Tracked topic
…a new benchmark with expert-resynthesized data. Generated by Qwen/Qwen2.5-Coder-32B-Instruct This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target…
…Bench (IA-Bench), a benchmark covering four core image agent capabilities : Plan , Reason , Search , and Memory . Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Fine-grained visual reasoning remains challenging for vision-language models , especially when small but critical visual cues are buried in high-resolution images. Existing…
…Across three model families (Qwen3, Gemma-3, OLMo-3.1), mean-ablating the top LOCOS heads on the NoLiMa non-literal retrieval benchmark collapses ROUGE-L at lower head counts than prior…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Recent feedforward 3D reconstruction methods predict point map s and estimate global 3D geometry remarkably well. However, their predictions still exhibit inaccurate local surface…
…Tested across dense and MoE families (Qwen3.5, Gemma-4, gpt-oss), securing massive surges on frontier benchmarks—including up to a +22.4% jump on categorized Omni-MATH Level 4, +9…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on…
…7B and Qwen3-Omni-30B on OmniVideo-100K yields performance gains of up to 20.59% on OmniVideo-Test , demonstrating strong generalization (up to 12.64% improvements) across established benchmarks like Daily…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation can cost…
…pediatric epilepsy treatment decisions by adapting to local prescribing practices and providing uncertainty-based deferral signals for low-confidence cases. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Specialist epilepsy expertise is…