13 papers
SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
SciForge Team, Zhangyang Gao, Minghao Fang +10
Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet genera…
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
Tingyu Li, Le Zhou, Siyuan Li +5
Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in comp…
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
Bo Yin, Xiaobin Hu, Chengming Xu +6
Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evi…
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
Jingxuan Wei, Xi Bai, Shan Liu +8
Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a f…
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Jinhang Xu, Qiyuan Zhu, Yujun Wu +11
LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers ope…
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
Bihui Yu, Xinglong Xu, Junjie Jiang +6
A LaTeX manuscript that compiles without error is not necessarily publication-ready. The resulting PDFs frequently suffer from misplaced floats, overflowing equations, inconsistent…
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
Yujun Wu, Dongxu Zhang, Xinchen Li +11
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In par…
AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories
Xue Xia, Chengkai Yao, Mingyu Tsoi +10
Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tigh…
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
Xiangxiang Zhang, Caijun Jia, Siyuan Li +9
Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent M…
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Chenkai Pan, Xinglong Xu, Yuhang Xu +6
Reliably transferring specialized human knowledge from text into large language models remains a fundamental challenge in artificial intelligence. Fine-tuning on domain corpora has…
HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts
Wenxuan Huang, Mingyu Tsoi, Yanhao Huang +10
Single-cell perturbation studies face dual heterogeneity bottlenecks: (i) semantic heterogeneity--identical biological concepts encoded under incompatible metadata schemas across d…
Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning
Tingyu Li, Zheng Sun, Jingxuan Wei +4
Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving lar…
Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
Juanxi Tian, Siyuan Li, Conghui He +2
Current multimodal models aim to transcend the limitations of single-modality representations by unifying understanding and generation, often using text-to-image (T2I) tasks to cal…