papers

Publications (17)

cs.LG2025

Knowledge Diversion for Efficient Morphology Control and Policy Transfer

Fu Feng, Ruixiao Shi, Yucheng Xie +3

Universal morphology control aims to learn a universal policy that generalizes across heterogeneous agent morphologies, with Transformer-based controllers emerging as a popular cho…

cs.LG2026

Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization

Fu Feng, Yucheng Xie, Ruixiao Shi +2

The pre-training and fine-tuning paradigm has become the dominant approach for model adaptation. However, conventional pre-training typically yields models at a fixed scale, wherea…

cs.CV2026

A Creative Agent is Worth a 64-Token Template

Ruixiao Shi, Fu Feng, Yucheng Xie +3

Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompt…

cs.LG2026

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling

Jianlu Shen, Fu Feng, Jiaze Xu +3

Transferring pre-trained knowledge from a source model to a target model of a different architectural size is a key challenge for flexible and efficient model scaling. However, cur…

cs.LG2026

Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform

Jianlu Shen, Fu Feng, Yucheng Xie +2

Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a pre-trained model is tightly coup…

cs.LG2025

WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models

Fu Feng, Yucheng Xie, Jing Wang +1

The growing complexity of model parameters underscores the significance of pre-trained models. However, deployment constraints often necessitate models of varying sizes, exposing l…

cs.CV2025

DivControl: Knowledge Diversion for Controllable Image Generation

Yucheng Xie, Fu Feng, Ruixiao Shi +3

Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial cont…

cs.AI2026

SafeGene: Reusable Adapters for Transferable Safety Alignment

Yanghan Wang, Zhiqiang Kou, Fu Feng +2

Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts…

cs.CV2025

KIND: Knowledge Integration and Diversion for Training Decomposable Models

Yucheng Xie, Fu Feng, Ruixiao Shi +3

Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges…

cs.CV2025

FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning

Ruixiao Shi, Fu Feng, Yucheng Xie +2

Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability…

cs.NE2023

Genes in Intelligent Agents

Fu Feng, Jing Wang, Xu Yang +1

The genes in nature give the lives on earth the current biological intelligence through transmission and accumulation over billions of years. Inspired by the biological intelligenc…

cs.CV2025

Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation

Fu Feng, Yucheng Xie, Xu Yang +2

``Creative'' remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concept…

cs.CV2026

Self-Supervised Weight Templates for Scalable Vision Model Initialization

Yucheng Xie, Fu Feng, Ruixiao Shi +3

The increasing scale and complexity of modern model parameters underscore the importance of pre-trained models. However, deployment often demands architectures of varying sizes, ex…

cs.CV2025

Distribution-Conditional Generation: From Class Distribution to Creative Generation

Fu Feng, Yucheng Xie, Xu Yang +2

Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize tr…

physics.optics2024

Investigating and Controlling the Libration and Rotation Dynamics of Nanoparticles in an Optomechanical System

Chaoxiong He, Jinchuan Wang, Ying Dong +7

In optomechanical systems, the libration and rotation of nanoparticles offer profound insights for ultrasensitive torque measurement and macroscopic quantum superpositions. Achieve…

cs.CV2026

FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models

Yucheng Xie, Fu Feng, Ruixiao Shi +4

The training of diffusion models is computationally intensive, making effective pre-training essential. However, real-world deployments often demand models of variable sizes due to…

cs.LG2024

Transferring Core Knowledge via Learngenes

Fu Feng, Jing Wang, Xin Geng

The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks withou…