ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Zhi Wang

Zhi Wang

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 14, 2026, 11:32 PM AMS

23

papers

495

total citations

papers (23)

Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding

Provably efficient multi-task reinforcement learning with model transfer

NEURIPS 2021arXiv

Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning

ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices

OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments

PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

EVOS: Efficient Implicit Neural Training via EVOlutionary Selector

Procedural Level Generation with Diffusion Models from a Single Example

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning

Enhancing Implicit Neural Representations via Symmetric Power Transformation

JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision

NEURIPS 2025arXiv

COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation

Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling

DICE: Staleness-Centric Optimizations for Parallel Diffusion MoE Inference

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition

DeepHalo: A Neural Choice Model with Controllable Context Effects

NEURIPS 2025arXiv