5 papers
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
Yanqi Dai, Yuxiang Ji, Xiao Zhang +3
Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we identify a systematic lack of emph…
Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty
Yanqi Dai, Yong Wang, Zebin You +3
Visual instruction tuning is a key training stage of large multimodal models. However, when learning multiple visual tasks simultaneously, this approach often results in suboptimal…
MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents
Yanqi Dai, Huanran Hu, Lei Wang +3
Recently, Role-Playing Agents (RPAs) have garnered increasing attention for their potential to deliver emotional value and facilitate sociological research. However, existing studi…
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds
Lei Wang, Jianxun Lian, Yi Huang +5
Role-playing is a crucial capability of Large Language Models (LLMs), enabling a wide range of practical applications, including intelligent non-player characters, digital twins, a…
Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts
Jinqiang Long, Yanqi Dai, Guoxing Yang +4
As the research of Multimodal Large Language Models (MLLMs) becomes popular, an advancing MLLM model is typically required to handle various textual and visual tasks (e.g., VQA, De…