Model Detail
Rose-1.5-Medium
—Rose-1.5-Medium is a code generation model with 49M parameters released by GODELEV. Distributed under the permissive apache-2.0 license.
Rose-1.5-Medium ships with 49M parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Rose-1.5-Medium is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos
arXiv:2608.29003v1 Announce Type: cross Abstract: In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assumptions. In this work, we propose Robust Semantic-aware Gaussian Splatting SLAM (RoSe-SLAM), to addres
ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models
arXiv:2606.19965v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts. How reliably can a model turn the same visual evidence into the action re
RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
arXiv:2510.06143v2 Announce Type: replace Abstract: LLMs are powerful generators of synthetic data, which are used for training smaller, specific models. This is especially valuable for low-resource languages, where human-labelled data is scarce but LLMs can still produce high-quality text. However,
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
arXiv:2605.03720v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains largely undere
AI traffic to US retailers rose 393% in Q1, and it’s boosting their revenue too
Adobe says AI traffic to U.S. retail sites also jumped 269% in March, with visitors converting better and generating more revenue than non-AI shoppers.
ROSE: An Intent-Centered Evaluation Metric for NL2SQL
arXiv:2604.12988v1 Announce Type: cross Abstract: Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasingly unreliable. It is sensitive to syntactic variation, ignores that questions may admit multiple int
