8 papers
ParallelWorld: Test-Time Scaling for Agentic Embodied Reasoning
Min Chen, Shengjun Zhang, Yuxin Li +4
Embodied AI has emerged as a key paradigm for autonomous systems operating in complex physical environments. While end-to-end models have established strong local capabilities for…
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
Shengjun Zhang, Zhang Zhang, Simin Huang +11
Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between…
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
Chensheng Dai, Shengjun Zhang, Yifan Li +3
Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computationa…
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
Tao Yu, Yujia Yang, Haopeng Jin +17
Traditional video retrieval benchmarks focus on matching precise descriptions to closed video pools, failing to reflect real-world searches characterized by fuzzy, multi-dimensiona…
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Shengjun Zhang, Zhang Zhang, Chensheng Dai +1
Recent reinforcement learning has enhanced the flow matching models on human preference alignment. While stochastic sampling enables the exploration of denoising directions, existi…
Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
Zhan Zhang
Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a p…
Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
Zhongxi Qiu, Zhang Zhang, Yan Hu +2
This paper explores optimal data selection strategies for Reinforcement Learning with Verified Rewards (RLVR) training in the medical domain. While RLVR has shown exceptional poten…
Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
Yujie Chen, Haotong Qin, Zhang Zhang +3
State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-di…