16 papers
Sprout: Building Dynamic Memory While Reasoning for Agentic Video Understanding
Wei Chen, Xuanyu Zheng, Yancheng Long +6
Long video understanding relies on video memory to overcome the context limits of multimodal large language models. Existing methods follow a build-then-reasoning pipeline: memory…
GSM: Efficient Language Modeling with Shared Global State
Yunao Zheng, Bin Wen, Xiaojie Wang +12
Improving language model efficiency requires not only cheaper operations but also eliminating redundant computation. We argue that effective modeling requires information accessibi…
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
Wenqi Liu, Shijie Ma, Yunxiao Wang +21
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang +13
Visual captioning requires models to capture visual content faithfully while minimizing both omission and hallucination. As the dominant paradigm for captioning, MLLMs have achieve…
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
Xingyu Lu, Jinpeng Wang, YiFan Zhang +12
We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model wit…
UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
Hongyang Wei, Bin Wen, Yancheng Long +22
We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing dif…
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
Wenqi Liu, Yunxiao Wang, Shijie Ma +14
In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To addres…
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
Yankai Yang, Yancheng Long, Hongyang Wei +12
Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as i…
SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
Yancheng Long, Yankai Yang, Hongyang Wei +12
Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Exi…
Kwai Keye-VL 1.5 Technical Report
Biao Yang, Bin Wen, Boyang Ding +58
In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Mode…
Thyme: Think Beyond Images
Yi-Fan Zhang, Xingyu Lu, Shukang Yin +17
Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance…
Kwai Keye-VL Technical Report
Kwai Keye Team, Biao Yang, Bin Wen +57
While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form vi…
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
Yi-Fan Zhang, Xingyu Lu, Xiao Hu +13
Multimodal Reward Models (MRMs) play a crucial role in enhancing the performance of Multimodal Large Language Models (MLLMs). While recent advancements have primarily focused on im…
VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
Xingyu Lu, Tianke Zhang, Chang Meng +14
Exponentially growing short video platforms (SVPs) face significant challenges in moderating content detrimental to users' mental health, particularly for minors. The dissemination…
InstructEngine: Instruction-driven Text-to-Image Alignment
Xingyu Lu, Yuhang Hu, YiFan Zhang +9
Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations…