Cover Image

GRASP: GRouped Activation Shared Parameterization for Parameter-Efficient Fine-Tuning and Robust Inference of Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bal, Malyaban, Sengupta, Abhronil
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation
by: Bal, Malyaban, et al.
Published: (2023)

P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks
by: Bal, Malyaban, et al.
Published: (2024)

RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers
by: Mia, Md Zesun Ahmed, et al.
Published: (2026)

Delving Deeper Into Astromorphic Transformers
by: Mia, Md Zesun Ahmed, et al.
Published: (2023)

Scaling SNNs Trained Using Equilibrium Propagation to Convolutional Architectures
by: Lin, Jiaqi, et al.
Published: (2024)

Exploring Extreme Quantization in Spiking Language Models
by: Bal, Malyaban, et al.
Published: (2024)

Benchmarking Spiking Neural Network Learning Methods with Varying Locality
by: Lin, Jiaqi, et al.
Published: (2024)

Spatio-Temporal Pruning for Compressed Spiking Large Language Models
by: Jiang, Yi, et al.
Published: (2025)

On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning
by: Lin, Jiaqi, et al.
Published: (2025)

Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning
by: Mia, Md Zesun Ahmed, et al.
Published: (2025)

Astrocyte Regulated Neuromorphic Central Pattern Generator Control of Legged Robotic Locomotion
by: Han, Zhuangyu, et al.
Published: (2023)

Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain
by: Han, Zhuangyu, et al.
Published: (2026)

Stochastic Spiking Neural Networks with First-to-Spike Coding
by: Jiang, Yi, et al.
Published: (2024)

Hysteresis Activation Function for Efficient Inference
by: Kimhi, Moshe, et al.
Published: (2024)

Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts
by: Zhang, Buze, et al.
Published: (2026)

SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning
by: Dai, Gaole, et al.
Published: (2024)

ActNAS : Generating Efficient YOLO Models using Activation NAS
by: Sah, Sudhakar, et al.
Published: (2024)

Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
by: Li, Boyan, et al.
Published: (2023)

Trilinear Compute-in-Memory Architecture for Energy-Efficient Transformer Acceleration
by: Mia, Md Zesun Ahmed, et al.
Published: (2026)

Differential Evolution Algorithm based Hyper-Parameters Selection of Transformer Neural Network Model for Load Forecasting
by: Sen, Anuvab, et al.
Published: (2023)

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
by: Ishikawa, Satoki, et al.
Published: (2024)

Neuro-Symbolic Activation Discovery: Transferring Mathematical Structures from Physics to Ecology for Parameter-Efficient Neural Networks
by: Hajbi, Anas
Published: (2026)

Deriving Activation Functions Using Integration
by: Huang, Allen Hao, et al.
Published: (2024)

Resource-Efficient and Robust Inference of Deep and Bayesian Neural Networks on Embedded and Analog Computing Platforms
by: Klein, Bernhard
Published: (2025)

Topology-Aware Activation Functions in Neural Networks
by: Snopov, Pavel, et al.
Published: (2025)

Expanded Gating Ranges Improve Activation Functions
by: Huang, Allen Hao
Published: (2024)

SerpentFlow: Generative Unpaired Domain Alignment via Shared-Structure Decomposition
by: Keisler, Julie, et al.
Published: (2026)

Code World Models for Parameter Control in Evolutionary Algorithms
by: Sartori, Camilo Chacón, et al.
Published: (2026)

Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
by: Qiu, Xin, et al.
Published: (2025)

Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
by: Ma, Pui-Wai
Published: (2024)

Adaptive Activation Functions for Predictive Modeling with Sparse Experimental Data
by: Pourkamali-Anaraki, Farhad, et al.
Published: (2024)

APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks
by: Subramanian, Barathi, et al.
Published: (2024)

A More Accurate Approximation of Activation Function with Few Spikes Neurons
by: Jeong, Dayena, et al.
Published: (2024)

Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
by: Kutsuna, Takuro
Published: (2024)

Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
by: Postmus, Joris, et al.
Published: (2024)

Learnable Activation Functions in Physics-Informed Neural Networks for Solving Partial Differential Equations
by: Farea, Afrah, et al.
Published: (2024)

Evolving Multi-Channel Confidence-Aware Activation Functions for Missing Data with Channel Propagation
by: Sani, Naeem Shahabi, et al.
Published: (2026)

ART: Actually Robust Training
by: Chwilczyński, Sebastian, et al.
Published: (2024)

NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
by: Fu, Rong, et al.
Published: (2026)

Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELU
by: Roodschild, Matias, et al.
Published: (2024)