…Hao Wang , , , , , , Abstract X2SAM is a unified multimodal model that extends segmentation capabilities from images to videos while supporting conversational instructions and visual prompts for both modalities. AI-generated summary Multimodal Large…
…To better understand the political rhetoric from various movements, ranging from left to right, we propose a transformer-based model capable of projecting the political orientation of a text on a continuous…
…AI-generated summary While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Media compression standards have reached a plateau in terms of the rate-distortion-complexity trade-off , limiting the ability to offload expensive AI perception…
…AI-generated summary The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of…
…Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations , where a…
…We present Ultralytics YOLO 26, a unified real-time vision model family that addresses these limitations through coordinated architecture and training advances. YOLO 26 uses a dual-head design for native NMS…
…Xiyu Ren , , Yiming Du , , , , , , , , , , , Abstract A new benchmark evaluates memory capabilities in vision-language models through multi-session conversations, revealing limitations of both long-context and memory-augmented approaches. AI-generated summary…
…tracking in videos, performing poorly even when human-level capabilities are required, and existing agentic approaches do not effectively address these limitations. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Understanding a…
…chart parsers remain limited to narrow chart families. Across all models, radar charts and hand-drawn scenarios stay especially challenging. These findings show that ChartArena exposes clear capability gaps and provides a…