Saratchandran, Hemanth

16 publications

ICCV 2025 Always Skip Attention Yiping Ji, Hemanth Saratchandran, Peyman Moghadam, Simon Lucey

ICLR 2025 Efficient Learning with Sine-Activated Low-Rank Matrices Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey

ICCV 2025 Enhancing Transformers Through Conditioned Embedded Tokens Hemanth Saratchandran, Simon Lucey

CVPR 2025 Preconditioners for the Stochastic Training of Neural Fields Shin-Fang Chng, Hemanth Saratchandran, Simon Lucey

ICLR 2025 RandLoRA: Full Rank Parameter-Efficient Fine-Tuning of Large Models Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad

NeurIPS 2025 Spectral Conditioning of Attention Improves Transformer Performance Hemanth Saratchandran, Simon Lucey

NeurIPS 2025 Structured Initialization for Vision Transformers Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran, Simon Lucey

ICCV 2025 Towards Higher Effective Rank in Parameter-Efficient Fine-Tuning Using Khatri-Rao Product Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Anton van den Hengel, Ehsan Abbasnejad

ICML 2024 A Sampling Theory Perspective on Activations for Implicit Neural Representations Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey

CVPR 2024 From Activation to Initialization: Scaling Insights for Optimizing Neural Fields Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey

ECCV 2024 Invertible Neural Warp for NeRF Shin-Fang Chng, Ravi Garg, Hemanth Saratchandran, Simon Lucey

ECCV 2024 Weight Conditioning for Smooth Optimization of Neural Networks Hemanth Saratchandran, Thomas X Wang, Simon Lucey

ICCV 2023 Curvature-Aware Training for Coordinate Networks Hemanth Saratchandran, Shin-Fang Chng, Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey

ICML 2023 How Much Does Initialization Affect Generalization? Sameera Ramasinghe, Lachlan Ewen Macdonald, Moshiur Farazi, Hemanth Saratchandran, Simon Lucey

NeurIPS 2023 On Skip Connections and Normalisation Layers in Deep Optimisation Lachlan MacDonald, Jack Valmadre, Hemanth Saratchandran, Simon Lucey

ICMLW 2023 On the Effectiveness of Neural Priors in Modeling Dynamical Systems Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey