Yonggan Fu

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

Achievements

+14 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (5)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) 🤝 Dynamic Duo (15) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (13) 🧬 Topic Evolution ⚡ Prolific Year (6) ❓ The Questioner 📈 Trend Setter 🗃️ Keyword Collector (129) 🔥 Unstoppable (6) 💎 Century Club (29)

Conferences

ICML (9) ICLR (6) NIPS (5) AAAI (3) CVPR (2) ICCV (2) ACL (1) EACL (1) ECCV (1)

Top co-authors

Yingyan Lin (15) Yingyan Celine Lin (9) Zhongzhi Yu (8) Haoran You (6) Chaojian Li (6) Yue Wang (5) Yingyan (Celine) Lin (5) Yang Zhang (5) Yongan Zhang (4) Zhifan Ye (4)

Research topics

Computer Vision (1)

Keywords

model compression (8) neural architecture search (5) adversarial robustness (4) efficient computing (3) adversarial training (2) vision transformer (2) lottery ticket hypothesis (2) convolutional neural network (2) novel view synthesis (2) neural radiance field (2) efficient training (2) efficient inference (2) knowledge distillation (2) attention mechanism (1) self-supervised learning (1) ensemble learning (1) image generation (1) model quantization (1) few-shot learning (1) speech processing (1)

Papers

Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute EACL 2026 LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models ICML 2025 Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment ICCV 2025 LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement ICLR 2025 Hymba: A Hybrid-head Architecture for Small Language Models ICLR 2025 LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025 AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment NIPS 2024 Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration ICML 2024 Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields ECCV 2024 Rad-NeRF: Ray-decoupled Training of Neural Radiance Field NIPS 2024 Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning CVPR 2023 NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations ICML 2023 Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence CVPR 2023 Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning ICML 2023 Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing NIPS 2022 MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022 Early-Bird GCNs: Graph-Network Co-optimization towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets AAAI 2022 Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations? ICLR 2022 ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks ICML 2022 DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks ICML 2022 CPT: Efficient Deep Neural Network Training via Cyclic Precision ICLR 2021 Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks NIPS 2021 SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-Powered Intelligent PhlatCam ICCV 2021 HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark ICLR 2021 Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021 Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021 AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks ICML 2020 FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training NIPS 2020 Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks ICLR 2020 Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference AAAI 2020