Zhuang Liu

37 papers · 2017–2026 · 11 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🌍 Conference Polyglot (11) 🏃 Academic Marathon (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (13)

🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (6) 🗺️ Taxonomy Completionist (65) 👑 Triple Crown 🤝 Dynamic Duo (10) 🧬 Topic Evolution 🏆 Grand Slam 💎 Century Club (36) ⚡ Prolific Year (9) ❓ The Questioner (2) 🗃️ Keyword Collector (105) 🔥 Unstoppable (7)

Conferences

CVPR (9) ICLR (8) ICCV (6) ICML (5) ACL (3) AAAI (1) EMNLP (1) IJCAI (1) IJCNLP (1) NAACL (1) NIPS (1)

Top co-authors

Trevor Darrell (10) Zhiqiang Shen (7) Saining Xie (6) Zhiqiu Xu (5) Xinlei Chen (5) Yann LeCun (4) Yida Yin (4) Degen Huang (4) Kaiyu Huang (4) Gao Huang (3)

Keywords

self-supervised learning (4) large language model (4) image classification (3) neural network (3) transfer learning (3) contrastive learning (3) convolutional neural network (3) semantic segmentation (3) multimodal learning (3) domain generalization (2) few-shot learning (2) vision-language model (2) vision transformer (2) model compression (2) model architecture (2) data augmentation (2) zero-shot learning (2) representation learning (2) episodic learning (1) stochastic gradient descent (1)

Papers

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations ACL 2026 MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ICCV 2025 Transformers without Normalization CVPR 2025 Scaling Language-Free Visual Representation Learning ICCV 2025 Deconstructing Denoising Diffusion Models for Self-Supervised Learning ICLR 2025 A Coefficient Makes SVRG Effective ICLR 2025 A Decade's Battle on Dataset Bias: Are We There Yet? ICLR 2025 LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 Idiosyncrasies in Large Language Models ICML 2025 Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference NAACL 2025 ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy ICML 2024 Understanding Bias in Large-Scale Visual Datasets NIPS 2024 Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs CVPR 2024 Initializing Models with Larger Ones ICLR 2024 A Simple and Effective Pruning Approach for Large Language Models ICLR 2024 ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders CVPR 2023 Dropout Reduces Underfitting ICML 2023 ImageBind: One Embedding Space To Bind Them All CVPR 2023 Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning AAAI 2022 Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space CVPR 2022 Anytime Dense Prediction with Confidence Adaptivity ICLR 2022 A ConvNet for the 2020s CVPR 2022 Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning ICCV 2021 Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability ACL 2021 Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability IJCNLP 2021 Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control ICLR 2021 FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining IJCAI 2020 A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation EMNLP 2020 Test-Time Training with Self-Supervision for Generalization under Distribution Shifts ICML 2020 MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation CVPR 2020 Few Sample Knowledge Distillation for Efficient Network Compression CVPR 2020 Rethinking the Value of Network Pruning ICLR 2019 DUT-BIM at MEDIQA 2019: Utilizing Transformer Network and Medical Domain-Specific Contextualized Representations for Question Answering ACL 2019 Few-Shot Object Detection via Feature Reweighting ICCV 2019 Densely Connected Convolutional Networks CVPR 2017 Learning Efficient Convolutional Networks Through Network Slimming ICCV 2017 DSOD: Learning Deeply Supervised Object Detectors From Scratch ICCV 2017