6 papers
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
Yifu Luo, Haoyuan Sun, Xinhao Hu +12
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is h…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks
Zhuang Zhuang, Zhipeng Wei, Ji Dai +4
Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be…
Boosting Latent Diffusion Models via Disentangled Representation Alignment
John Page, Xuesong Niu, Kai Wu +1
Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attemp…
Visual Generation Tuning
Jiahao Guo, Sinan Du, Jingfeng Yao +7
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However…
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Sinan Du, Jiahao Guo, Bo Li +8
Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predomin…