Isolater - Feed

Ax Yiquan Wu, Yuhang Liu, Yifei Liu, Ang Li, Siying Zhou, Kun Kuang 20d ago

Luwen Technical Report

Open-source Chinese legal language model built on Baichuan foundation using continued pretraining and instruction tuning.

Ax Ruida Hu, Xinchen Wang, Chao Peng, Cuiyun Gao, David Lo 20d ago

Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios

CLI-Tool-Bench benchmark for evaluating LLM agents' end-to-end software generation from intent without predefined scaffolds.

Ax Xiangyu Wang, Jin Wu, Haoran Shi, Wei Xia, Jiarui Yu, Chanjin Zheng 20d ago

TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks

Framework enabling multi-LLM collaboration with role-based team structure for solving complex multi-step contextualized tasks.

Ax Guillermo Gil de Avalle, Laura Maruster, Eric Sloot, Christos Emmanouilidis 20d ago

FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts

Pipeline for extracting procedural knowledge and directed graphs from maintenance flowchart images using vision-language models.

Ax Zhiyu Cao, Peifeng Li, Qiaoming Zhu 20d ago

Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search

Multi-faceted preference alignment approach for conversational query rewriting using feedback from retrieval and generation components.

Ax Xinchen Wang, Ruida Hu, Cuiyun Gao, Pengfei Gao, Chao Peng 20d ago

Evaluating Repository-level Software Documentation via Question Answering and Feature-Driven Development

Benchmark for evaluating LLM-generated repository documentation using question answering, addressing limitations of LLM-as-judge evaluation methods.

Ax Huy Q. Le, Loc X. Nguyen, Yu Qiao, Seong Tae Kim, Eui-Nam Huh, Choong Seon Hong 20d ago

FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift

FedDAP addresses domain shift in federated learning using prototype learning for privacy-sensitive applications.

Ax Andrea Pollastro, Andrea Apicella, Francesco Isgr\`o, Roberto Prevete 20d ago

Instance-Adaptive Parametrization for Amortized Variational Inference

Instance-adaptive variational autoencoders reduce amortization gap in latent variable models for deep generative modeling.

Ax Zhixiong Zhao, Zukang Xu, Zhixuan Chen, Dawei Yang 20d ago

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization

MoBiE: binarization framework for efficient inference of mixture-of-experts LLMs using post-training quantization.

Ax Yunhao Feng, Yifan Ding, Yingshui Tan, Boren Zheng, Yanming Guo, Xiaolong Li, Kun Zhai, Yishan Li, Wenke Huang 20d ago

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

SkillTrojan: backdoor attack framework targeting skill-based agent systems through malicious skill implementations.

Ax Dihong Jiang, Ruoqi Cao, Zhiyuan Dang, Li Huang, Qingsong Zhang, Zhiyu Wang, Shihao Piao, Shenggao Zhu, Jianlong Chang, Zhouchen Lin, Qi Tian 20d ago

OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale

OmniTabBench: largest tabular data benchmark comparing GBDTs, neural networks, and foundation models at scale.

Ax Paula Dodig, Boshko Koloski, Katarina Sitar \v{S}u\v{s}tar, Senja Pollak, Matthew Purver 20d ago

Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models

ESG sentiment analysis dataset and models for Slovene news, addressing corporate performance assessment in emerging markets.

Ax Jiang Zhou, Yunhao Wang, Xing Wu, Tinghao Yu, Feng Zhang 20d ago

WRAP++: Web discoveRy Amplified Pretraining

WRAP++ improves LLM pretraining through synthetic data rephrasing that captures cross-document relationships and associative context.

Ax Jeongho Yoon, Chanhee Park, Yongchan Chun, Hyeonseok Moon, Heuiseok Lim 20d ago

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation

Privacy-preserving LLM inference method enabling text-free processing through alignment and adaptation, reducing privacy risks without computational overhead.

Ax Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye 20d ago

On the Step Length Confounding in LLM Reasoning Data Selection

Analysis of step length confounding bias in LLM reasoning dataset selection pipelines used for fine-tuning complex reasoning models on chain-of-thought tasks.

Ax Yijie Zhong, Yunfan Gao, Haofen Wang 20d ago

HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues

Memory architecture for long-term dialogue systems using boundary-guided event segmentation and query-adaptive retrieval to improve scalability and personalization.

Ax Xiaotian Luo, Xun Jiang, Jiangcheng Wu 20d ago

MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors

Benchmark for evaluating LLM diagnostic robustness in medical dialogue with adversarial patient behaviors at varying severity levels and cross-dimension interactions.

Ax Mingchen Li, Wajdi Aljedaani, Yingjie Liu, Navyasri Meka, Xuan Lu, Xinyue Ye, Junhua Ding, Yunhe Feng 20d ago

Digital Skin, Digital Bias: Uncovering Tone-Based Biases in LLMs and Emoji Embeddings

Large-scale study examining bias in skin-toned emoji representations across LLMs and embedding models, addressing societal bias perpetuation in AI systems.

Ax Miguel A. DelaCruz, Patricia Mae Santos, Rafael T. Navarro 20d ago

Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasion

Research on physical adversarial attacks against surveillance systems including person detection, multi-object tracking, and visible-infrared evasion techniques.

Ax Bajian Xiang, Tingwei Guo, Xuan Chen, Yang Han 20d ago

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models

Research on redundancy in Large Speech Language Models reveals structured token-level redundancy to reduce inference costs while maintaining semantic fidelity.

Ax Nikolaos D. Tantaroudas, Ilias Karachalios, Andrew J. McCracken 20d ago

SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training

SentinelSphere combines ML-based threat detection with LLM-powered security training to address cybersecurity skill gaps and human vulnerabilities.

Ax N. D. Tantaroudas, A. J. McCracken, I. Karachalios, E. Papatheou, V. Pastrikakis 20d ago

XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI

Extended reality platform combining XR and multimodal AI for personalized career guidance and coaching.

Ax Rudra Jadhav, Janhavi Danve 20d ago

The AI Skills Shift: Mapping Skill Obsolescence, Emergence, and Transition Pathways in the LLM Era

Benchmark measuring occupational skill susceptibility to LLM automation across 263 tasks and 35 O*NET skill categories.

Ax Yuheng Shi, Xiaohuan Pei, Linfeng Wen, Minjing Dong, Chang Xu 20d ago

Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models

Query-aware adaptive perception method for reducing tokens in multimodal LLM inference while maintaining fine-grained understanding.

Ax Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie 20d ago

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Efficient scaling method for diffusion model reinforcement learning using mixed precision and selective rollout quantization.

Ax Milad Moradi, Ke Yan, David Colwell, Matthias Samwald, Rhona Asgari 20d ago

Multi-modal user interface control detection using cross-attention

Multi-modal UI control detection combining YOLO vision with GPT-generated text descriptions via cross-attention.

Ax Andoni Irazusta Garmendia 20d ago

A First Guess is Rarely the Final Answer: Learning to Search in the Travelling Salesperson Problem

Neural improvement method learning local search policies for TSP, generalizing beyond single-solution outputs.

Ax Milad Moradi, Ke Yan, David Colwell, Rhona Asgari 20d ago

An empirical study of LoRA-based fine-tuning of large language models for automated test case generation

Empirical study of LoRA fine-tuning LLMs for automated test case generation from natural language requirements.

Ax Ioannis Kyprakis, Vasileios Skaramagkas, Georgia Karanasiou, Lampros Lakkas, Andri Papakonstantinou, Domen Ribnikar, Kalliopi Keramida, Dorothea Tsekoura, Ketti Mazzocco, Anastasia Constantinidou, Konstantinos Marias, Dimitrios I. Fotiadis, Manolis Tsiknakis 20d ago

Frailty Estimation in Elderly Oncology Patients Using Multimodal Wearable Data and Multi-Instance Learning

Multimodal wearable framework for frailty estimation in elderly breast cancer patients.

Ax Renyang Liu, Jiale Li, Jie Zhang, Cong Wu, Xiaojun Jia, Shuxin Li, Wei Zhou, Kwok-Yan Lam, See-kiong Ng 20d ago

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

Adversarial patch attacks on palmprint recognition systems in physical settings.

Ax Jaeyoung Chung, Hyunjin Son, Kyoung Mu Lee 20d ago

Generative Phomosaic with Structure-Aligned and Personalized Diffusion

Generative approach to photomosaic creation using diffusion models with structure alignment.

Ax Ioannis Kyprakis, Vasileios Skaramagkas, Georgia Karanasiou, Vasilis Bouratzis, Andri Papakonstantinou, Dimitar Stefanovski, Kalliopi Keramida, Aristofania Simatou, Ketti Mazzocco, Anastasia Constantinidou, Konstantinos Marias, Dimitrios I. Fotiadis, Manolis Tsiknakis 20d ago