…model achieves only 58.6% accuracy, and a 34.9-point gap between open-weight and proprietary models highlights substantial room for improvement in complex chart and table understanding . We release our…
…The model and code will be publicly released at https://github.com/H-EmbodVis/HERMESV2. View arXiv page View PDF Project page GitHub 61 Add to collection Community Driving world models serve…
…Our resulting model, SearchSwarm-30B-A3B , achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH , the best results among all models of comparable scale. We will release our harness, model…
…https://github.com/Xrvitd/ ComboStoc View arXiv page View PDF Project page GitHub 38 Add to collection Community Today we're releasing ComboStoc , a simple new training strategy for diffusion generative models…
…We will release our code and models at: https://github.com/L-CodingSpace/semi- dpo View arXiv page View PDF Project page Add to collection Community Project Page: https://liming-ai.github…
Papers arxiv:2605.22771 Reducing Political Manipulation with Consistency Training Published on May 28 Submitted by Long Phan on May 29 Center for AI Safety Authors: , , , , , Abstract Large language models demonstrate systematic…
…even with 12.5% of experts, it retains near full-model performance, while a matched standard MoE degrades sharply. We’re releasing the model, matched baseline, code, technical report, and an interactive…
Papers arxiv:2605.06548 Continuous Latent Diffusion Language Model Published on May 7 Submitted by taesiri on May 8 #3 Paper of the day ByteDance Seed Authors: Hongcan Guo , , , , , , , , , Guoqiang Wei , Abstract…
…Experimental validation demonstrates significant performance improvements for models trained on our data. All datasets are publicly released to advance the field of marine artificial intelligence and empower domain-specific MLLMs. View arXiv…
…Evaluations across 10 state-of-the-art LLMs, including closed and open-source models, show that models can often select a plausible object, but fail to identify the correct parts, their affordances…