paper-with-me

Papers

Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

2026-05-03 · Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li arxiv

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $β$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $β$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

📄 PDF Abstract BibTeX arXiv:2605.01973

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning

2025-10-22 · M. H. I. Abdalla, Zhipin Wang, Christian Frey, Steffen Eger 외 arxiv

Large Language Model (LLM) conditioning refers to instructing an LLM to generate content in accordance with the norms and values of a specific culture, beliefs of a particular political orientation, or any desired text-s…

Prompt Engineering

Hyper-CL: Conditioning Sentence Representations with Hypernetworks

2024-03-14 · Young Hyun Yoo, Jii Cha, Changhyeon Kim, Taeuk Kim

While the introduction of contrastive learning frameworks in sentence representation learning has significantly contributed to advancements in the field, it still remains unclear whether state-of-the-art sentence embeddi…

Computational EfficiencyContrastive LearningKnowledge Graph CompletionRepresentation Learning+3

HyWA: Hypernetwork Weight Adapting Personalized Voice Activity Detection

2025-10-14 · Mahsa Ghazvini Nejad, Hamed Jafarzadeh Asl, Amin Edraki, Mohammadreza Sadeghi 외 arxiv

Personalized Voice Activity Detection (PVAD) systems activate only in response to a specific target speaker. Speaker-conditioning methods are employed to inject information about the target speaker into a VAD pipeline, t…

Activity Detection

HyperCGAN: Text-to-Image Synthesis with HyperNet-Modulated Conditional Generative Adversarial Networks

2021-09-29 · Kilichbek Haydarov, Aashiq Muhamed, Jovana Lazarevic, Ivan Skorokhodov 외

We present HyperCGAN: a conceptually simple and general approach for text-to-image synthesis that uses hypernetworks to condition a GAN model on text. In our setting, the generator and the discriminator weights are contr…

Image Generation

HyperKKL: Learning KKL Observers for Non-Autonomous Nonlinear Systems via Hypernetwork-Based Input Conditioning

2026-03-31 · Yahia Salaheldin Shaaban, Abdelrahman Sayed Sayed, M. Umar B. Niazi, Karl Henrik Johansson arxiv

Kazantzis-Kravaris/Luenberger (KKL) observers are a class of state observers for nonlinear systems that rely on an injective map to transform the nonlinear dynamics into a stable quasi-linear latent space, from where the…