cs.LGNov 16, 2026

Specificity-Guided Knowledge Diversion for Decomposable Generative Models

Authors: Yucheng Xie, Fu Feng, Jing Wang, Xin Geng, Yong Rui

Organizations: School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China

Abstract

Generative model pre-training typically optimizes a model as a whole without explicitly organizing its parameters for selective reuse. Decomposable pre-training instead learns reusable components for downstream adaptation while retaining strong generative performance. However, existing knowledge diversion methods incur substantial parameter overhead through weight factorization and rely on fixed component assignments to induce specialization, potentially compromising in-distribution generation quality. We therefore propose Specificity-Guided Knowledge Diversion (SGKDiv), which learns how generative knowledge is shared and specialized for effective generation and selective downstream reuse. SGKDiv constructs Knowledge Units from paired feed-forward channels, preserving native computational structure without SVD-based reparameterization. Calibrated condition-wise routing combines a shared usage prior with conditional adjustments, while complementary regularization shapes their allocation, diversity, and magnitude. Together, these designs replace predefined component assignments with adaptively learned and explicitly regulated knowledge specialization. Experiments across diverse model and training settings demonstrate better in-distribution generation than dense and MoE baselines, alongside stronger downstream adaptation than representative PEFT methods across eight datasets.

Figures & tables

Explore similar work

Oct 17, 2026

Knowledge Diversion: A Novel Paradigm for Pre-training Decomposable Image Generation Models

Large-scale pre-trained models have become foundational to modern machine learning, yet conventional pre-training objectives primarily optimize source-domain performance without explicitly considering downstream requirements. Consequently, transferable and task-specific knowledge remains entangled within a shared parameter space, limiting selective knowledge reuse and efficient downstream adaptation. This limitation is particularly consequential for image-generation models, which must accommodate diverse conditions and domains. To address this challenge, we introduce Knowledge Diversion (KDiv), a condition-aware pre-training paradigm for learning inherently decomposable generative models. Before pre-training, KDiv factorizes randomly initialized weights into rank-one Knowledge Units, which are organized into learngenes and tailors. During pre-training, continuous condition-aware routing consolidates knowledge shared across conditions in learngenes while directing condition-dependent variations to tailors. This structured organization enables learngenes to capture transferable generative priors and tailors to develop condition-specific expertise, allowing the resulting model to be selectively recombined for diverse downstream conditions. Extensive experiments across class-, text-, and image-conditioned generation demonstrate that KDiv consistently matches or surpasses dense baselines at comparable pre-training cost and achieves the strongest average downstream performance with a trainable parameter budget comparable to low-rank adaptation methods.
Mar 29, 2026

Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling

Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast, humans flexibly adapt their internal generative representations to each perceptual or imaginative context. Inspired by this capability, we introduce Composer, a new paradigm for adaptive generative modeling based on test-time instance-specific parameter composition. Composer generates input-conditioned parameter adaptations at inference time, which are injected into the pretrained model's weights, enabling per-input specialization without fine-tuning or retraining. Adaptation occurs once prior to multi-step generation, yielding higher-quality, context-aware outputs with minimal computational and memory overhead. Experiments show that Composer substantially improves performance across diverse generative models and use cases, including lightweight/quantized models and test-time scaling. By leveraging input-aware parameter composition, Composer establishes a new paradigm for designing generative models that dynamically adapt to each input, moving beyond static parameterization.
Mar 25, 2026

TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models

To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g. LoRA) is a common practice. However, as new LLM architectures and pre-trained models emerge, transferring this specialized knowledge to newer models becomes an important task. In many scenarios, the original specialized data may be unavailable due to privacy or commercial restrictions, necessitating distillation and transfer of this specialized knowledge from the fine-tuned base model to a different pre-trained model. We present TuneShift-KD, a novel approach that automatically distills specialized knowledge from a fine-tuned model to a target model using only a few examples representative of the specialized information. Our key insight is that specialized knowledge can be identified through perplexity differences between base and fine-tuned models: prompts where the fine-tuned model responds confidently (low perplexity), but the base model struggles (high perplexity), indicate queries corresponding to the specialized knowledge learned by the fine-tuned model. TuneShift-KD leverages this insight to create a synthetic training dataset to transfer the specialized knowledge. Using an iterative process, TuneShift-KD generates more prompts similar to those that generated responses with specialized knowledge. TuneShift-KD does not require training discriminators or access to training datasets. It is an automated approach that only requires the initial fine-tuned and base models and a few representative prompts. Our experiments demonstrate that models fine-tuned using TuneShift-KD achieve higher accuracy than prior approaches, enabling ease of deployment and more effective transfer of the specialized knowledge.