Hemanth Saratchandran

According to our database, Hemanth Saratchandran authored at least 37 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Preconditioned Attention: Enhancing Efficiency in Transformers.

Hemanth Saratchandran

CoRR, March, 2026

Spectral Conditioning of Attention Improves Transformer Performance.

Hemanth Saratchandran, Simon Lucey

CoRR, March, 2026

The Inlet Rank Collapse in Implicit Neural Representations: Diagnosis and Unified Remedy.

Jianqiao Zheng, Hemanth Saratchandran, Simon Lucey

CoRR, February, 2026

Procedural Pretraining: Warming Up Language Models with Abstract Data.

Liangze Jiang, Zachary Shinnick, Anton van den Hengel, Hemanth Saratchandran, Damien Teney

CoRR, January, 2026

SineLoRA∆: Sine-Activated Delta Compression.

Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Paul Albert, Simon Lucey

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

SineProject: Machine Unlearning for Stable Vision Language Alignment.

Arpit Garg, Hemanth Saratchandran, Simon Lucey

CoRR, November, 2025

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN.

Jianqiao Zheng, Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Simon Lucey

CoRR, November, 2025

Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers.

Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Damien Teney, Anton van den Hengel

CoRR, November, 2025

Cutting the Skip: Training Residual-Free Transformers.

Yiping Ji, James Martens, Jianqiao Zheng, Ziqin Zhou, Peyman Moghadam, Xinyu Zhang, Hemanth Saratchandran, Simon Lucey

CoRR, October, 2025

Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs.

Arpit Garg, Hemanth Saratchandran, Ravi Garg, Simon Lucey

CoRR, September, 2025

Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems.

Jiaqi Yao, Lewis Mitchell, John Maclean, Hemanth Saratchandran

CoRR, September, 2025

Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning.

Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran, Anton van den Hengel, Damien Teney

CoRR, May, 2025

Compressing Sine-Activated Low-Rank Adapters through Post-Training Quantization.

Cameron Gordon, Yiping Ji, Hemanth Saratchandran, Paul Albert, Simon Lucey

CoRR, May, 2025

Leaner Transformers: More Heads, Less Depth.

Hemanth Saratchandran, Damien Teney, Simon Lucey

CoRR, May, 2025

Structured Initialization for Vision Transformers.

Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran, Simon Lucey

CoRR, May, 2025

Efficient Learning with Sine-Activated Low-Rank Matrices.

Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey

Proceedings of the Thirteenth International Conference on Learning Representations, 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

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Enhancing Transformers Through Conditioned Embedded Tokens.

Hemanth Saratchandran, Simon Lucey

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Always Skip Attention.

Yiping Ji, Hemanth Saratchandran, Peyman Moghadam, Simon Lucey

Proceedings of the IEEE/CVF International Conference on Computer Vision, 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

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Preconditioners for the Stochastic Training of Neural Fields.

Shin-Fang Ch'ng, Hemanth Saratchandran, Simon Lucey

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Rethinking Softmax: Self-Attention with Polynomial Activations.

Hemanth Saratchandran, Jianqiao Zheng, Yiping Ji, Wenbo Zhang, Simon Lucey

CoRR, 2024

Sine Activated Low-Rank Matrices for Parameter Efficient Learning.

Yiping Ji, Hemanth Saratchandran, Cameron Gordon, Zeyu Zhang, Simon Lucey

CoRR, 2024

Preconditioners for the Stochastic Training of Implicit Neural Representations.

Shin-Fang Ch'ng, Hemanth Saratchandran, Simon Lucey

CoRR, 2024

Analyzing the Neural Tangent Kernel of Periodically Activated Coordinate Networks.

Hemanth Saratchandran, Shin-Fang Ch'ng, Simon Lucey

CoRR, 2024

Architectural Strategies for the optimization of Physics-Informed Neural Networks.

Hemanth Saratchandran, Shin-Fang Ch'ng, Simon Lucey

CoRR, 2024

A sampling theory perspective on activations for implicit neural representations.

Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Weight Conditioning for Smooth Optimization of Neural Networks.

Hemanth Saratchandran, Thomas X. Wang, Simon Lucey

Proceedings of the Computer Vision - ECCV 2024, 2024

Invertible Neural Warp for NeRF.

Shin-Fang Ch'ng, Ravi Garg, Hemanth Saratchandran, Simon Lucey

Proceedings of the Computer Vision - ECCV 2024, 2024

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields.

Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations.

Cameron Gordon, Lachlan E. MacDonald, Hemanth Saratchandran, Simon Lucey

Proceedings of the Computer Vision - ACCV 2024, 2024

2023

On the effectiveness of neural priors in modeling dynamical systems.

Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey

CoRR, 2023

On skip connections and normalisation layers in deep optimisation.

Lachlan E. MacDonald, Jack Valmadre, Hemanth Saratchandran, Simon Lucey

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

How much does Initialization Affect Generalization?

Sameera Ramasinghe, Lachlan Ewen MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey

Proceedings of the International Conference on Machine Learning, 2023

Curvature-Aware Training for Coordinate Networks.

Hemanth Saratchandran, Shin-Fang Ch'ng, Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

A global analysis of global optimisation.

Lachlan Ewen MacDonald, Hemanth Saratchandran, Jack Valmadre, Simon Lucey

CoRR, 2022

How You Start Matters for Generalization.

Sameera Ramasinghe, Lachlan E. MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey

CoRR, 2022