We note that our work focuses on architectural comparisons rather than competing with recent SLM developments (e.g., SmolLM, MobileLLM). Our analysis isolates the fundamental advantages of ...

Context windows are becoming a computational bottleneck. The longer an agent runs, the more tokens accumulate from retrieved documents, reasoning traces and conversation history, and the more memory ...

Abstract: Recent neural models for video captioning are typically built using a framework that combines a pre-trained visual encoder with a large language model(LLM) decoder. However, large language ...

This time, I have gathered four open models that claim to be "coding-specialized." While the lineup is varied, including Qwen-based and Gemma fine-tuned models, they all share one goal: to verify if ...

使用 1.7B 总共需 1.8G 显存。 用 0.6B 版可以再省 500MB 显存，但对速度的提升不大，因为计算瓶径在于 Predictor ...

Abstract: Chest X-ray report generation has attracted increasing research attention. However, most existing methods neglect the temporal information and typically generate reports conditioned on a ...

Gemma 4 12B is a new model in the Gemma 4 family announced by Google on June 3, 2026. It is positioned as an "encoder-free unified multimodal model optimized for laptops." The official blog (Google ...

Not bad for limited hardware ...