A 4B compiler model generates LoRA adapters from natural-language specs, enabling a frozen 0.6B interpreter to match Qwen3-32B performance on fuzzy text tasks at 50× less memory.
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SCOPE uses cohort-level external supervision, confidence-aware pseudo-labels, and a lightweight prototype-conditioned adapter (ProAdapter) to adapt frozen EEG foundation models in label-limited settings, reporting consistent gains across 50 experimental configurations.
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.
citing papers explorer
-
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
A 4B compiler model generates LoRA adapters from natural-language specs, enabling a frozen 0.6B interpreter to match Qwen3-32B performance on fuzzy text tasks at 50× less memory.
-
SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels
SCOPE uses cohort-level external supervision, confidence-aware pseudo-labels, and a lightweight prototype-conditioned adapter (ProAdapter) to adapt frozen EEG foundation models in label-limited settings, reporting consistent gains across 50 experimental configurations.
-
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.