran Zhong et al.2025 · 0 citationsarXiv
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback2501.12895v1 · Yafu Li, Xuyang Hu, Xiaoye Qu et al.2025 · 1 citationarXiv
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models2501.03124v5 · Mingyang Song, Zhaochen Su, Xiaoye Qu et al.2025 · 10 citationsarXiv
LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training2411.15708v1 · Xiaoye Qu, Daize Dong, Xuyang Hu et al.2024 · 0 citationsarXiv
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling2409.19291v3 · Jihai Zhang, Xiaoye Qu, Tong Zhu et al.2024 · 6 citationsarXiv
SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information2409.14083v1 · Jiashuo Sun, Jihai Zhang, Yucheng Zhou et al.2024 · 2 citationsarXiv
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning2408.17150v1 · Xiaoye Qu, Jiashuo Sun, Wei Wei et al.2024 · 1 citationarXiv
Mitigating Multilingual Hallucination in Large Vision-Language Models2408.00550v1 · Xiaoye Qu, Mingyang Song, Wei Wei et al.2024 · 3 citationsarXiv
Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation2408.00555v1 · Xiaoye Qu, Qiyuan Chen, Wei Wei et al.2024 · 11 citationsarXiv
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training2406.16554v1 · Tong Zhu, Xiaoye Qu, Daize Dong et al.2024 · 40 citationsarXiv
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts2406.11256v1 · Tong Zhu, Daize Dong, Xiaoye Qu et al.2024 · 1 citationarXiv
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion2406.15480v2 · Chenghao Fan, Zhenyi Lu, Wei Wei et al.2024 · 3 citationsarXiv
Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models2406.07001v1 · Zhenyi Lu, Jie Tian, Wei Wei et al.2024 · 12 citationsarXiv
Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning2402.11816v3 · Jihai Zhang, Xiang Lan, Xiaoye Qu et al.2024 · 2 citationsarXiv
Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graph2401.02212v1 · Rikui Huang, Wei Wei, Xiaoye Qu et al.2024 · 7 citationsarXiv
Career total: 113 works. 77 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.