Hemanth Saratchandran
14 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (21) π Renaissance Researcher (5) π Interdisciplinary Bridge π Conference Polyglot (6) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
π
Grand Slam
π€
Dynamic Duo
(11)
π
Century Club
(13)
β‘
Prolific Year
(6)
β
The Questioner
Conferences
ICCV (4)
CVPR (2)
ECCV (2)
ICLR (2)
ICML (2)
AAAI (1)
NIPS (1)
Top co-authors
Research topics
Keywords
neural field
(2)
skip connection
(2)
low-rank adaptation
(2)
neural network optimization
(2)
vision transformer
(1)
self-attention mechanism
(1)
stochastic optimization
(1)
knowledge distillation
(1)
stochastic gradient descent
(1)
fourier analysis
(1)
image compression
(1)
model adaptation
(1)
attention mechanism
(1)
loss landscape
(1)
parameter efficient
(1)
theoretical analysis
(1)
gradient descent
(1)
optimization theory
(1)
neural representation
(1)
signal representation
(1)
Papers
SineLoRAβ: Sine-Activated Delta Compression
AAAI 2026
Preconditioners for the Stochastic Training of Neural Fields
CVPR 2025
Always Skip Attention
ICCV 2025
Enhancing Transformers Through Conditioned Embedded Tokens
ICCV 2025
Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product
ICCV 2025
Efficient Learning with Sine-Activated Low-Rank Matrices
ICLR 2025
RandLoRA: Full rank parameter-efficient fine-tuning of large models
ICLR 2025
Invertible Neural Warp for NeRF
ECCV 2024
A sampling theory perspective on activations for implicit neural representations
ICML 2024
Weight Conditioning for Smooth Optimization of Neural Networks
ECCV 2024
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
CVPR 2024
How much does Initialization Affect Generalization?
ICML 2023
Curvature-Aware Training for Coordinate Networks
ICCV 2023
On skip connections and normalisation layers in deep optimisation
NIPS 2023