11 papers
Sparse Multi-Stage Expert-Agent Routing for Complex Clinical Reasoning
Sike Xiang, Shuang Chen, Qian sun +3
Complex clinical reasoning requires models to update diagnostic hypotheses as new evidence emerges and to coordinate different medical specialities under limited consultation resou…
PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle
Yicheng Xiao, Haoxuan Ma, Caorui Li +7
Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region Segmentation and Region Understanding, extending multimodal interaction from wh…
AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally
Shaowen Wang, Yuke Zheng, Tansheng Zhu +4
Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform frequency schedule and scaling a…
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
Shijue Huang, Hangyu Guo, Guanting Dong +8
Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visual context. Two bottlenecks l…
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
ZhiYuan Feng, Yu Deng, Ruichuan An +11
In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean task specification. Such re…
Checkup2Action: A Multimodal Clinical Check-up Report Dataset for Patient-Oriented Action Card Generation
Sike Xiang, Shuang Chen, Kevin Qinghong Lin +4
Routine clinical check-up reports combine laboratory measurements, physiological assessments, imaging findings and visually structured information, but rarely tell patients what to…
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
Qianshan Wei, Yishan Yang, Siyi Wang +12
Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Exp…
Revealing the Learning Dynamics of Long-Context Continual Pre-training
Yupu Liang, Shuang Chen, Guanwei Zhang +2
Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migr…
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
Shuang Chen, Yue Guo, Yimeng Ye +7
Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to over…
Interleaving Reasoning for Better Text-to-Image Generation
Wenxuan Huang, Shuang Chen, Zheyong Xie +15
Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction followin…
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Shuang Chen, Yue Guo, Zhaochen Su +7
Inspired by the remarkable reasoning capabilities of Deepseek-R1 in complex textual tasks, many works attempt to incentivize similar capabilities in Multimodal Large Language Model…