11 papers
BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems
Encheng Su, Pengze Li, Ziheng Hua +11
Multi-agent collaboration has emerged as a critical paradigm for tackling complex, long-horizon tasks; however, while coordination protocols continue to advance, systemic failures…
PROTEAN: Beyond De Novo Generation - Can LLM Agents Perform Text-Guided Protein Structure Editing?
Encheng Su, Xinping Liu, Yizhou Wang +11
Generative AI has achieved remarkable success in de novo protein design, yet protein engineering typically begins with existing, characterized proteins. The primary demand is targe…
Coupled Harness--Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su +8
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library…
DAPD: Dual-Anchored Policy Distillation
Jianyu Wu, Yizhou Wang, Encheng Su +2
On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a privilege ill…
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Chen Tang, Yizhou Wang, Jianyu Wu +26
Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and pe…
S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
Encheng Su, Jianyu Wu, Jinouwen Zhang +9
Long-horizon memory question answering often requires sparse evidence from heterogeneous histories, including events, object states, visual observations, temporal relations, and ca…
SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence
Encheng Su, Jianyu Wu, Chen Tang +9
As large language models (LLMs) transition from general knowledge retrieval to complex scientific discovery, their evaluation standards must also incorporate the rigorous norms of…
UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis
Junzhi Ning, Wei Li, Cheng Tang +24
Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central to medical AI. Most existing sy…
CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
Han Deng, Yuan Meng, Shixiang Tang +2
Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or hig…
Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
Xinzhu Ma, Cheng Wang, Chen Tang +5
Recovering CAD models from point clouds requires reconstructing their topology and sketch-based extrusion primitives. A dominant paradigm for representing sketches involves implici…
GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning
Yanzhou Su, Tianbin Li, Jiyao Liu +15
Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This pape…