WW
Weiqiang Wang
cs.CVcs.AIcs.LGcs.CLcs.CRcs.SDcs.IReess.AScs.HCcs.DC
On Valency
published · living versionsW_34j8mh82·v1 · currentpublished
Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
with Lai Wei, Yatai Li, Liangbo He, Jun Lan +8
1 version
W_t4jf9qjk·v1published
Preprints & journals
141 papers in the corpus · 2016–2026Cross-Lingual Speaker Verification with Self-Supervised Pre-Trained Models2610.11099v1 · Jinghan Peng, Yu Zheng, Weiqiang Wang et al.2026 · 0 citationsProc. Interspeech 2026, 6958-6962
PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence2609.37712v1 · GuangJian Team: Kaili Huang, Yongshuo Zhang, Bingtao Fu et al.2026 · 0 citationsarXiv
Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History2609.38114v1 · Weiqiang Wang, Zhuokun Chen, Yusheng Dai et al.2026 · 0 citationsarXiv
MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification2609.24061v1 · Yu Zheng, Jinghan Peng, ChangHao Zhang et al.2026 · 0 citationsarXiv
Learning Continuous Source Responses For Generalizable AI-Generated Image Detection2609.14316v1 · Manni Cui, Ruiqi Liu, Zijian Yu et al.2026 · 0 citationsarXiv
FastE: Readout-Triggered Token Compression for LLM Embedding Inference2609.08407v3 · Jinsong Shu, Jinyong Wen, Baokun Wang et al.2026 · 0 citationsarXiv
DE-Venus: A Data-Efficient RLVR Framework for Large Language Models2609.03324v1 · Shenzhi Yang, Guangcheng Zhu, Kai Tang et al.2026 · 0 citationsarXiv
Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents2609.03438v1 · Zhaoyuan Huang, Tianjie Ju, Pengzhou Cheng et al.2026 · 0 citationsarXiv
Emotion Understanding in Streaming Video with Trajectory-Aware Reliability2608.26786v2 · Qingsong Wang, Qigong Lei, Zitong Wang et al.2026 · 0 citationsarXiv
UI-Venus-2 Technical Report2609.00028v1 · Venus Team, Zhuohan Cai, Haoxing Chen et al.2026 · 0 citationsarXiv
AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection2608.23437v2 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation2608.20122v1 · Linhan Cao, Siyuan Li, Jun Lan et al.2026 · 0 citationsarXiv
CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects2608.15734v1 · Yusheng Dai, Kangdi Wang, Baolong Gao et al.2026 · 0 citationsarXiv
AT-ADD: All-Type Audio Deepfake Detection Challenge Summary2608.14249v1 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection2607.27113v1 · Hao Tan, Jun Lan, Zichang Tan et al.2026 · 0 citationsarXiv
Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering2607.18718v1 · Haolin He, Renhe Sun, Zheqi Dai et al.2026 · 0 citationsarXiv
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models2606.13709v1 · Yan Hong, Kedong Xiu, Wei Li et al.2026 · 0 citationsarXiv
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection2607.24771v1 · Yan Hong, Wei Li, Kedong Xiu et al.2026 · 0 citationsarXiv
Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots2606.04503v2 · Guangcheng Zhu, Shenzhi Yang, Haobo Wang et al.2026 · 0 citationsarXiv
GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering2605.29584v2 · Xin Sun, Jianan Xie, Zhongqi Chen et al.2026 · 0 citationsarXiv
EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents2605.27820v2 · Yunqi Liu, Tong Niu, Zitong Wang et al.2026 · 0 citationsarXiv
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection2605.28631v1 · Jianghao Wu, Jianfei Cai, Weiqiang Wang et al.2026 · 0 citationsarXiv
ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization2605.14497v1 · Letian Yang, Xu Liu, Yiqiang Lu et al.2026 · 0 citationsarXiv
Causal Probing for Internal Visual Representations in Multimodal Large Language Models2605.05593v3 · Zehao Deng, Tianjie Ju, Zheng Wu et al.2026 · 0 citationsarXiv
TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding2605.04962v1 · Minjie Qiang, Mingming Zhang, Xiaoyi Bao et al.2026 · 0 citationsarXiv
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data2604.19859v1 · Venus Team, Sunhao Dai, Yong Deng et al.2026 · 0 citationsarXiv
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off2604.13902v1 · Xiaofan Li, Ming Yang, Zhiyuan Ma et al.2026 · 0 citationsarXiv
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan2604.08184v1 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
Can LLMs Learn to Reason Robustly under Noisy Supervision?2604.03993v1 · Shenzhi Yang, Guangcheng Zhu, Bowen Song et al.2026 · 0 citationsarXiv
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography2603.22316v1 · Jing Xu, Weiqiang Wang, Cunjian Chen et al.2026 · 0 citationsarXiv
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images2603.02210v3 · Yichen Liu, Donghao Zhou, Jie Wang et al.2026 · 0 citationsarXiv
KMLP: A Scalable Hybrid Architecture for Web-Scale Tabular Data Modeling2602.22777v1 · Mingming Zhang, Pengfei Shi, Zhiqing Xiao et al.2026 · 0 citationsarXiv
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model2602.14492v2 · Jiahao Yuan, Yike Xu, Jinyong Wen et al.2026 · 0 citationsarXiv
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception2602.11858v2 · Lai Wei, Liangbo He, Jun Lan et al.2026 · 0 citationsarXiv
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning2602.10622v1 · Jiahao Yuan, Yike Xu, Jinyong Wen et al.2026 · 0 citationsarXiv
VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning2602.08828v1 · Hao Tan, Jun Lan, Senyuan Shi et al.2026 · 0 citationsarXiv
PPG as a Bridge: Cross-Device Authentication for Smart Wearables with Photoplethysmography2602.08972v1 · Jiacheng Liu, Jiankai Tang, Guangye Zhao et al.2026 · 0 citationsarXiv
UI-Venus-1.5 Technical Report2602.09082v2 · Venus Team, Changlong Gao, Zhangxuan Gu et al.2026 · 0 citationsarXiv
Adaptive and Balanced Re-initialization for Long-timescale Continual Test-time Domain Adaptation2602.06328v1 · Yanshuo Wang, Jinguang Tong, Jun Lan et al.2026 · 0 citationsarXiv
TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization2601.22776v2 · Shichao Ma, Zhiyuan Ma, Ming Yang et al.2026 · 0 citationsarXiv
Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation2601.11443v3 · Xin Sun, Zhongqi Chen, Qiang Liu et al.2026 · 1 citationICASSP 2026 - 2026 IEEE International Conference on Acoustics, ICASSP 2026 - 2026 IEEE International Conference on Acoustics, ICASSP 2026 - 2026 IEEE International Conference on Acoustics,
Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection2601.05580v1 · Hanyi Wang, Jun Lan, Yaoyu Kang et al.2026 · 0 citationsarXiv
Active Perception Agent for Omnimodal Audio-Video Understanding2512.23646v2 · Keda Tao, Wenjie Du, Bohan Yu et al.2025 · 0 citationsarXiv
TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning2512.13106v1 · Shenzhi Yang, Guangcheng Zhu, Xing Zheng et al.2025 · 0 citationsarXiv
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding2512.12560v1 · Xinqi Jin, Hanxun Yu, Bohan Yu et al.2025 · 0 citationsarXiv
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering2512.10999v4 · Xin Sun, Zhongqi Chen, Xing Zheng et al.2025 · 0 citationsarXiv
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length2512.04677v6 · Yubo Huang, Hailong Guo, Fangtai Wu et al.2025 · 1 citationarXiv
Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards2512.00743v1 · Qiang Lyu, Zicong Chen, Chongxiao Wang et al.2025 · 0 citationsarXiv
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models2511.14582v2 · Keda Tao, Kele Shao, Bohan Yu et al.2025 · 0 citationsarXiv
Instruction-aware User Embedding via Synergistic Language and Representation Modeling2510.11016v1 · Ziyi Gao, Yike Xu, Jiahao Yuan et al.2025 · 0 citationsarXiv
Career total: 361 works. 141 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.