Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile drivi...
We study post-training for dynamically routed mixture-of-experts (MoE) models, focusing on integrating independently optimized specialists while keeping consolidation efficient. Our approach combines calibrated multi-teacher on-policy distillation (C-MOPD), which matches each selected teacher on a local Top-$K$ support...
Yue He, Jia-Hui Hu, Sha-Man Tang et al.· 0 citations
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generati...
The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on general and reasoning tasks. However, existing fast-slow reasoning paradigms mainly regulate textual reasoning length, while visual computation introduce...
Quan-Lin Chen, Xiu-Wei Chen, Kun Xiang et al.· 0 citations
To stream long videos while maintaining visual quality and temporal consistency, Self Forcing mitigates exposure bias through self-rollout training on self-generated histories with key-value (KV) caching. To keep memory manageable, it detaches historical caches, preserving forward dependencies between chunks but severi...
Dong-Bin Zhang, Chao-Da Zheng, Kang-Jie Chen et al.· 0 citations
RoXDrive is introduced, a plug-and-play closed-loop RL framework that enables reliable policy optimization by identifying action-faithful world-model rollouts and an Action-Vision Faithfulness Evaluator for inverse dynamics estimation with geometry-aware auxiliary trajectory supervision, enabling long-horizon assessmen...
Hong-Bin Lin, Chao-Da Zheng, Yi-Ming Yang et al.· arXiv.org· 1 citation
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generati...
Qi-Ze Yu, Lian-Rui Fan, Bo-Yu Chen et al.· 0 citations
This work presents VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis, and introduces robust geometry conditioning, combining training-time regularization with inference-time guidance for improved robustness.
X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning, is introduced.
Hao-Jun Zhang, Yi Zou, Min Chen et al.· 0 citations
Despite its compact active-parameter budget, Turing-20B-A2B achieves, at the base-model stage, overall general capability exceeding Qwen3-8B Base and approaching Qwen3.5-9B Base, while maintaining strong long-context performance and favorable prefill-latency scaling.
Yu-Heng Zhang, Yi-Zhao Wang, Daijun Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.