…This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self…
…We also curate VideoKR-Eval, a new expert-annotated benchmark where questions require genuine video understanding and knowledge-intensive reasoning rather than textual shortcuts. Our experiments show that, under a standard SFTrightarrowGRPO…
…In this work, we systematically study MoE compression in large-scale pretraining, focusing on three key questions: whether pruning provides a better initialization than training from scratch, how expert compression choices affect…
…View arXiv page View PDF Add to collection Community This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers were recommended…
…AI-generated summary Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question…
…Violet Xiang , , , , Abstract ExpRL uses human-written question-answer data as reward scaffolds to provide automated reinforcement learning priming for language models, outperforming traditional methods on math reasoning tasks. Generated by Qwen…
…View arXiv page View PDF GitHub 1 Add to collection Community Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will…
…This bottleneck limits rapid exploration and raises a fundamental question: how much interpretable structure is already visible from activation geometry before training another neural dictionary? Our intuition is simple: many interpretable directions…
…We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community. View arXiv page…
…In this work, we study LLM continual post-training through three questions: What drives forgetting? When do sequentially acquired capabilities transfer or interfere? How can compatibility be used to control update integration…