Isolater - Feed

Ax Narmeen Oozeer, Luke Marks, Shreyans Jain, Fazl Barez, Amirali Abdullah 2d ago

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models

K-Steering enables unified multi-attribute control of LLM behavior at inference time using non-linear steering on hidden activations.

Ax Mijeong Kim, Gunhee Kim, Jungyoon Choi, Wonjae Roh, Bohyung Han 2d ago

PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis

PhysGaia benchmark for dynamic novel view synthesis with physics-aware evaluation of multi-body interactions and realistic collisions.

Ax Shuo Jiang, Min Xie, Jianxi Luo 2d ago

Large Language Models for Combinatorial Optimization of Design Structure Matrix

LLMs applied to combinatorial optimization of Design Structure Matrices in engineering, demonstrating reasoning capabilities for complex system reorganization.

Ax Yuiga Wada, Kazuki Matsuda, Komei Sugiura, Graham Neubig 2d ago

ZINA: Multimodal Fine-grained Hallucination Detection and Editing

ZINA detects and edits fine-grained hallucinations in multimodal LLMs, proposing a novel evaluation task for MLLM quality.

Ax Lujun Li, Yiqun Wang, Radu State 2d ago

Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications

Vision Transformer-based framework reconstructs multispectral satellite imagery obscured by clouds using SAR data for crop mapping.

Ax Federico Zucchi, Thomas Lampert 2d ago

PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers

PRISM: lightweight fully convolutional model for multivariate time-series classification on edge devices.

Ax Ugur Cetintemel, Shu Chen, Alexander W. Lee, Deepti Raghavan, Duo Lu, Andrew Crotty 2d ago

Making Prompts First-Class Citizens for Adaptive LLM Pipelines

Framework treating prompts as first-class citizens in LLM pipelines to enable reuse, optimization, and runtime adaptation in complex agent systems.

Ax Dixon Domfeh, Saeid Safarveisi 2d ago

CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market

CATNet applies geometric deep learning (R-GCN) to catastrophe bond spread prediction in financial markets.

Ax Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni, Zibin Dong, Pengyi Li, Yan Zheng, Hongyao Tang, Jianye Hao 2d ago

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

Embodied-R1 introduces a 3B VLM using "pointing" as unified intermediate representation to address the seeing-to-doing gap in robotic manipulation across different embodiments.

Ax Wangsong Yin, Daliang Xu, Mengwei Xu, Gang Huang, Xuanzhe Liu 2d ago

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference

ShadowNPU system co-design for efficient on-device LLM inference on NPUs, addressing quantization sensitivity in attention operators.

Ax Phongsakon Mark Konrad, Andrei-Alexandru Popa, Yaser Sabzehmeidani, Liang Zhong, Madhulika Tripathy, Andrei Constantinescu, Elisa A. Liehn, Serkan Ayvaz 2d ago

Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets

Benchmarking study of deep learning segmentation models for carotid artery structures in histopathological images with limited datasets.

Ax Tao Long, Xuanming Zhang, Sitong Wang, Zhou Yu, Lydia B Chilton 2d ago

DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow

DoubleAgents system for human-agent alignment in coordination tasks using a coordination agent and dashboard for preference elicitation and feedback.

Ax Miao Jing, Mengting Jia, Junling Lin, Zhongxia Shen, Huan Gao, Mingkun Xu, Shangyang Li 2d ago

Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks

Neural-MedBench reasoning-intensive benchmark for evaluating clinical reasoning ability of vision-language models beyond classification accuracy.

Ax Rohit Chowdhury, Aniruddha Bala, Rohan Jaiswal, Siddharth Roheda 2d ago

Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing

Vid-Freeze defense mechanism against malicious image-to-video generation using temporal freezing adversarial techniques.

Ax Zhimeng Luo, Lixin Wu, Adam Frisch, Daqing He 2d ago

Measuring Competency, Not Performance: Item-Aware Evaluation Across Medical Benchmarks

MedIRT psychometric framework for evaluating LLM medical competency rather than benchmark-specific performance using Item Response Theory.

Ax Vincent Grari, Tim Arni, Thibault Laugel, Sylvain Lamprier, James Zou, Marcin Detyniecki 2d ago

ACT: Agentic Classification Tree

ACT system combines decision trees with LLMs to provide transparent, interpretable, and auditable AI decisions on unstructured data.

Ax Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li 2d ago

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

Study of how autonomy levels in LLM agents affect user privacy concerns and trust, with implications for personalization design.

Ax Haotian Wu, Shufan Jiang, Chios Chen, Yiyang Feng, Hehai Lin, Heqing Zou, Yao Shu, Chengwei Qin 2d ago

FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline

FURINA-Builder multi-agent pipeline for automatically constructing customizable role-playing benchmarks at scale for evaluating LLM agent behavior.

Ax Kazuki Egashira, Robin Staab, Thibaud Gloaguen, Mark Vero, Martin Vechev 2d ago

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

Security analysis of LLM pruning methods showing vulnerabilities in popular inference engines like vLLM when models are pruned before deployment.

Ax Vijay M. Galshetwar, Praful Hambarde, Prashant W. Patil, Akshay Dudhane, Sachin Chaudhary 2d ago

Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation

Survey of image and video restoration techniques for adverse weather conditions in intelligent transportation systems and autonomous driving.

Ax Muhammad Junaid Asif, Abdul Rehman, Asim Mehmood, Rana Fayyaz Ahmad, Shazia Saqib 2d ago

Leveraging Wireless Sensor Networks for Real-Time Monitoring and Control of Industrial Environments

IoT and wireless sensor networks for industrial monitoring and control using NRF transceivers and Arduino microcontrollers.

Ax Shinwoo Park, Hyejin Park, Hyeseon Ahn, Yo-Sub Han 2d ago

A Linguistics-Aware LLM Watermarking via Syntactic Predictability

Watermarking technique for LLMs using syntactic predictability to balance text quality against detection robustness for governance and trustworthiness.

Ax Xingrui Wang, Jiang Liu, Chao Huang, Xiaodong Yu, Ze Wang, Ximeng Sun, Jialian Wu, Alan Yuille, Emad Barsoum, Zicheng Liu 2d ago

XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models

XModBench benchmark measures cross-modal consistency and modality-specific biases in omni-modal large language models across audio, vision, and text.

Ax Gao Yang, Yuhang Liu, Siyu Miao, Xinyue Liang, Zhengyang Liu, Heyan Huang 2d ago

LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation

Game-theoretic framework for evaluating LLMs on subjective and open-ended tasks beyond fixed-format benchmarks with reference answers.

Ax Chun Chet Ng, Zhen Hao Chu, Jia Yu Lim, Yin Yin Boon, Wei Zeng Low, Jin Khye Tan 2d ago

AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring

Application of AI to bank statement analysis for credit scoring of Malaysian MSMEs using alternative data sources instead of traditional credit bureau data.

Ax Mengqi Li, Lei Zhao, Anthony Man-Cho So, Ruoyu Sun, Xiao Li 2d ago

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

SePT method enables LLMs to improve reasoning without external rewards by alternating between self-generating responses and fine-tuning on those responses.

Ax Xi He, Sirui Lu, Bei Zeng 2d ago

Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems

Multi-agent system with Lean 4 verification layer for exact scientific discovery in quantum code design, combining symbolic synthesis and automated verification.

Ax Tong Ma, Hui Lai, Hui Wang, Zhenhu Tian, Chaochao Li, Fengjie Xu, Ling Fang 2d ago

ATLAS: A Layered Constraint-Guided Framework for Structured Artifact Generation in LLM-Assisted MDE

ATLAS framework combines LLMs with model-driven workflows for generating structured artifacts that satisfy schemas, domain rules, and audit requirements through constraint compilation and validation.

Ax Irina Proskurina, Marc-Antoine Carpentier, Julien Velcin 2d ago

HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection

Interpretable model for detecting implicit and explicit hate speech using prototype-based representations for transfer learning.

Ax Qibing Ren, Zhijie Zheng, Jiaxuan Guo, Junchi Yan, Lizhuang Ma, Jing Shao 2d ago

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Research on financial fraud risks from collaborative LLM agents including MultiAgentFraudBench for simulating multi-agent fraud scenarios.

Ax Tommy Sha (Kindred), Zhan Cheng (Kindred), Haotian Zhai (Kindred), Xuwei Ding (Kindred), Junnan Li (Kindred), Haixiang Tang (Kindred), Zaoting Sun (Kindred), Yanchuan Tang (Kindred), Yongzhe (Kindred), Yi, Yuan Gao, Anhao Li 2d ago

FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis

Fairness-aware stroke diagnosis framework combining domain-adversarial training with group distributionally robust optimization.

Ax Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae, Nidhi Rastogi 2d ago

SPHINX: A Synthetic Environment for Visual Perception and Reasoning

Synthetic environment generating visual reasoning puzzles with ground-truth solutions across 25 task types for benchmark construction.

Ax Lingdong Wang, Guan-Ming Su, Divya Kothandaraman, Tsung-Wei Huang, Mohammad Hajiesmaili, Ramesh K. Sitaraman 2d ago

Low-Bitrate Video Compression through Semantic-Conditioned Diffusion

Video compression framework using semantic conditioning and diffusion models for ultra-low bitrate encoding.

Ax Qi'ao Xu, Tianwen Qian, Yuqian Fu, Kailing Li, Yang Jiao, Jiacheng Zhang, Xiaoling Wang, Liang He 2d ago

ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos

Benchmark for task-oriented spatio-temporal grounding in egocentric videos for embodied AI agents.

Ax Jia Hu, Zhexi Lian, Xuerun Yan, Ruiang Bi, Dou Shen, Yu Ruan, Chunlong Xia, Haoran Wang 2d ago

MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving

Physics-informed transformer model for socially-aware autonomous driving that learns social interaction dynamics.

Ax Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong, Zheng Liu, Yejun Tang, Huan Yang, Guanbin Li, Lianwen Jin 2d ago

ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention

Drag-based image editing method using diffusion models with token injection and attention mechanisms for precise visual manipulation.

Ax Junhyung Park, Yuqing Zhou 2d ago

A fine-grained look at causal effects in causal spaces

Theoretical framework for analyzing causal effects at fine-grained levels in high-dimensional data like images and language models.

Ax Chao Wen, Tung Phung, Pronita Mehrotra, Sumit Gulwani, Roger E. Beaty, Tomohiro Nagashima, Adish Singla 2d ago

Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

Interface design study on scaffolding divergent and convergent thinking in human-AI co-creation with generative models.

Ax Minh V. T. Thai, Tue Le, Dung Nguyen Manh, Huy Phan Nhat, Nghi D. Q. Bui 2d ago

SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

SWE-EVO benchmark for evaluating AI coding agents on long-horizon software evolution tasks spanning multiple files and iterations.

Ax Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Nils Feldhus, Christin Seifert, Hinrich Sch\"utze, Sebastian M\"oller, Vera Schmitt 2d ago

Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation

Research on using LLMs to generate multilingual counterfactual examples for model interpretability across languages.

Ax Zihua Yang, Xin Liao, Yiqun Zhang, Yiu-ming Cheung 2d ago