No article text was recorded for this version.
architectural scalability (architectural scaling uncertainty)
Version 1 of 1757 papers758 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Composer: A Search Framework for Hybrid Neural Architecture Design
- Blog: Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
- Blog: Arbitrary Few Parameters are Good Enough for Adapting Large-scale Pre-trained Language Models
- Blog: DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
- Blog: Understanding Artificial Neural Network's Behavior from Neuron Activation Perspective
- Blog: MISS: A Generative Pretraining and Finetuning Approach for Med-VQA
- Blog: InfMLLM: A Unified Framework for Visual-Language Tasks
- Blog: Tractable Transformers for Flexible Conditional Generation
- Blog: Analysis and Comparison of Recent MLP Features for LVCSR Systems
- Blog: Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model
- Blog: Composer: A Search Framework for Hybrid Neural Architecture Design
- Blog: Forming Trees with Treeformers
- Blog: Leveraging Image as Compressed Visual Prompt and Hierarchical Visual Knowledge for Effective Image Utilization in MLLMs
- Blog: A Simple Log-based Loss Function for Ordinal Text Classification
- Blog: MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation
- Blog: Poly Kernel Inception Network for Remote Sensing Detection
- Blog: Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
- Blog: Designing Concise ConvNets with Columnar Stages
- Blog: The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
- Blog: Rethinking Mobile Block for Efficient Neural Models
- Blog: Learning with Unmasked Tokens Drives Stronger Vision Learners
- Blog: TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks
- Blog: MemEIC: A Step Toward Continual and Compositional Knowledge Editing
- Blog: A safety realignment framework via subspace-oriented model fusion for large language models
- Blog: Identifying Sub-networks in Neural Networks via Functionally Similar Representations
- Blog: Value Residual Learning
- Blog: SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
- Blog: SPRINT: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
- Blog: Parameter-Efficient Fine-Tuning Design Spaces
- Blog: ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models
- Blog: Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations
- Blog: Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation
- Blog: MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations
- Blog: Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions
- Blog: SkCoder: A Sketch-based Approach for Automatic Code Generation
- Blog: Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
- Blog: How Many Heads Make an SSM? A Unified Framework for Attention and State Space Models
- Blog: BTS: Harmonizing Specialized Experts into a Generalist LLM
- Blog: Efficient Modulation for Vision Networks
- Blog: Towards Efficient Post-training Quantization of Pre-trained Language Models
- Blog: ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
- Blog: Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning
- Blog: Late Fusion and Multi-Level Fission Amplify Cross-Modal Transfer in Text-Speech LMs
- Blog: One Simple Trick to Fix Your Bayesian Neural Network
- Blog: Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
- Blog: Inner-layer Token Self-modulation as Another Scaling Axis for LLMs
- Blog: Frequency Autoregressive Image Generation with Continuous Tokens
- Blog: Spectral Gating Networks
- Blog: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning
- Blog: Attention Projection Mixing with Exogenous Anchors
- Blog: RWKV-CLIP: A Robust Vision-Language Representation Learner
- Blog: Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
- Blog: multivariateGPT: a decoder-only transformer for multivariate categorical and numeric data
- Blog: Rethinking Token-Mixing MLP for MLP-based Vision Backbone
- Blog: Vision Mamba: A Comprehensive Survey and Taxonomy
- Blog: Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
- Blog: Bridging Game Theory and Transformer Routing: Mean Field Equilibria for Mixture of Experts
- Blog: Can We Generate Realistic Hands Only Using Convolution?
- Blog: Simplifying Transformer Blocks
- Blog: Crypto-Oriented Neural Architecture Design
Showing 60 of 757 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_scalability_architectural__ad98bfd4,
title = {architectural scalability (architectural scaling uncertainty)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-scalability-architectural-scaling-uncertainty/rdr_ad98bfd45eb149219f47f763173d5742},
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_architectural_scalability_architectural__ad98bfd4_v1,
title = {architectural scalability (architectural scaling uncertainty)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-scalability-architectural-scaling-uncertainty/rdr_ad98bfd45eb149219f47f763173d5742/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}