conftrace_
← Authors

Zhihang Yuan

23 papers · 2020–2026 · 9 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+9 more ↓ 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (5) πŸ—ΊοΈ Taxonomy Completionist (29)
🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) πŸ‘‘ Triple Crown πŸ† Grand Slam ⚑ Prolific Year (13) πŸ’Ž Century Club (22) πŸ—ƒοΈ Keyword Collector (76) πŸ”₯ Unstoppable (5)

Conferences

CVPR (4) ICCV (4) ICML (4) ICLR (3) NIPS (3) ECCV (2) AAAI (1) ACL (1) EMNLP (1)

Top co-authors

Dawei Yang (9) Yuzhang Shang (8) Sifan Zhou (6) Zhixuan Chen (5) Xing Hu (5) Yu Wang (4) Zukang Xu (4) Yan Yan (3) Guohao Dai (3) Hanling Zhang (3)

Keywords

model compression (5) model quantization (3) diffusion transformer (3) diffusion model (3) video generation (2) post-training quantization (2) model acceleration (2) vision transformer (1) attention mechanism (1) contrastive learning (1) sampling strategy (1) computational efficiency (1) autonomous driving (1) neural architecture search (1) curriculum learning (1) efficient computing (1) neural network optimization (1) transfer learning (1) efficient inference (1) text-to-image generation (1)

Papers

OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMs AAAI 2026 EA-Vit: Efficient Adaptation for Elastic Vision Transformer ICCV 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate ICCV 2025 DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers ICCV 2025 QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning ICCV 2025 MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods ICLR 2025 OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting ICLR 2025 MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance ICML 2025 MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design ICML 2025 RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization ICML 2025 GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning ACL 2025 PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram CVPR 2025 A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training CVPR 2025 DiTFastAttn: Attention Compression for Diffusion Transformer Models NIPS 2024 PB-LLM: Partially Binarized Large Language Models ICLR 2024 Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding ICML 2024 PD-Quant: Post-Training Quantization Based on Prediction Difference Metric CVPR 2023 MIM4DD: Mutual Information Maximization for Dataset Distillation NIPS 2023 Post-Training Quantization on Diffusion Models CVPR 2023 PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization ECCV 2022 Latency-aware Spatial-wise Dynamic Networks NIPS 2022 S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search ECCV 2020