Hemanth Saratchandran

44 papers A* 9Journal 32Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Preconditioned Attention: Enhancing Efficiency in Transformers. CoRR Hemanth Saratchandran
2026	J	`jnl`	Procedural Pretraining: Warming Up Language Models with Abstract Data. CoRR Liangze Jiang, Zachary Shinnick, Anton van den Hengel, Hemanth Saratchandran, Damien Teney
2026	A*	`conf`	SineLoRA∆: Sine-Activated Delta Compression. AAAI Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Paul Albert, Simon Lucey
2026	J	`jnl`	Spectral Conditioning of Attention Improves Transformer Performance. CoRR Hemanth Saratchandran, Simon Lucey
2026	J	`jnl`	The Inlet Rank Collapse in Implicit Neural Representations: Diagnosis and Unified Remedy. CoRR Jianqiao Zheng, Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	Always Skip Attention. CoRR Yiping Ji, Hemanth Saratchandran, Peyman Moghadam, Simon Lucey
2025	J	`jnl`	Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers. CoRR Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Damien Teney, Anton van den Hengel
2025	J	`jnl`	Compressing Sine-Activated Low-Rank Adapters through Post-Training Quantization. CoRR Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Paul Albert, Simon Lucey
2025	J	`jnl`	Cutting the Skip: Training Residual-Free Transformers. CoRR Yiping Ji, James Martens, Jianqiao Zheng, Ziqin Zhou, Peyman Moghadam, Xinyu Zhang, Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems. CoRR Jiaqi Yao, Lewis Mitchell, John Maclean, Hemanth Saratchandran
2025	A*	`conf`	Efficient Learning with Sine-Activated Low-Rank Matrices. ICLR Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey
2025	J	`jnl`	Enhancing Transformers Through Conditioned Embedded Tokens. CoRR Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	From Tables to Signals: Revealing Spectral Adaptivity in TabPFN. CoRR Jianqiao Zheng, Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	Leaner Transformers: More Heads, Less Depth. CoRR Hemanth Saratchandran, Damien Teney, Simon Lucey
2025	A*	`conf`	Preconditioners for the Stochastic Training of Neural Fields. CVPR Shin-Fang Ch'ng, Hemanth Saratchandran, Simon Lucey
2025	A*	`conf`	RandLoRA: Full rank parameter-efficient fine-tuning of large models. ICLR Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez Opazo, Anton van den Hengel, Ehsan Abbasnejad
2025	J	`jnl`	RandLoRA: Full-rank parameter-efficient fine-tuning of large models. CoRR Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez Opazo, Anton van den Hengel, Ehsan Abbasnejad
2025	J	`jnl`	SineProject: Machine Unlearning for Stable Vision Language Alignment. CoRR Arpit Garg, Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs. CoRR Arpit Garg, Hemanth Saratchandran, Ravi Garg, Simon Lucey
2025	J	`jnl`	Structured Initialization for Vision Transformers. CoRR Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran, Simon Lucey
2025	J	`jnl`	Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri-Rao Product. CoRR Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Anton van den Hengel, Ehsan Abbasnejad
2025	J	`jnl`	Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning. CoRR Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Anton van den Hengel, Damien Teney
2024	J	`jnl`	A Sampling Theory Perspective on Activations for Implicit Neural Representations. CoRR Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey
2024	A*	`conf`	A sampling theory perspective on activations for implicit neural representations. ICML Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey
2024	J	`jnl`	Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks. CoRR Hemanth Saratchandran, Shin-Fang Ch'ng, Simon Lucey
2024	J	`jnl`	Architectural Strategies for the optimization of Physics-Informed Neural Networks. CoRR Hemanth Saratchandran, Shin-Fang Ch'ng, Simon Lucey
2024	—	`conf`	D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations. ACCV (7) Cameron Gordon, Lachlan E. MacDonald, Hemanth Saratchandran, Simon Lucey
2024	J	`jnl`	D'OH: Decoder-Only random Hypernetworks for Implicit Neural Representations. CoRR Cameron Gordon, Lachlan Ewen MacDonald, Hemanth Saratchandran, Simon Lucey
2024	A*	`conf`	From Activation to Initialization: Scaling Insights for Optimizing Neural Fields. CVPR Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey
2024	J	`jnl`	From Activation to Initialization: Scaling Insights for Optimizing Neural Fields. CoRR Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey
2024	—	`conf`	Invertible Neural Warp for NeRF. ECCV (17) Shin-Fang Ch'ng, Ravi Garg, Hemanth Saratchandran, Simon Lucey
2024	J	`jnl`	Invertible Neural Warp for NeRF. CoRR Shin-Fang Ch'ng, Ravi Garg, Hemanth Saratchandran, Simon Lucey
2024	J	`jnl`	Preconditioners for the Stochastic Training of Implicit Neural Representations. CoRR Shin-Fang Ch'ng, Hemanth Saratchandran, Simon Lucey
2024	J	`jnl`	Rethinking Softmax: Self-Attention with Polynomial Activations. CoRR Hemanth Saratchandran, Jianqiao Zheng, Yiping Ji, Wenbo Zhang, Simon Lucey
2024	J	`jnl`	Sine Activated Low-Rank Matrices for Parameter Efficient Learning. CoRR Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey
2024	—	`conf`	Weight Conditioning for Smooth Optimization of Neural Networks. ECCV (85) Hemanth Saratchandran, Thomas X. Wang, Simon Lucey
2024	J	`jnl`	Weight Conditioning for Smooth Optimization of Neural Networks. CoRR Hemanth Saratchandran, Thomas X. Wang, Simon Lucey
2023	A*	`conf`	Curvature-Aware Training for Coordinate Networks. ICCV Hemanth Saratchandran, Shin-Fang Ch'ng, Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2023	J	`jnl`	Curvature-Aware Training for Coordinate Networks. CoRR Hemanth Saratchandran, Shin-Fang Ch'ng, Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2023	A*	`conf`	How much does Initialization Affect Generalization? ICML Sameera Ramasinghe, Lachlan Ewen MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey
2023	A*	`conf`	On skip connections and normalisation layers in deep optimisation. NeurIPS Lachlan E. MacDonald, Jack Valmadre, Hemanth Saratchandran, Simon Lucey
2023	J	`jnl`	On the effectiveness of neural priors in modeling dynamical systems. CoRR Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey
2022	J	`jnl`	A global analysis of global optimisation. CoRR Lachlan Ewen MacDonald, Hemanth Saratchandran, Jack Valmadre, Simon Lucey
2022	J	`jnl`	How You Start Matters for Generalization. CoRR Sameera Ramasinghe, Lachlan E. MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey