Developing Graphical User Interface (GUI) Agents faces two key challenges that hinder their effectiveness. First, existing agents lack robust reasoning capabilities, relying primarily on single-step operations and failing to incorporate reflective learning mechanisms. This usually leads to errors being repeated in the execution of complex, multi-step tasks. Most current systems rely very much on textual… →

Large reasoning models are developed to solve difficult problems by breaking them down into smaller, manageable steps and solving each step individually. The models use reinforcement learning to enhance their reasoning abilities and develop very detailed and logical solutions. However, while this method is effective, it has its challenges. Overthinking and error in missing or… →

Developing effective multi-modal AI systems for real-world applications requires handling diverse tasks such as fine-grained recognition, visual grounding, reasoning, and multi-step problem-solving. Existing open-source multi-modal language models are found to be wanting in these areas, especially for tasks that involve external tools such as OCR or mathematical calculations. The abovementioned limitations can largely be attributed… →

The rapid growth of digital platforms has brought image safety into sharp focus. Harmful imagery—ranging from explicit content to depictions of violence—poses significant challenges for content moderation. The proliferation of AI-generated content (AIGC) has exacerbated these challenges, as advanced image-generation models can easily create unsafe visuals. Current safety systems rely heavily on human-labeled datasets, which… →