No article text was recorded for this version.
computational cost of large models
Version 1 of 1208 papers209 conceptsfrozen 2026-10-04
Papers in this version
- Blog: BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings
- Blog: AdapLeR: Speeding up Inference by Adaptive Length Reduction
- Blog: Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective
- Blog: Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM
- Blog: Resource-efficient Inference with Foundation Model Programs
- Blog: ZeroGen: Efficient Zero-shot Learning via Dataset Generation
- Blog: Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
- Blog: Mixed Distillation Helps Smaller Language Models Reason Better
- Blog: SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
- Blog: LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation
- Blog: Can we obtain significant success in RST discourse parsing by using Large Language Models?
- Blog: SciRus: Tiny and Powerful Multilingual Encoder for Scientific Texts
- Blog: Disfluency Detection with Unlabeled Data and Small BERT Models
- Blog: Leveraging SAM for Single-Source Domain Generalization in Medical Image Segmentation
- Blog: Augmenting interpretable models with large language models during training
- Blog: Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation
- Blog: DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
- Blog: Towards Next-Generation Steganalysis: LLMs Unleash the Power of Detecting Steganography
- Blog: Lightweight Transformers for Conversational AI
- Blog: Adaptable and Reliable Text Classification using Large Language Models
- Blog: BackSlash: Rate Constrained Optimized Training of Large Language Models
- Blog: A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
- Blog: Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation
- Blog: Generating Faithful and Salient Text from Multimodal Data
- Blog: Multi-Agent Credit Assignment with Pretrained Language Models
- Blog: DINOv2 based Self Supervised Learning For Few Shot Medical Image Segmentation
- Blog: Structural Pruning of Pre-trained Language Models via Neural Architecture Search
- Blog: FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework
- Blog: 50 Shades of Deceptive Patterns: A Unified Taxonomy, Multimodal Detection, and Security Implications
- Blog: LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling
- Blog: K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering
- Blog: Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via Prompting
- Blog: LETS-C: Leveraging Text Embedding for Time Series Classification
- Blog: LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework
- Blog: Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
- Blog: Adversarial Text Purification: A Large Language Model Approach for Defense
- Blog: Multiple Word Embeddings for Increased Diversity of Representation
- Blog: Small and Practical BERT Models for Sequence Labeling
- Blog: Word Sense Induction with Knowledge Distillation from BERT
- Blog: BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance
- Blog: DeepDFA: Dataflow Analysis-Guided Efficient Graph Learning for Vulnerability Detection
- Blog: In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
- Blog: Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
- Blog: DE3-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks
- Blog: Generating Data for Symbolic Language with Large Language Models
- Blog: SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
- Blog: DINO-VITS: Data-Efficient Noise-Robust Zero-Shot Voice Cloning via Multi-Tasking with Self-Supervised Speaker Verification Loss
- Blog: BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression
- Blog: IndicBART: A Pre-trained Model for Indic Natural Language Generation
- Blog: Rethinking the Authorship Verification Experimental Setups
- Blog: Early Exiting BERT for Efficient Document Ranking
- Blog: Multilingual Sequence-to-Sequence Models for Hebrew NLP
- Blog: Squeezed Very Deep Convolutional Neural Networks for Text Classification
- Blog: OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
- Blog: Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition
- Blog: Conceptualizing Suicidal Behavior: Utilizing Explanations of Predicted Outcomes to Analyze Longitudinal Social Media Data
- Blog: GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots
- Blog: MIGA: A Unified Multi-Task Generation Framework for Conversational Text-to-SQL
- Blog: Intra-Correlation Encoding for Chinese Sentence Intention Matching
- Blog: Bridging Distribution Gap via Semantic Rewriting with LLMs to Enhance OOD Robustness
Showing 60 of 208 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_computational_cost_of_large_models_e9427762,
title = {computational cost of large models},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-cost-of-large-models/rdr_e942776238b64af0912bf2637ab25f3f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_computational_cost_of_large_models_e9427762_v1,
title = {computational cost of large models},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-cost-of-large-models/rdr_e942776238b64af0912bf2637ab25f3f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}