❌

Normal view

Received — 10 September 2026 ⏭

FrontierChallenge: Evaluating Scientific Workflow Completion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Liangcai Su · Zhaopeng Feng · Zhuo Chen · Zhen Zhang · Xiang Lin · Ruilin Li · Handuo Zhang · Ning Wang · Kailong Wen · Yueqi Guo · Feng Xing · Yiling Guo · Brian Wang · Chenxiong Qian · Simon Shaolei Du · Lidong Bing · Xinyu Wang
10 September 2026 at 12:00
arXiv:2608.24979v2 Announce Type: replace Abstract: Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three agent scaffolds. Pass Rate measures the fraction of tasks satisfying the full-completion criterion, while Avg. Score captures partial progress. Each of the best-performing configurations completed only 20 of the 97 released tasks, yielding a Pass Rate of 20.6%. Partial progress translated especially poorly into complete delivery in analytical chemistry and electrochemistry/environment: Avg. Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%. Among non-passing Claude Code trajectories, 75.5% still ended with language claiming completion. Complementary HDS6 process scores correlate strongly with task outcomes, supporting FrontierChallenge as a benchmark of Heavy Duty Solver capabilities. These findings show that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered, highlighting the need to evaluate end-to-end workflow execution and the completeness of scientific deliverables together.

RAU: Reference-based Anatomical Understanding with Vision Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yiwei Li · Yikang Liu · Jiaqi Guo · Lin Zhao · Zheyuan Zhang · Xiao Chen · Boris Mailhe · Ankush Mukherjee · Terrence Chen · Shanhui Sun
10 September 2026 at 12:00
arXiv:2509.22404v2 Announce Type: replace-cross Abstract: Anatomical understanding, which is the ability to identify, localize, or segment anatomical structures, is critical in medical image analysis; however, its progress is constrained by the scarcity of expert-labeled data. A promising remedy is to leverage an annotated reference image to guide the interpretation of an unlabeled target. Although recent vision-language models (VLMs) exhibit non-trivial visual reasoning, their reference-based understanding and fine-grained localization remain limited. We introduce RAU, a framework for reference-based anatomical understanding with VLMs. We first show that a VLM learns to identify anatomical regions through relative spatial reasoning between reference and target images, trained on a moderately sized dataset. We validate this capability through visual question answering (VQA) and bounding box prediction. Next, we demonstrate that the VLM-derived spatial cues can be seamlessly integrated with the fine-grained segmentation capability of SAM2, enabling localization and pixel-level segmentation of small anatomical regions, such as vessel segments. Across two in-distribution and two out-of-distribution datasets, RAU consistently outperforms a SAM2 fine-tuning baseline using the same memory setup, yielding more accurate segmentations and more reliable localization. More importantly, its generalization ability to unseen modalities makes it scalable to unseen datasets, a property crucial for medical image applications. To the best of our knowledge, RAU is the first to explore the capability of VLMs for reference-based identification, localization, and segmentation of anatomical structures in medical images. Its promising performance highlights the potential of VLM-driven approaches for anatomical understanding in automated clinical workflows.
Received — 27 May 2026 ⏭

A visual analysis of the research dynamics of biomarkers for lung cancer screening

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Huange Zhu · Burong Li · Ranran Kong · Jun Yang · Zeqi Guo · Jiafeng Yin
26 May 2026 at 18:00

Clin Epigenetics. 2026 May 26;18(1):90. doi: 10.1186/s13148-026-02084-2.

ABSTRACT

BACKGROUND: Non-invasive biomarkers offer potential to improve risk stratification and early diagnosis of lung cancer, complementing low-dose computed tomography (LDCT) screening. This study employed bibliometric analysis to identify global research trends, collaborative networks, and future directions in lung cancer biomarker research. Publications on lung cancer biomarkers for screening were retrieved from the Web of Science Core Collection (WoSCC). Data processing and visualisation were performed using Citespace, VOSviewer, KH Coder, Latent Dirichlet Allocation (LDA) topic modelling, and the online bibliometric analysis platform. Burst detection analysis was performed to predict emerging research trends.

RESULTS: Analysis of 3636 publications revealed exponential growth in research output since 2014. International collaboration demonstrated a dual-core structure centred on China and the United States, with Chinese institutions showing high publication volumes and American institutions demonstrating greater citation influence. Journal citation mapping revealed three evolutionary phases: basic mechanisms-clinical translation-intelligent integration. LDA topic modelling identified 22 topics grouped into five core research directions: imaging and pathological diagnostic techniques; molecular and omics marker research; liquid biopsy and new detection technologies; clinical and translational medicine research; and tumour biology and treatment mechanisms. Burst detection analysis predicted future four priority areas: epigenetic studies centred on DNA methylation for risk prediction; treatment resistance and invasion mechanisms; liquid biopsy technology development; and targeted therapy clinical trials.

CONCLUSIONS: Lung cancer biomarker research has evolved towards multimodal, intelligent screening approaches. Future research priorities include DNA methylation-based markers, circulating microRNA signatures, and artificial intelligence-assisted diagnostic platforms to improve early detection accuracy and complement LDCT screening.

PMID:42185923 | DOI:10.1186/s13148-026-02084-2

Received — 2 April 2026 ⏭

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Iordanis Fostiropoulos · Muhammad Rafay Azhar · Abdalaziz Sawwan · Boyu Fang · Yuchen Liu · Jiayi Liu · Hanchao Yu · Qi Guo · Jianyu Wang · Fei Liu · Xiangjun Fan
1 April 2026 at 12:00
arXiv:2603.29112v1 Announce Type: new Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike traditional RecSys benchmarks that focus on item prediction accuracy, our benchmark evaluates how well LLMs can extract and verify user interests from engagement data. We propose two novel metric families: Interest Groundedness (IG), decomposed into precision and recall components to separately penalize hallucinated interest categories and reward coverage, and Interest Specificity (IS), which assesses the distinctiveness of verified LLM-predicted user profiles. We release a synthetic dataset constructed on real user interactions on a global short-form video platform. Our dataset contains both implicit and explicit engagement signals and rich textual descriptions. We validate our dataset fidelity against user surveys, and evaluate eight open-weight LLMs spanning 7B to 120B parameters. Our findings reveal performance bottlenecks in current LLMs, particularly their limited ability to accurately count and attribute engagement signals across heterogeneous interaction types.

SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kuangshi Ai · Haichao Miao · Kaiyuan Tang · Nathaniel Gorski · Jianxin Sun · Guoxi Liu · Helgi I. Ingolfsson · David Lenz · Hanqi Guo · Hongfeng Yu · Teja Leburu · Michael Molash · Bei Wang · Tom Peterka · Chaoli Wang · Shusen Liu
1 April 2026 at 12:00
arXiv:2603.29139v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled agentic systems that translate natural language intent into executable scientific visualization (SciVis) tasks. Despite rapid progress, the community lacks a principled and reproducible benchmark for evaluating these emerging SciVis agents in realistic, multi-step analysis settings. We present SciVisAgentBench, a comprehensive and extensible benchmark for evaluating scientific data analysis and visualization agents. Our benchmark is grounded in a structured taxonomy spanning four dimensions: application domain, data type, complexity level, and visualization operation. It currently comprises 108 expert-crafted cases covering diverse SciVis scenarios. To enable reliable assessment, we introduce a multimodal outcome-centric evaluation pipeline that combines LLM-based judging with deterministic evaluators, including image-based metrics, code checkers, rule-based verifiers, and case-specific evaluators. We also conduct a validity study with 12 SciVis experts to examine the agreement between human and LLM judges. Using this framework, we evaluate representative SciVis agents and general-purpose coding agents to establish initial baselines and reveal capability gaps. SciVisAgentBench is designed as a living benchmark to support systematic comparison, diagnose failure modes, and drive progress in agentic SciVis. The benchmark is available at https://scivisagentbench.github.io/.
Received — 26 March 2026 ⏭

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qirui Wang · Qi Guo · Yiding Sun · Junkai Yang · Dongxu Zhang · Shanmin Pang · Qing Guo
25 March 2026 at 12:00
arXiv:2603.22943v1 Announce Type: new Abstract: Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity.
Received — 5 March 2026 ⏭

FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jin Cui · Boran Zhao · Jiajun Xu · Jiaqi Guo · Shuo Guan · Pengju Ren
4 March 2026 at 13:00
arXiv:2511.19476v3 Announce Type: replace-cross Abstract: Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on heuristics lacking theoretical guarantees. Neither approach explicitly constrains distributional equivalence, largely because continuous distribution matching is considered inapplicable to discrete sampling. Moreover, prevalent metrics (e.g., MSE, KL, CE, MMD) cannot accurately capture higher-order moment discrepancies, leading to suboptimal coresets. In this work, we propose FAST, the first DNN-free distribution-matching coreset selection framework that formulates the coreset selection task as a graph-constrained optimization problem grounded in spectral graph theory and employs the Characteristic Function Distance (CFD) to capture full distributional information in the frequency domain. We further discover that naive CFD suffers from a "vanishing phase gradient" issue in medium and high-frequency regions; to address this, we introduce an Attenuated Phase-Decoupled CFD. Furthermore, for better convergence, we design a Progressive Discrepancy-Aware Sampling strategy that progressively schedules frequency selection from low to high, preserving global structure before refining local details and enabling accurate matching with fewer frequencies while avoiding overfitting. Extensive experiments demonstrate that FAST significantly outperforms state-of-the-art coreset selection methods across all evaluated benchmarks, achieving an average accuracy gain of 9.12%. Compared to other baseline coreset methods, it reduces power consumption by 96.57% and achieves a 2.2x average speedup, underscoring its high performance and energy efficiency.
Received — 25 February 2026 ⏭

FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Boran Zhao · Jin Cui · Jiajun Xu · Jiaqi Guo · Shuo Guan · Pengju Ren
24 February 2026 at 13:00
arXiv:2511.19476v2 Announce Type: replace-cross Abstract: Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on heuristics lacking theoretical guarantees. Neither approach explicitly constrains distributional equivalence, largely because continuous distribution matching is considered inapplicable to discrete sampling. Moreover, prevalent metrics (e.g., MSE, KL, CE, MMD) cannot accurately capture higher-order moment discrepancies, leading to suboptimal coresets. In this work, we propose FAST, the first DNN-free distribution-matching coreset selection framework that formulates the coreset selection task as a graph-constrained optimization problem grounded in spectral graph theory and employs the Characteristic Function Distance (CFD) to capture full distributional information in the frequency domain. We further discover that naive CFD suffers from a "vanishing phase gradient" issue in medium and high-frequency regions; to address this, we introduce an Attenuated Phase-Decoupled CFD. Furthermore, for better convergence, we design a Progressive Discrepancy-Aware Sampling strategy that progressively schedules frequency selection from low to high, preserving global structure before refining local details and enabling accurate matching with fewer frequencies while avoiding overfitting. Extensive experiments demonstrate that FAST significantly outperforms state-of-the-art coreset selection methods across all evaluated benchmarks, achieving an average accuracy gain of 9.12%. Compared to other baseline coreset methods, it reduces power consumption by 96.57% and achieves a 2.2x average speedup, underscoring its high performance and energy efficiency.
There are no more articles
❌