Seed1.5-VL Technical Report

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

Image captioning has long been a pivotal task in visual understanding, with recent advancements in vision-language models (VLMs) significantly enhancing the ability to generate detailed image captions. However, the evaluation of detailed image captioning remains underexplored due to outdated evaluation metrics and coarse annotations. In this paper, we introduce DeCapBench along with a novel metric, DCScore, specifically designed for detailed captioning tasks. DCScore evaluates hallucinations and fine-grained comprehensiveness by deconstructing responses into the smallest self-sufficient units, termed primitive information units, and assessing them individually. Our evaluation shows that DCScore aligns more closely with human judgment than other rule-based or model-based metrics. Concurrently, DeCapBench exhibits a high correlation with VLM arena results on descriptive tasks, surpassing existing benchmarks for vision-language models. Additionally, we present an automatic fine-grained feedback collection method, FeedQuill, for preference optimization based on our advanced metric, showing robust generalization capabilities across auto-generated preference data. Extensive experiments on multiple VLMs demonstrate that our method not only significantly reduces hallucinations but also enhances performance across various benchmarks, achieving superior detail captioning performance while surpassing GPT-4o.

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

MOBA games, e.g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far. However, these AI systems mainly focus on how to compete with humans, less on exploring how to collaborate with humans. To this end, this paper makes the first attempt to investigate human-agent collaboration in MOBA games. In this paper, we propose to enable humans and agents to collaborate through explicit communication by designing an efficient and interpretable Meta-Command Communication-based framework, dubbed MCC, for accomplishing effective human-agent collaboration in MOBA games. The MCC framework consists of two pivotal modules: 1) an interpretable communication protocol, i.e., the Meta-Command, to bridge the communication gap between humans and agents; 2) a meta-command value estimator, i.e., the Meta-Command Selector, to select a valuable meta-command for each agent to achieve effective human-agent collaboration. Experimental results in Honor of Kings demonstrate that MCC agents can collaborate reasonably well with human teammates and even generalize to collaborate with different levels and numbers of human teammates. Videos are available at https://sites.google.com/view/mcc-demo.

Invertible Image Dataset Protection

Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by the competitors after using them online. We propose a novel solution for dataset protection in this scenario by robustly and reversibly transform the images into adversarial images. We develop a reversible adversarial example generator (RAEG) that introduces slight changes to the images to fool traditional classification models. Even though malicious attacks train pirated models based on the defensed versions of the protected images, RAEG can significantly weaken the functionality of these models. Meanwhile, the reversibility of RAEG ensures the performance of authorized models. Extensive experiments demonstrate that RAEG can better protect the data with slight distortion against adversarial defense than previous methods.

Hiding Images into Images with Real-world Robustness

The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks. To solve this problem, we introduce a generative deep network based method for hiding images into images while assuring high-quality extraction from the destructive synthesized images. An embedding network is sequentially concatenated with an attack layer, a decoupling network and an image extraction network. The addition of decoupling network learns to extract the embedded watermark from the attacked image. We also pinpoint the weaknesses of the adversarial training for robustness in previous works and build our improved real-world attack simulator. Experimental results demonstrate the superiority of the proposed method against typical digital attacks by a large margin, as well as the performance boost of the recovered images with the aid of progressive recovery strategy. Besides, we are the first to robustly hide three secret images.

Unsupervised Classification of Street Architectures Based on InfoGAN

Street architectures play an essential role in city image and streetscape analysing. However, existing approaches are all supervised which require costly labeled data. To solve this, we propose a street architectural unsupervised classification framework based on Information maximizing Generative Adversarial Nets (InfoGAN), in which we utilize the auxiliary distribution $Q$ of InfoGAN as an unsupervised classifier. Experiments on database of true street view images in Nanjing, China validate the practicality and accuracy of our framework. Furthermore, we draw a series of heuristic conclusions from the intrinsic information hidden in true images. These conclusions will assist planners to know the architectural categories better.