12 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…
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Runxi Cheng, Yuchen Guan, Yongxian Wei +7
Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-trainin…
Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis
Yongxian Wei, Yilin Zhao, Zixuan Hu +7
Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-quality data. However, existing a…
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
Yongxian Wei, Runxi Cheng, Weike Jin +7
Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert m…
VACoT: Rethinking Visual Data Augmentation with VLMs
Zhengzhuo Xu, Chong Sun, SiNan Du +3
While visual data augmentation remains a cornerstone for training robust vision models, it has received limited attention in visual language models (VLMs), which predominantly rely…
ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning
Zhengzhuo Xu, SiNan Du, Yiyan Qi +4
Multimodal Large Language Models (MLLMs) have emerged as powerful tools for chart comprehension. However, they heavily rely on extracted content via OCR, which leads to numerical h…