KJ
Kaiyu Jiang
cs.CVcs.AIcs.CLcs.LGcs.MM
On Valency
published · living versionsW_njafcqd3·v1 · currentpublished
VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
with Muxi Diao, Wenbin Xu, Lele Yang, Xuyang Ma +19
1 version
Preprints & journals
13 papers in the corpus · 2025–2026Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding2609.35497v1 · Wei Chen, Xuanyu Zheng, Yancheng Long et al.2026 · 0 citationsarXiv
GSM: Efficient Language Modeling with Shared Global State2609.33465v3 · Yunao Zheng, Bin Wen, Xiaojie Wang et al.2026 · 0 citationsarXiv
Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations2609.03426v2 · Yunao Zheng, Bin Wen, Xiaojie Wang et al.2026 · 0 citationsarXiv
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents2608.23329v2 · Wenqi Liu, Shijie Ma, Yunxiao Wang et al.2026 · 0 citationsarXiv
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning2605.28023v1 · Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang et al.2026 · 0 citationsarXiv
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL2602.22623v1 · Xingyu Lu, Jinpeng Wang, YiFan Zhang et al.2026 · 0 citationsarXiv
UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing2602.14186v1 · Hongyang Wei, Bin Wen, Yancheng Long et al.2026 · 0 citationsarXiv
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos2602.07801v4 · Wenqi Liu, Yunxiao Wang, Shijie Ma et al.2026 · 0 citationsarXiv
SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning2602.07458v4 · Yancheng Long, Yankai Yang, Hongyang Wei et al.2026 · 0 citationsarXiv
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models2602.07533v3 · Yankai Yang, Yancheng Long, Hongyang Wei et al.2026 · 0 citationsarXiv
Kwai Keye-VL 1.5 Technical Report2509.01563v3 · Biao Yang, Bin Wen, Boyang Ding et al.2025 · 0 citationsarXiv
Thyme: Think Beyond Images2508.11630v1 · Yi-Fan Zhang, Xingyu Lu, Shukang Yin et al.2025 · 0 citationsarXiv
InstructEngine: Instruction-driven Text-to-Image Alignment2504.10329v2 · Xingyu Lu, Yuhang Hu, YiFan Zhang et al.2025 · 0 citationsarXiv
Career total: 14 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.