No article text was recorded for this version.
cross-architecture generalization (decoder-only model compatibility)
Version 1 of 145 papers45 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Mentor-KD: Making Small Language Models Better Multi-step Reasoners
- Blog: Efficient Active Learning with Adapters
- Blog: ICaRus: Identical Cache Reuse for Efficient Multi-Model Inference
- Blog: Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt
- Blog: Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
- Blog: Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering
- Blog: AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages
- Blog: SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification
- Blog: Learning from Negative Samples in Biomedical Generative Entity Linking
- Blog: HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
- Blog: CodePrompt: Task-Agnostic Prefix Tuning for Program and Language Generation
- Blog: FastDraft: How to Train Your Draft
- Blog: Commonsense Knowledge Transfer for Pre-trained Language Models
- Blog: Evaluating the Generalization Property of Prefix-based Methods for Data-to-text Generation
- Blog: Crosslingual Generalization through Multitask Finetuning
- Blog: Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars
- Blog: How does the task complexity of masked pretraining objectives affect downstream performance?
- Blog: Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments
- Blog: Hyperdecoders: Instance-specific decoders for multi-task NLP
- Blog: Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models
- Blog: Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
- Blog: A Single Linear Layer Yields Task-Adapted Low-Rank Matrices
- Blog: Retrieval of Soft Prompt Enhances Zero-Shot Task Generalization
- Blog: Investigating the Potential of Task Arithmetic for Cross-Lingual Transfer
- Blog: A Universal Decoupled Training Framework for Human Parsing
- Blog: NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption
- Blog: Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks
- Blog: Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning
- Blog: Lifelong Event Detection via Optimal Transport
- Blog: Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models
- Blog: UniTrans: Unified Parameter-Efficient Transfer Learning and Multimodal Alignment for Large Multimodal Foundation Model
- Blog: Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding
- Blog: Position Really Matters: Towards a Holistic Approach for Prompt Tuning
- Blog: MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions
- Blog: Low-Rank Adaptation for Multilingual Summarization: An Empirical Study
- Blog: To Adapt or to Fine-tune: A Case Study on Abstractive Summarization
- Blog: EnerGIZAr: Leveraging GIZA++ for Effective Tokenizer Initialization
- Blog: Quick Dense Retrievers Consume KALE: Post Training KullbackLeibler Alignment of Embeddings for Asymmetrical dual encoders
- Blog: Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers
- Blog: TADA : Task Agnostic Dialect Adapters for English
- Blog: Hadamard Adapter: An Extreme Parameter-Efficient Adapter Tuning Method for Pre-trained Language Models
- Blog: BRIDO: Bringing Democratic Order to Abstractive Summarization
- Blog: Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning
- Blog: LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
- Blog: Lexical Generalization Improves with Larger Models and Longer Training
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_architecture_generalization_decode_b3bf12bf,
title = {cross-architecture generalization (decoder-only model compatibility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalization-decoder-only-model-compatibility/rdr_b3bf12bf397d4300a7aa8c893393a3a8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_architecture_generalization_decode_b3bf12bf_v1,
title = {cross-architecture generalization (decoder-only model compatibility)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-generalization-decoder-only-model-compatibility/rdr_b3bf12bf397d4300a7aa8c893393a3a8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}