3 citations · 6 across the 16 of their papers we have counts for
21 papers
The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
Sijie Zhao, Zeqi Zhou, Heli Qi +6
Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a benchmark. We show that this loop can be handed to…
EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations
Heli Qi, Zeqi Zhou, Jingjun Yi +5
Remote sensing images often carry composite degradations, in which haze, cloud, noise, blur, low light, and low resolution coexist. Restoring them requires deciding which tool to a…
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Dingyuan Dai, Heli Qi, Lei Liu +28
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized int…
Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases
Rui Yang, Weihao Xuan, Yi Lin +23
Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practice, including progressive discl…
Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus
Yuheng Lu, Qingcheng Zeng, Heli Qi +6
Deep research agents are increasingly evaluated on their ability to search for evidence, reason over retrieved sources, and produce grounded answers. Existing browsing benchmarks,…
Knowledge Index of Noah's Ark
Sheng Jin, Minghao Liu, Yunze Xiao +24
Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotation that permits lazy consen…
Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
Junjue Wang, Weihao Xuan, Heli Qi +7
Operational disaster response goes beyond damage assessment, requiring responders to integrate multi-sensor signals, reason over road networks, populations and key facilities, plan…
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Fang Wu, Weihao Xuan, Heli Qi +26
Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries…
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Qingcheng Zeng, Yuheng Lu, Zeqi Zhou +6
Code-switching is a pervasive linguistic phenomenon in global communication, yet modern information retrieval systems remain predominantly designed for, and evaluated within, monol…
The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
Weihao Xuan, Qingcheng Zeng, Heli Qi +3
Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamen…
Toward Global Large Language Models in Medicine
Rui Yang, Huitao Li, Weihao Xuan +48
Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed…
TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots
Tianyu Liu, Weihao Xuan, Hao Wu +15
Advances in AI have introduced several strong models in computational pathology to usher it into the era of multi-modal diagnosis, analysis, and interpretation. However, the curren…
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Fang Wu, Weihao Xuan, Heli Qi +4
Although RLVR has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…
VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking
Shunyu Liu, Minghao Liu, Huichi Zhou +31
Recent advances have showcased the extraordinary capabilities of Large Language Model (LLM) agents in tackling web-based information-seeking tasks. However, existing efforts mainly…
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
Weihao Xuan, Qingcheng Zeng, Heli Qi +2
Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models expr…
DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
Junjue Wang, Weihao Xuan, Heli Qi +8
Large vision-language models (VLMs) have made great achievements in Earth vision. However, complex disaster scenes with diverse disaster types, geographic regions, and satellite se…
DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
Weihao Xuan, Junjue Wang, Heli Qi +5
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains li…
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
Weihao Xuan, Rui Yang, Heli Qi +29
Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingui…
Segment Anything with Multiple Modalities
Aoran Xiao, Weihao Xuan, Heli Qi +3
Robust and accurate segmentation of scenes has become one core functionality in various visual recognition and navigation tasks. This has inspired the recent development of Segment…
CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
Aoran Xiao, Weihao Xuan, Heli Qi +5
The recent Segment Anything Model (SAM) has demonstrated remarkable zero-shot capability and flexible geometric prompting in general image segmentation. However, SAM often struggle…