7 papers
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Chongjian Ge, Hanwen Jiang, Tianyu Wang +9
The paper presents Chimera, a hybrid visual diffusion transformer that processes text, image, and video tokens in a single raster-ordered stream using efficient attention mechanism…
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Yiming Ren, Yiran Xu, Zicheng Lin +8
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
Yiming Ren, Junjie Wang, Yuxin Meng +11
Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests…
DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance
Peiying Zhang, Nanxuan Zhao, Matthew Fisher +3
Recent vision-language model (VLM)-based approaches have achieved impressive results on SVG generation. However, because they generate only text and lack visual signals during deco…
RELIC: Interactive Video World Model with Long-Horizon Memory
Yicong Hong, Yiqun Mei, Chongjian Ge +11
A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approa…