Isolater - Feed

Ax Abu Tyeb Azad, Ishita Sur Apan, Fahim Ahmed, Sumaiya Karim Katha, Ezharuddin Jubaer, Armun Alam, Pranjal Kumar Nandi, Amin Ahsan Ali, Aman Chadha, Md Mofijul Islam, AKM Mahbubur Rahman 23d ago

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

BaFCo benchmark dataset for Bangla form comprehension using multimodal LLMs, addressing low-resource language document understanding gaps.

Ax Kenneth Benavides, Josh Fleischer, Danti Chen 23d ago

EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems

EvalLoop methodology for evaluation-driven iterative improvement of LLM-based business systems, focusing on diagnosis and fixing rather than static model selection.

Ax Illia Dovhoshliubnyi, Nima Soroush, Ashkan Sami, Alexander Brownlee 23d ago

What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests

Empirical taxonomy of code mutations in AI-generated pull requests for performance optimization, analyzing 33k agent PRs.

Ax Damian Hodel, Jevin West, Aylin Caliskan 23d ago

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

RPAM: metric for measuring semantic associations and biases in language models with predictive validity for downstream task performance.

Ax Benjamin Minhao Chen, Zhiyu Li 23d ago

Beyond Accuracy: How Humans Evaluate Legally Correct but Socially Controversial Legal Advice from Machines

Survey study examining human trust in AI-generated legal advice versus human lawyers when advice is legally correct but socially controversial.

Ax Haz Sameen Shahgir, Yufei Li, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Yue Dong 23d ago

SCOReD: Student-Aware CoT Optimization for Recommendation Distillation

SCOReD: chain-of-thought distillation optimization for recommendation systems using student-aware training to avoid verbose reasoning traces.

Ax Mohammadreza Rashidi 23d ago

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

Survey of execution-layer security research for AI coding agents covering isolation, access control, TOCTOU vulnerabilities, and protocol threats.

Ax Mohammadreza Rashidi 23d ago

Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

Security vulnerability analysis of Model Context Protocol implementations showing tool metadata concealment attacks across AI coding agent servers.

Ax Minho Kim 23d ago

When Should LLMs Search? Counterfactual Supervision for Search Routing

Counterfactual supervision method to train LLMs when to use external search versus parametric knowledge for improved task performance.

Ax Lejian Zhang, Xueyan Tang, Jing Tang 23d ago

Data-dependent Evaluations for Budgeted Submodular Maximization

Data-dependent evaluation methods for budgeted submodular maximization algorithms in machine learning optimization problems.

Ax Guang Yang, Brian Siyuan Zheng, Victoria Ebert, Noah A. Smith 23d ago

LEGATO 2: Toward Multimodal Sheet Music Recognition and Understanding

Legato 2 pipeline for optical music recognition processing sheet music sequentially to extract symbolic notation and semantic knowledge.

Ax Chuhao Zhou, Liquan Wang, Shuxin Cao, Xiangyu Chen, Yuxuan Hu, Boyu Ma, Animesh Garg, Jianfei Yang 23d ago

FORGE: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning

FORGE framework enables robots to generalize tool use across novel objects via keypoint trajectory reasoning for functional transfer learning.

Ax Yake Wei, Yuan Wang, Fengyun Rao, Jing Lyu, Di Hu 23d ago

Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning

SegAnswer: multimodal LLM method using pixel-level segmentation before answering to improve visual reasoning accuracy in image understanding tasks.

Ax Fred Mutisya, Oscar Onyango, Sarah Sitati, Syokau Ilovi, Aeesha NJ Malik, Brenda W'mosi, Brian Makini, Jalemba Aluuvala, Josiah Onyango, Rachael Kanguha Mmene, Steven Wanyee 23d ago

Complementary Roles of Image Classification and Vessel Segmentation in AI-Based Screening for Retinopathy of Prematurity Plus Disease in a Kenyan Preterm Cohort

AI-based screening system combining image classification and vessel segmentation for detecting retinopathy of prematurity in infants.

Ax Mingchen Li, Meikang Qiu, Zifan Peng, Heng Fan, Song Fu, Junhua Ding, Yunhe Feng 23d ago

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

Vulnerability analysis of aligned LLMs comparing same-lineage models to isolate safety behavior from architectural differences in code review terminology.

Ax Zhiyuan Chen, Jing Hu, Junzhe Wang, Yueyang Huang, Xinyi Yang, Zhaoyang Wang, Feng Zhu 23d ago

AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking

In-context learning approach for ranking antibody candidates by binding affinity using contextual information from labeled antigen-specific comparisons.

Ax Sishun Liu, Sajal Halder, Ke Deng, Yan Wang, Xiuzhen Zhang 23d ago

Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns

Unsupervised anomaly detection method for identifying information operations users via behavioral and language patterns on social media.

Ax Pan Li, Kai Chen, Shuai Chang, Shengzhi Zhang, Peizhuo Lv, Jinwen He 23d ago

Differentially Private Natural Gradient Descent

Natural gradient descent variant for differentially private training that accounts for loss curvature to improve optimization efficiency under privacy constraints.

Ax Yihua Liu 23d ago

Think Before You Grid-Search: Floor-First Triage for LLM Serving

Analytical framework for LLM serving optimization using floor-first residual-driven triage to estimate resource bottlenecks before grid search.

Ax Suneeta Mall, Vladimir Nekrasov, Ashnil Kumar, Sajith Karunasena, Aiden Nibali, Alix Bird, Mateo Diaz Shine, Jarrel Seah 23d ago

Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context

Harrison.Rad 1.5 multimodal foundation model for automated radiology report generation from images, clinical history, and prior studies.

Ax Cemil-Andrei Dilmac, Florinel-Alin Croitoru, Radu Tudor Ionescu 23d ago

Few-Medoids: An Embarrassingly Simple Coreset Selection Method for Few-Shot Knowledge Distillation

Simple coreset selection method using medoids for efficient few-shot knowledge distillation that surpasses random baseline sample selection.

Ax Jean-Francois Bonbhel 23d ago

K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)

Selective gradient computation framework reducing training cost by excluding low-loss samples from backward pass with unbiased gradient estimation.

Ax Mingyang Song, Luxin Xu, Haoyu Sun, Minzhou Pan, Yu Cheng, Bo Li 23d ago

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

Benchmark and methods for policy-adaptive image safety guardrails that generalize to policy changes without retraining.

Ax Ryota Tanaka, Taku Hasegawa, Kyosuke Nishida 23d ago

CMDR: Contextual Multimodal Document Retrieval

Contextual multimodal document retrieval benchmark and methods that preserve textual/visual content while resolving multi-page aggregation queries.

Ax Chunmin Xia, Jakub Harbaczewski, Nikhil Dsilva, Julie Raulin, Dominic Schneider, Achim Autenrieth 23d ago

Agentic AI for IPoDWDM Network Lifecycle Automation: An MCP-Enabled Architecture

Distributed multi-MCP architecture for vendor-agnostic SDN-based automation and autonomous control of multi-layer IPoDWDM networks with E2E service lifecycle automation.

Ax Krittanon Kaewtawee, Petmongkon Pornpichitsuwan, Natchaya Temyingyong, Nutnicha Laplamoon, Wachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn 23d ago

InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost

Cost-efficient influencer matching system using three-stage cascade of small open-weight models instead of frontier LLM prompting for semantic matching on Thai marketing criteria.

Ax Riccardo Terrenzi, Serkan Ayvaz 23d ago

Faithful or Findable? Evaluating LLM-Generated Metadata for RDF Dataset Search

Evaluation of LLM-generated metadata for RDF dataset search, comparing rewriting and agentic graph-based generation methods for retrieval effectiveness and faithfulness.

Ax Chunmin Xia, Jakub Harbaczewski, Nikhil Dsilva, Julie Raulin, Dominic Schneider, Achim Autenrieth 23d ago

MCP-Enabled Agentic AI for Autonomous IPoDWDM Network Lifecycle Automation

Agentic AI architecture using MCP protocol for autonomous control and lifecycle automation of multi-vendor IPoDWDM networks with closed-loop control validation.

Ax Daniel Shalam, Emanuel Ben Baruch, Avi Ben Cohen, Tal Remez 23d ago

Propose and Attend: Training-free MLLM Grounding Confidence via Multi-Token Localized Attention

Training-free method to improve grounding confidence in multimodal LLMs by detecting hallucinated spatial/temporal predictions using multi-token localized attention.

Ax Daryna Dementieva, Nikolay Babakov, Kathy H\"ammerl, Ilseyar Alimova, Jind\v{r}ich Libovick\'y, Shu Okabe, Miras Baisbay, Lukas Edman, Abrorkhon Inomkhujaev, Antonia Karamolegkou, Mateusz Lango, Volkan \"Ozer, Nikola Selic, Subhankar Swain, Tsedeniya Kinfe Temesgen, Galit Bary Weisberg, Alexander Fraser 23d ago

PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages

PluraMath extends mathematical reasoning evaluation to 99 languages beyond English and Chinese, addressing dataset bias in LLM benchmarks.

Ax Rohit Mehra, Kapil Singi, Vikrant Kaulgud, Vibhu Saujanya Sharma, Swapnajeet Gon Choudhury, Swati Sharma, Adam P. Burden, Majd Sakr 23d ago

Prompt Coach: An Empirical Evaluation of an Agentic Tutor for Learning Prompt Engineering in Software Development

Prompt Coach is agentic tutor providing Socratic guidance for developers learning prompt engineering within IDE workflow.

Ax Shiyi Ling, Zhi Zheng, Hui Zheng, Wenjun Xue, Feng Ye, Tong Xu 23d ago

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

SocaSim is LLM-based multi-agent simulation framework modeling Putnam's Social Capital Theory for studying collective action.

Ax Rohit Mehra, Samdyuti Suri, Prithviraj K Tagadinamani, Kapil Singi, Vikrant Kaulgud, Adam P. Burden 23d ago

Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development

Studies incidental learning loss in AI-assisted software development and proposes design strategies for agents to support developer education.

Ax Woo Jae Kim, Kyle Min, Suhyeon Ha, Joonsung Jeon, Sung-eui Yoon 23d ago

RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations

RoME uses mixture of low-rank experts to achieve robustness against multiple adversarial perturbations with reduced trade-offs.

Ax Youcheng Zong, Runda Jia, Dakuo He 23d ago

LLM-Guided Measurement Credibility Correction for Trustworthy Industrial Process Inference

LLM-guided approach to correct measurement credibility in industrial soft sensing and process inference for robust predictions.

Ax Xin Peng, Ang Gao 23d ago

x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

Training-free acceleration method for diffusion and flow matching models via x-prediction without retraining or distillation.

Ax Muhammad Imran, Vincenzo Stoico, Ivano Malavolta 23d ago

Static Metrics Are Insufficient: Predicting Java Method Energy Usage with Execution Time

Predicts Java method energy usage incorporating execution time to enable early energy optimization in software development.

Ax Raafat Abualazm, Ayman AboElhassan, Amr G. Wassal 23d ago

Evaluating Fine-Tuning and Metrics for Neural Decompilation of Dart AOT Binaries

Empirical study of fine-tuning and evaluation metrics for neural decompilation of Dart AOT binaries using code-generation models.

Ax Aurora Francesca Zanenga, Andrea Bombarda, Marsha Chechik, Saverio D'Amico, Rita De Sanctis, Alberto Zambelli, Claudio Menghi 23d ago

Property-Driven Synthetic Data Engineering for Data-Scarce Software Systems: Reflections from the Breast Cancer Domain

Analyzes property-driven synthetic data generation engineering for data-scarce domains like breast cancer treatment planning systems.

Ax Chenxu Wang, Yongkun Yang, Boyuan Du, Shiwei Lin, Huaping Liu 23d ago

LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

Study on LLM agents for deliberative collaboration under partial observability with joint decision-making benchmark and multi-agent coordination.

Ax Chenhao Yuan, Yinhao Xu, Shuwen Xu, Xizhi Yang, Jiaxiang Liu, Chenxi Zhou, Shaoping Huang, Haolin Ren, Pengfei Cao, Jun Zhao, Kang Liu 23d ago

LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis

LongCrafter synthesizes long-context supervised fine-tuning data with evidence graphs to improve LLM understanding across diverse tasks.

Ax Jie Huang, Pengfei Yin, Zihan Xu, Daniel Capurro, Mike Conway, Ting Dang 23d ago

X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models

X-FEMR proposes token-level explainability approach for Electronic Health Records foundation models using transformers for clinical prediction tasks.

Ax Alexander Rombach, Chantale Lauer, Nijat Mehdiyev 23d ago