ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Tianwei Zhang

Tianwei Zhang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:40 AM AMS

21

papers

250

total citations

papers (21)

Privacy-Preserving Collaborative Learning With Automatic Transformation Search

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms

NEURIPS 2022arXiv

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

Learning to Optimize Non-Rigid Tracking

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

NEURIPS 2023arXiv

Disco4D: Disentangled 4D Human Generation and Animation from a Single Image

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

NEURIPS 2025arXiv

An LLM-Empowered Adaptive Evolutionary Algorithm for Multi-Component Deep Learning Systems

Impact-driven Context Filtering For Cross-file Code Completion

Hybrid Concept Bottleneck Models

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack

Deep Multitask Learning with Progressive Parameter Sharing

Color Backdoor: A Robust Poisoning Attack in Color Space

BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach

Iron: Private Inference on Transformers

Improving Adversarial Robustness of 3D Point Cloud Classification Models

Computation and Data Efficient Backdoor Attacks

Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models

Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation