Haoran You

Identifiers

• name variant Haoran You 0.60 · backfill

Papers (35)

1. UniSER: A Foundation Model for Unified Soft Effects Removal cs.CV · 2025 · author #7
2. LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models cs.LG · 2025 · author #5
3. Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training cs.CV · 2025 · author #3
4. Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers cs.CV · 2024 · author #1
5. Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture cs.AR · 2024 · author #6
6. EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting cs.LG · 2024 · author #4
7. When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models cs.CL · 2024 · author #1
8. ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization cs.LG · 2024 · author #1
9. Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI cs.AI · 2024 · author #5
10. NetDistiller: Empowering Tiny Deep Learning via In-Situ Distillation cs.LG · 2023 · author #5
11. NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants cs.LG · 2023 · author #4
12. ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer cs.LG · 2023 · author #1
13. Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction cs.AR · 2023 · author #7
14. Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design cs.CV · 2023 · author #6
15. Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference cs.CV · 2022 · author #1
16. NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks cs.AR · 2022 · author #2
17. ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design cs.LG · 2022 · author #1
18. SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning cs.CV · 2022 · author #1
19. i-FlatCam: A 253 FPS, 91.49 $\mu$J/Frame Ultra-Compact Intelligent Lensless Camera for Real-Time and Efficient Eye Tracking in VR/AR cs.AR · 2022 · author #7
20. EyeCoD: Eye Tracking System Acceleration via FlatCam-based Algorithm & Accelerator Co-Design cs.HC · 2022 · author #1
21. ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks cs.LG · 2022 · author #1
22. LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference cs.LG · 2022 · author #5
23. I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization cs.AR · 2022 · author #6
24. GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design cs.AR · 2021 · author #1
25. G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency cs.AR · 2021 · author #2
26. HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark cs.LG · 2021 · author #6
27. Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets cs.LG · 2021 · author #1
28. Max-Affine Spline Insights Into Deep Network Pruning cs.LG · 2021 · author #1
29. SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training cs.LG · 2021 · author #5
30. FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training cs.CV · 2020 · author #2
31. DNA: Differentiable Network-Accelerator Co-Search cs.LG · 2020 · author #5
32. ShiftAddNet: A Hardware-Inspired Deep Network cs.LG · 2020 · author #1
33. SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation cs.LG · 2020 · author #5
34. Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks cs.LG · 2019 · author #1
35. Bayesian Cycle-Consistent Generative Adversarial Networks via Marginalizing Latent Sampling cs.LG · 2018 · author #1

Mentions

• 2507.14204 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2504.09606 #3 · arxiv_oai · confidence 0.70 Haoran You
• 2304.12467 #7 · arxiv_oai · confidence 0.70 Haoran You
• 2206.08141 #7 · arxiv_oai · confidence 0.70 Haoran You
• 2103.10584 #6 · arxiv_oai · confidence 0.70 Haoran You
• 2412.16822 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2112.11594 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2210.09573 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2207.03677 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2205.08119 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2103.00794 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2101.02338 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2010.12785 #1 · arxiv_oai · confidence 0.70 Haoran You
• 1909.11957 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2206.00877 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2304.11842 #6 · arxiv_oai · confidence 0.70 Haoran You
• 2012.13113 #2 · arxiv_oai · confidence 0.70 Haoran You
• 2010.14778 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2406.05981 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2409.13153 #6 · arxiv_oai · confidence 0.70 Haoran You
• 2406.07368 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2306.06446 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2211.10526 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2406.15758 #4 · arxiv_oai · confidence 0.70 Haoran You
• 2401.01040 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2310.19820 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2306.13586 #4 · arxiv_oai · confidence 0.70 Haoran You
• 2210.13361 #2 · arxiv_oai · confidence 0.70 Haoran You
• 2203.07713 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2203.03606 #6 · arxiv_oai · confidence 0.70 Haoran You
• 2101.01163 #5 · arxiv_oai · confidence 0.70 Haoran You
• 2109.08983 #2 · arxiv_oai · confidence 0.70 Haoran You
• 1811.07465 #1 · arxiv_oai · confidence 0.70 Haoran You
• 2005.03403 #5 · arxiv_oai · confidence 0.70 Haoran You

Frequent Coauthors

• Yingyan Celine Lin 22 shared papers
• Yonggan Fu 18 shared papers
• Chaojian Li 14 shared papers
• Yang Zhao 9 shared papers
• Yongan Zhang 9 shared papers
• Yingyan Lin 8 shared papers
• Huihong Shi 7 shared papers
• Zhongzhi Yu 7 shared papers
• Cheng Wan 5 shared papers
• Shang Wu 5 shared papers
• Sixu Li 5 shared papers
• Yue Wang 5 shared papers
• Zhangyang Wang 5 shared papers
• Shunyao Zhang 4 shared papers
• Xiaohan Chen 4 shared papers
• Ang Li 3 shared papers
• Baopu Li 3 shared papers
• Jiayi Yuan 3 shared papers
• Tong Geng 3 shared papers
• Yingyan (Celine) Lin 3 shared papers