arXiv subjects

Chen Yue

Publications and source records attributed to Chen Yue.

5 recordsLinked to original sources

arXiv2026

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents' capability in driving this process, we present AutoResearchBench, a dedicated benchmark for autonomous scientific literature discovery. AutoResearchBench consists of two complementary task types: (1) Deep Research, which requires tracking down a specific target paper through a progressive, multi-step probing process, and (2) Wide Research, which requires comprehensively collecting a set of papers satisfying given conditions. Compared to previous benchmarks on agentic web browsing, AutoResearchBench is distinguished along three dimensions: it is research-oriented, calling for in-depth comprehension of scientific concepts; literature-focused, demanding fine-grained utilization of detailed information; and open-ended, involving an unknown number of qualified papers and thus requiring deliberate reasoning and search throughout. These properties make AutoResearchBench uniquely suited for evaluating autonomous research capabilities, and extraordinarily challenging. Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research, while many other strong baselines fall below 5%. We publicly release the dataset and evaluation pipeline to facilitate future research in this direction. We publicly release the dataset, evaluation pipeline, and code at https://github.com/CherYou/AutoResearchBench.

cs.AI↗

arXiv2025

Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work, we introduce MeasureBench, a benchmark on visual measurement reading covering both real-world and synthesized images of various types of measurements, along with an extensible pipeline for data synthesis. Our pipeline procedurally generates a specified type of gauge with controllable visual appearance, enabling scalable variation in key details such as pointers, scales, fonts, lighting, and clutter. Evaluation on popular proprietary and open-weight VLMs shows that even the strongest frontier VLMs struggle with measurement reading in general. We have also conducted preliminary experiments with reinforcement finetuning (RFT) over synthetic data, and find a significant improvement on both in-domain synthetic subset and real-world images. Our analysis highlights a fundamental limitation of current VLMs in fine-grained spatial grounding. We hope this resource and our code releases can help future advances on visually grounded numeracy and precise spatial perception of VLMs, bridging the gap between recognizing numbers and measuring the world.

cs.CV↗

arXiv2025

FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions

We conduct a moderate-scale contamination-free (to some extent) evaluation of current large reasoning models (LRMs) with some preliminary findings. We also release ROME, our evaluation benchmark for vision language models intended to test reasoning from visual clues. We attach links to the benchmark, evaluation data, and other updates on this website: https://flageval-baai.github.io/LRM-Eval/

cs.CL↗

arXiv2013

Estimating a graphical intra-class correlation coefficient (GICC) using multivariate probit-linear mixed models

Data reproducibility is a critical issue in all scientific experiments. In this manuscript, we consider the problem of quantifying the reproducibility of graphical measurements. We generalize the concept of image intra-class correlation coefficient (I2C2) and propose the concept of the graphical intra-class correlation coefficient (GICC) for such purpose. The concept of GICC is based on multivariate probit-linear mixed effect models. We will present a Markov Chain EM (MCEM) algorithm for estimating the GICC. Simulations results with varied settings are demonstrated and our method is applied to the KIRBY21 test-retest dataset.

stat.ME↗

arXiv2013

Parametrization of white matter manifold-like structures using principal surfaces

In this manuscript, we are concerned with data generated from a diffusion tensor imaging (DTI) experiment. The goal is to parameterize manifold-like white matter tracts, such as the corpus callosum, using principal surfaces. We approach the problem by finding a geometrically motivated surface-based representation of the corpus callosum and visualize the fractional anisotropy (FA) values projected onto the surface; the method applies to any other diffusion summary as well as to other white matter tracts. We provide an algorithm that 1) constructs the principal surface of a corpus callosum; 2) flattens the surface into a parametric 2D map; 3) projects associated FA values on the map. The algorithm was applied to a longitudinal study containing 466 diffusion tensor images of 176 multiple sclerosis (MS) patients observed at multiple visits. For each subject and visit the study contains a registered DTI scan of the corpus callosum at roughly 20,000 voxels. Extensive simulation studies demonstrate fast convergence and robust performance of the algorithm under a variety of challenging scenarios.

stat.AP↗