XH
Xuming Hu
cs.CLcs.AIcs.CVcs.LGcs.IRcs.CRcs.MMcs.HCcs.MAcs.RO
On Valency
published · living versionsW_tbwg7pq8·v1 · currentpublished
TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling
with Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu, Yuxi Chen +3
1 version
W_4y6r4vd4·v1published
Preprints & journals
196 papers in the corpus · 2020–2026TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling2610.26025v2 · Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu et al.2026 · 0 citationsarXivon Valency
AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces2609.34854v1 · Zhijie Deng, Ling Li, Junhao Ji et al.2026 · 0 citationsarXiv
InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning2609.32660v1 · Hanqian Li, Sirui Huang, Chen Ling et al.2026 · 0 citationsarXiv
Concentrate After Imagination: Text-Conditioned Evidence Grounding for Partially Relevant Video Retrieval2609.08999v1 · Shuaiqi Cheng, Siyu You, Yanbi Wu et al.2026 · 0 citationsarXiv
SemTrace: Source-Grounded Semantic Signatures for Tracing LLM Exposure to Protected Documents2608.29575v1 · Junyan Zhang, Yudong Zeng, Yongwei Huang et al.2026 · 0 citationsarXiv
EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation2608.29092v1 · Sihang Jia, Shuliang Liu, Songbo Yang et al.2026 · 0 citationsarXiv
Small Frequency Corrections Can Change What Survives KV Cache Compression2608.27128v4 · Hong Chen, Yudong Zeng, Yongwei Huang et al.2026 · 0 citationsarXiv
Unsupervised Post-Training of Foundation Models: A Survey2608.24982v2 · Yijie Xu, Qianyi Cai, Huizai Yao et al.2026 · 0 citationsarXiv
AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval2608.08732v1 · Haoyu Zuo, Yibo Yan, Xin Zou et al.2026 · 0 citationsarXiv
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns2607.25467v1 · Hong Chen, Kang Chen, Yuxuan Fan et al.2026 · 0 citationsarXiv
Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?2607.17262v1 · Yubo Gao, Haotian Wu, Xiaoyu Xu et al.2026 · 0 citationsarXiv
Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation2607.14497v2 · Chi Kit Wong, Ye Pan, Yuanhuiyi Lyu et al.2026 · 0 citationsarXiv
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation2606.29805v2 · Xin Zou, Haolin Deng, Yibo Yan et al.2026 · 0 citationsarXiv
Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning2606.29812v1 · Xin Zou, Haolin Deng, Yibo Yan et al.2026 · 0 citationsarXiv
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning2606.30378v1 · Haocong He, Chenfei Liao, Zichen Wen et al.2026 · 0 citationsarXiv
Bridging the Post-discharge Gap: A Traceable Multi-agent Framework for Safe and Continuous Care2606.25334v1 · Runwei Guan, Yi Zhou, Heyi Lin et al.2026 · 0 citationsarXiv
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents2606.25852v1 · Peng Xu, Sijia Chen, Junzhuo Li et al.2026 · 0 citationsarXiv
PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols2606.05003v2 · He Liu, Boyuan Gu, Shuaiqi Cheng et al.2026 · 0 citationsEMNLP 2026 (findings)
MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework2606.07654v1 · Haowen Xiang, Yibo Yan, Jiahao Huo et al.2026 · 0 citationsarXiv
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs2606.01168v1 · Yubo Gao, Haotian Wu, Hong Chen et al.2026 · 0 citationsarXiv
Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization2605.31312v1 · Haolin Deng, Xin Zou, Zhiwei Jin et al.2026 · 0 citationsarXiv
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression2605.26678v2 · Hong Chen, Xiang Liu, Yubo Gao et al.2026 · 0 citationsarXiv
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness2605.25796v3 · Jiahao Huo, Wenjie Qu, Yibo Yan et al.2026 · 0 citationsarXiv
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL2605.17295v1 · Shaobo Wang, Yujie Chen, Yafeng Sun et al.2026 · 0 citationsarXiv
When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs2605.11559v1 · Fanpu Cao, Xin Zou, Xuming Hu et al.2026 · 0 citationsarXiv
Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding2604.17422v2 · Shaoguang Wang, Weiyu Guo, Ziyang Chen et al.2026 · 0 citationsarXiv
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation2604.12424v1 · Sihang Jia, Shuliang Liu, Songbo Yang et al.2026 · 0 citationsarXiv
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval2604.10167v1 · Yibo Yan, Mingdong Ou, Yi Cao et al.2026 · 0 citationsarXiv
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding2604.09000v2 · Junxi Wang, Te Sun, Jiayi Zhu et al.2026 · 0 citationsarXiv
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models2604.06694v2 · Yuxuan Wang, Peize He, Xiyan Gui et al.2026 · 0 citationsarXiv
Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation2604.03592v2 · Kening Zheng, Wei-Chieh Huang, Jiahao Huo et al.2026 · 0 citationsarXiv
Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models2603.27375v1 · Yuhang Han, Yuyang Wu, Zhengbo Jiao et al.2026 · 0 citationsarXiv
AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents2603.18429v1 · Yibo Shi, Jungang Li, Linghao Zhang et al.2026 · 0 citationsarXiv
Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models2603.17541v1 · Linghao Zhang, Jungang Li, Yonghua Hei et al.2026 · 0 citationsarXiv
Panoramic Affordance Prediction2603.15558v1 · Zixin Zhang, Chenfei Liao, Hongfei Zhang et al.2026 · 0 citationsarXiv
LatentGeo: Learnable Auxiliary Constructions in Latent Space for Multimodal Geometric Reasoning2603.12166v1 · Haiying Xu, Zihan Wang, Song Dai et al.2026 · 0 citationsarXiv
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design2603.10379v1 · Junzhuo Li, Peijie Jiang, Changxin Tian et al.2026 · 0 citationsarXiv
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision2603.06032v1 · Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng et al.2026 · 0 citationsarXiv
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations2603.01666v1 · Yibo Yan, Mingdong Ou, Yi Cao et al.2026 · 0 citationsarXiv
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework2602.19549v2 · Yibo Yan, Mingdong Ou, Yi Cao et al.2026 · 0 citationsarXiv
Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval2602.19961v3 · Yibo Yan, Jiahao Huo, Guanbo Feng et al.2026 · 0 citationsarXiv
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding2601.21262v4 · Jiahao Huo, Yu Huang, Yibo Yan et al.2026 · 0 citationsarXiv
SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching2601.21927v1 · Hong Chen, Xiang Liu, Bo Wang et al.2026 · 0 citationsarXiv
Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models2601.08383v1 · Bo Wang, Junzhuo Li, Hong Chen et al.2026 · 0 citationsarXiv
A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model2601.07291v1 · Qi Zheng, Shuliang Liu, Yu Huang et al.2026 · 0 citationsarXiv
Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models2601.05144v2 · Shuliang Liu, Xingyu Li, Hongyi Liu et al.2026 · 0 citationsarXiv
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering2601.05159v1 · Shuliang Liu, Songbo Yang, Dong Fang et al.2026 · 0 citationsarXiv
Rethinking Token-Wise Feature Caching: Accelerating Diffusion Transformers With Dual Feature Caching.42241263 · Zou, Chang, Zheng, Shikang, Zhang, Evelyn et al.2026 · 3 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:6211-6220
VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction2511.18831v1 · Shaobo Wang, Tianle Niu, Runkang Yang et al.2025 · 0 citationsarXiv
EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models2511.10201v1 · Junquan Huang, Haotian Wu, Yubo Gao et al.2025 · 0 citationsarXiv
Career total: 267 works. 196 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.