7 papers
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
Zhefan Rao, Meng Chu, Xuan Zhang +93
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction require…
CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
Zhaolong Su, Yujin Han, Feng Wang +3
Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing against a…
From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models
Bingqing Jiang, Li Luo, Zichao Yu +3
On-policy distillation (OPD) specializes pretrained video diffusion models through teacher supervision along the student's own generation trajectory. Although large video models ar…
Triplet-Block Diffusion RWKV
Ke Lin, Yiyang Luo, Zhaolong Su +2
Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and discrete diffusion models e…
How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings
Zhiheng Li, Zongyang Ma, Jiaxian Chen +12
Document parsing models are improving rapidly, but existing benchmarks are still insufficient for a comprehensive evaluation of their capabilities. We introduce PureDocBench, a ben…
FedUMM: A General Framework for Federated Learning with Unified Multimodal Models
Zhaolong Su, Leheng Zhao, Xiaoying Wu +2
Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically…
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
Zhaolong Su, Wang Lu, Hao Chen +2
Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental incons…