On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning
cs.LG, cs.AI
Submitted: 2026-06-21
Updated: 2026-10-12
Terminology
Sources
- Bayesian sparsity and class sparsity priors for dictionary learning and coding
- X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- Evaluating Object Hallucination in Large Vision-Language Models
- Valley: Video Assistant with Large Language model Enhanced abilitY
- SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
- Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
- Greedy Deep Dictionary Learning
- freePruner: A Training-free Approach for Large Multimodal Model Acceleration
- Hybrid Token Compression for Vision-Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks