Papers

Filtered to layer fusion · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

112 upvotes · 25 SEP 2026 · Hongyang Du, Yunfei Xie, Junjie Ye et al.

This paper improves the performance of representation autoencoders (RAEs) by training a decoder to work with different layers of a pre-trained visual encoder, rather than relying on a fixed layer fusion. A practitioner might care about this because it allows for more flexible and robust image generation.

representation learningautoencoderslayer fusionregularizationdiffusion models