Xinyu Zhou

27 papers · 2017–2026 · 9 conferences · across top CS/AI conferences

Achievements

+8 more ↓

🏃 Academic Marathon (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🐝 Cross-Pollinator (6)

🏃 Academic Marathon (8) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (6) 🧬 Topic Evolution 🔥 Unstoppable (6) 💎 Century Club (24) ⚡ Prolific Year (6) 🗃️ Keyword Collector (127)

Conferences

CVPR (8) ICCV (5) NIPS (3) AAAI (2) ACL (2) COLING (2) ECCV (2) ICML (2) EMNLP (1)

Top co-authors

Wenqiang Zhang (7) Pinxue Guo (7) Jinglun Li (6) Lingyi Hong (6) Boxin Shi (5) Wei Zhang (4) Kaixun Jiang (4) Peiqi Duan (4) Chao Xu (3) Raef Bassily (3)

Research topics

Differential Privacy (1)

Keywords

event camera (4) visual object tracking (3) representation learning (2) neural network (2) model compression (2) few-shot learning (2) multi-modal learning (2) image reconstruction (2) language model (2) large language model (2) diffusion model (2) neuromorphic event (2) label propagation (1) density estimation (1) vision transformer (1) neuromorphic computing (1) statistical modeling (1) image segmentation (1) differential privacy (1) computer vision (1)

Papers

Seeing Is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding AAAI 2026 MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis ACL 2026 Text-based Aerial-Ground Person Retrieval AAAI 2026 Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability COLING 2025 Private Model Personalization Revisited ICML 2025 Event-based Visual Vibrometry ICCV 2025 General Compression Framework for Efficient Transformer Object Tracking ICCV 2025 The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation ICCV 2025 FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs EMNLP 2025 Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models COLING 2025 EvDiG: Event-guided Direct and Global Components Separation CVPR 2024 DeTrack: In-model Latent Denoising Learning for Visual Object Tracking NIPS 2024 Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction CVPR 2024 OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning CVPR 2024 OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework ECCV 2024 Differentially Private Worst-group Risk Minimization ICML 2024 SIMSUM: Document-level Text Simplification via Simultaneous Summarization ACL 2023 Reading Relevant Feature from Global Representation Memory for Visual Object Tracking NIPS 2023 Few Shot Font Generation Via Transferring Similarity Guided Global Style and Quantization Local Style ICCV 2023 Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection ICCV 2023 Task-level Differentially Private Meta Learning NIPS 2022 EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction CVPR 2022 EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events CVPR 2021 DPGN: Distribution Propagation Graph Network for Few-Shot Learning CVPR 2020 Learning Delicate Local Representations for Multi-Person Pose Estimation ECCV 2020 ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices CVPR 2018 EAST: An Efficient and Accurate Scene Text Detector CVPR 2017