The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos

The introduction of OS-Sentinel marks a significant advancement in enhancing the safety of mobile GUI agents powered by Vision-Language Models (VLMs). This framework aims to address critical safety concerns, such as system compromise and privacy leakage, by utilizing a hybrid validation approach within a dynamic sandbox environment called MobileRisk-Live, which includes realistic operational trajectories with detailed annotations.

A new framework called Speculative Verdict (SV) has been introduced to enhance the reasoning capabilities of Vision-Language Models (VLMs) when dealing with complex, information-rich images. SV operates in two stages: the draft stage, where small VLMs generate diverse reasoning paths, and the verdict stage, where a stronger VLM synthesizes these paths to produce accurate answers efficiently.

Recent advancements in Vision-Language Models (VLMs) have led to the development of Training-free Dual Hyperbolic Adapters (T-DHA), a novel adaptation method that enhances cross-modal reasoning without requiring extensive training resources. This method utilizes hyperbolic space to better represent hierarchical relationships between semantic concepts, improving both representation and discrimination capabilities.

A new benchmark called Tri-Bench has been introduced to assess the reliability of Vision-Language Models (VLMs) in spatial reasoning tasks, particularly under conditions of camera tilt and object interference. The benchmark evaluates four recent VLMs using a fixed prompt and measures their accuracy against 3D ground truth, revealing an average accuracy of approximately 69%.

A novel method called CLIP-UP has been introduced to enhance Vision-Language Models (VLMs) by detecting unanswerable questions in Visual Question Answering (VQA) tasks. This method utilizes CLIP-based similarity measures to assess question-image alignment, allowing models to refrain from providing incorrect answers to questions about non-existent objects in images.

A new task called Cross-View Point Correspondence (CVPC) has been proposed to enhance spatial understanding in Vision-Language Models (VLMs). This task is supported by the introduction of CrossPoint-Bench, a benchmark designed to evaluate models based on human cognitive processes of perception, reasoning, and correspondence. The evaluation reveals that current state-of-the-art models, such as Gemini-2.5-Pro, significantly lag behind human performance, with a 54.65% accuracy gap.

The introduction of MedGR$^2$, a novel framework for Generative Reward Learning in medical reasoning, addresses the critical shortage of high-quality, expert-annotated data that hampers the application of Vision-Language Models (VLMs) in medicine. This framework enables the automated creation of multi-modal medical data, enhancing the training process for both Supervised Fine-Tuning and Reinforcement Learning.

The introduction of AutoNeural marks a significant advancement in the design of Vision-Language Models (VLMs) specifically optimized for Neural Processing Units (NPUs). This architecture addresses the inefficiencies of existing VLMs on edge AI hardware by utilizing a MobileNetV5-style backbone and integrating State-Space Model principles, enabling stable integer-only inference.