activity
20232026
most citedLAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

40 citations · 45 across the 13 of their papers we have counts for

collaborators
Showing 2026Show all

7 papers · 1 filter

cs.LG2026

Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries

Chunlei Shi, Jiong Wang, Yi-Lin Wei +4

Accurate regional near-surface temperature forecasting is fundamental to short-range weather services and downstream risk assessment. Existing deep learning-based regional forecast…

cs.CL2026

Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams

Fengxiang Wang, Qiuyang Yu, Yueying Li +14

Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains i…

cs.CL2026

AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification

Haobo Li, Eunseo Jung, Wenxiao Zhao +8

Recent advances in large language models (LLMs) have enabled AI systems to assist scientific research and peer review. However, an essential capability for reliable AI-assisted sci…

cs.AI2026

Agents-K1: Towards Agent-native Knowledge Orchestration

Zongsheng Cao, Bihao Zhan, Jinxin Shi +25

Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstract…

cs.MM2026

LangRetrieval: Language-Guided Self-Evolving Satellite-to-Radar Retrieval via CSI-Driven Reward

Chunlei Shi, Junming Hou, Yi-Lin Wei +5

Satellite-to-radar (S2R) retrieval estimates ground radar precipitation from geostationary satellite observations, providing a critical solution for precipitation monitoring in rad…

physics.geo-ph2026

TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology

Feng Liu, Jian Xu, Xin Cui +11

Modern seismic networks resolve earthquake sequences in unprecedented detail, yet explaining how large earthquakes emerge from evolving fault systems remains difficult. We introduc…

cs.AI2026

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Shiyang Feng, Runmin Ma, Xiangchao Yan +53

We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architec…