Xiangchao Yan

Intern-S2-Preview: Scientific Agentic Foundation Model

Lei Bai, Jiaqi Cao, Chiyu Chen, Guanzhou Chen et autres

Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal …

Towards Physics-Faithful Generation of Scientific Diagrams

Minghui Zhang, Jinxin Shi, Yifan Chang, Liangliang Zhao et autres

Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on …

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Yifan Zhou, Qihao Yang, Yan Li, Donggang Li et autres

Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), …

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Yifan Zhou, Qihao Yang, Yan Li, Donggang Li et autres

Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), …

cn, us, ca, fi (code pays fourni par la source)

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui et autres

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure …

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui et autres

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure …

Agents-K1: Towards Agent-native Knowledge Orchestration

Zongsheng Cao, Bihao Zhan, Jinxin Shi, Jiong Wang et autres

Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat \texttt{cites} edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To …

Agents-K1: Towards Agent-native Knowledge Orchestration

Zongsheng Cao, Bihao Zhan, Jinxin Shi, Jiong Wang et autres

Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat \texttt{cites} edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To …

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Shangheng Du, Xiangchao Yan, Jinxin Shi, Zongsheng Cao et autres

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isolation, memoryless search, and lack of hierarchical …

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Shangheng Du, Xiangchao Yan, Jinxin Shi, Zongsheng Cao et autres

Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isolation, memoryless search, and lack of hierarchical …

cn, ca (code pays fourni par la source)

Bi3D++: Hybrid Bi-Domain Active Learning for Cross-Domain 3D Object Detection

Jiakang Yuan, Xiangchao Yan, Botian Shi, Bo Zhang et autres

Domain adaptation has recently been widely explored for 3D detection. Previous works mainly use unsupervised domain adaptation (UDA) to address domain discrepancies. Despite notable improvements, their performance still largely trails models trained with fully annotated target data, due to larger domain gaps …

cn (code pays fourni par la source)

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

Renqiu Xia, Haoyang Peng, Hancheng Ye, Mingsheng Li et autres

Charts are common in literature across various scientific fields, conveying rich information easily accessible to readers. Current chart-related tasks focus on either chart perception that extracts information from the visual charts, or chart reasoning given the extracted data, e.g. in a tabular …

cn (code pays fourni par la source)