Search

直接匹配不多,已補上最新動態。

Tag: #mllms3 results

MathSpatial Exposes MLLMs' Spatial Reasoning Gap

MathSpatial Exposes MLLMs' Spatial Reasoning Gap

MLLMs excel in perception but fail mathematical spatial reasoning, scoring under 60% on tasks humans solve at 95% accuracy. MathSpatial introduces a framework with MathSpatial-Bench (2K problems), MathSpatial-Corpus (8K training data), and MathSpatial-SRT for structured reasoning. Fine-tuning Qwen2.5-VL-7B achieves strong results with 25% fewer tokens.

ArXiv AIResearchFeb 13#research#mathspatial#qwen
MLLMs Survey on Chart Fusion

MLLMs Survey on Chart Fusion

Survey organizes MLLM evolution for chart understanding via multimodal fusion. Introduces taxonomy of tasks and datasets. Highlights limitations in perception and reasoning, suggesting alignment and RL enhancements.

ArXiv AIResearchFeb 12#research#mllms#survey
Ox Alpha:神秘模型公開亮相

Ox Alpha:神秘模型公開亮相

Ox Alpha 是一款透過 OpenRouter 與 OpenCode 提供的匿名模型,具備 100 萬 token 上下文、圖片與影片輸入、工具呼叫及免費使用等能力。早期測試顯示其推理與程式設計表現強勁,但開發者、參數量、訓練資料與正式基準排名仍未獲確認。