No article text was recorded for this version.
unidimensional model scaling
Version 1 of 127 papers27 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compressed MoE ASR Model Based on Knowledge Distillation and Quantization
- Blog: Scaling depth capacity via zero/one-layer model expansion
- Blog: Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression
- Blog: Decomposable-Net: Scalable Low-Rank Compression for Neural Networks
- Blog: On the Transformer Growth for Progressive BERT Training
- Blog: CONet: Channel Optimization for Convolutional Neural Networks
- Blog: Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
- Blog: Reducing Transformer Depth on Demand with Structured Dropout
- Blog: Switchable Representation Learning Framework with Self-Compatibility
- Blog: Cooperative Learning for Cost-Adaptive Inference
- Blog: SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
- Blog: Slimmable Neural Networks
- Blog: Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency
- Blog: Once-for-All Sequence Compression for Self-Supervised Speech Models
- Blog: FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment
- Blog: DeeDiff: Dynamic Uncertainty-Aware Early Exiting for Accelerating Diffusion Model Generation
- Blog: Masked Structural Growth for 2x Faster Language Model Pre-training
- Blog: Slimmable Generative Adversarial Networks
- Blog: Layer Pruning on Demand with Intermediate CTC
- Blog: Adaptive Computation with Elastic Input Sequence
- Blog: WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling
- Blog: InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
- Blog: Dynamic Slimmable Network
- Blog: QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution
- Blog: Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
- Blog: Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation
- Blog: LESA: Learnable LLM Layer Scaling-Up
History & citation
Current · Permanent link
- This direction split from Elastic Neural Architectures for Dynamic Deployment (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_unidimensional_model_scaling_77d611f6,
title = {unidimensional model scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unidimensional-model-scaling/rdr_77d611f6448b4f1898c363185ba984ea},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_unidimensional_model_scaling_77d611f6_v1,
title = {unidimensional model scaling},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unidimensional-model-scaling/rdr_77d611f6448b4f1898c363185ba984ea/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}