Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording...
Xiang-Yun Zeng, Yuan-Dong Yang, Zhi-Qiu Zhang et al.· 1 citation
GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows. However, the diversity of available trajectories is constrained by the applications, interface states, and workflows accessible in the underlying environments...
Cheng Yang, Yi-Fan Wu, Yu-Tao Huang et al.· 0 citations
This work proposes Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding, which outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.
Haojie Huang, Xin-Lei Yu, Cheng-Ming Xu et al.· 3 citations
The results chart an engineering path toward recursive self-improvement, in which humans distill the principles of model building, agents operationalize them through evidence-driven experimentation, and each generation of AI becomes a more capable architect of the next.
Cheng Yang, Jiayang Lyu, Shang Liu et al.· 0 citations
Reinforcement learning (RL) improves reasoning, but its performance depends on the policy from which training begins. We study on-policy distillation (OPD) as a preparation stage for RL and ask whether its benefits extend beyond improvements in the distilled model's initial accuracy. Under shared RL settings, students...
Human evaluation confirms that RefCaptioner achieves the best overall performance among the open-source models while remaining competitive on standard video captioning benchmarks, and human evaluation further confirms that its captions are preferred by annotators and enable more source-faithful video reconstruction wit...
Teng-Fei Liu, Yang Shi, Yu-Ran Wang et al.· arXiv.org· 0 citations
The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather than merely equipping them with a sophisticated yet inefficient reasoning paradigm. In this work, we rethink agentic visual reasoning through two key dimensions of tool us...
Qixun Wang, Yang Shi, Le-Tian Cheng et al.· arXiv.org· 0 citations
LaMem-VLA is introduced, a latent-memory-native framework that reconstructs historical experience into latent memory tokens and directly interweaves them with VLA reasoning, and enables memory to directly participate in VLA reasoning and guide action generation under a bounded context.
Hongyu Qu, Jianzhe Gao, Xiaobin Hu et al.· 1 citation
This work introduces Latent On-Policy Self-Distillation (LOPD), which, rather than proposing another hand-crafted OPSD variant with a newly prescribed form of privileged context, makes the teacher's privileged context itself learnable end-to-end from experience.
Gui-Min Zhang, Jiayang Lyu, Ran Sun et al.· 6 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
