Ax Mahyar T. Moghaddam, Mina Alipour, Torben Worm, Mikkel Baun Kj{\ae}rgaard 29d ago

Toward a Sustainable Software Architecture Community: Evaluating ICSA's Environmental Impact

Analysis of carbon footprint from GenAI tool usage and conference activities in software architecture research.

Ax Leonardo Bitzki, Diego Kreutz, Tiago Heinrich, Douglas Fideles, Leandro Bertholdo, Silvio Quincozes, Angelo Diniz 29d ago

NetSecBed: A Container-Native Testbed for Reproducible Cybersecurity Experimentation

Container-based testbed for reproducible cybersecurity experimentation and network traffic generation.

Ax Rub\'en Moreno-Aguado, Alba Magall\'on, Victor Moreno, Yingying Fang, Guang Yang 29d ago

Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks

Study on training robust vision features for CT imaging to enable transfer learning for clinical diagnostic tasks.

Ax Juhan Park, Taerim Yoon, Seungmin Kim, Joonggil Kim, Wontae Ye, Jeongeun Park, Yoonbyung Chai, Geonwoo Cho, Geunwoo Cho, Dohyeong Kim, Kyungjae Lee, Yongjae Kim, Sungjoon Choi 29d ago

Learning Dexterous Grasping from Sparse Taxonomy Guidance

Research on dexterous robotic grasping using reinforcement learning with sparse guidance for multi-finger manipulation control.

Ax Cheol Woo Kum, Jai Moondra, Roozbeh Nahavandi, Andrew Perrault, Milind Tambe, Swati Gupta 29d ago

Many Preferences, Few Policies: Towards Scalable Language Model Personalization

Method for scalable LLM personalization using portfolio selection across heterogeneous user preferences, maintaining single shared model instead of per-user instances.

Ax Sofiane Bouaziz, Adel Hafiane, Raphael Canals, Rachid Nedjai 29d ago

Uncertainty-Aware Test-Time Adaptation for Cross-Region Spatio-Temporal Fusion of Land Surface Temperature

Test-time adaptation approach for cross-region generalization in land surface temperature prediction, addressing domain shifts in remote sensing applications.

Ax Xu Yan, Jun Yin, Shiliang Sun, Minghua Wan 29d ago

Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation

Method for incomplete multi-view multi-label classification using shared codebook and fused-teacher self-distillation under dual-missing conditions.

Ax Yaohan Guan, Pristina Wang, Najim Dehak, Alan Yuille, Jieneng Chen, Daniel Khashabi 29d ago

GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models

GENFIG1 benchmark evaluating vision-language models on generating Figure 1 visual summaries of scholarly research, assessing conceptual richness in scientific communication.

Ax Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta 29d ago

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

GraphicDesignBench: first comprehensive benchmark for evaluating AI models on professional graphic design tasks including layout, typography, and communicative intent.

Ax Kamyar Barakati, Boris N. Slautin, Utkarsh Pratiush, Hiroshi Funakubo, Sergei V. Kalinin 29d ago

PATHFINDER: Multi-objective discovery in structural and spectral spaces

Multi-objective automated discovery framework for microscopy and characterization workflows, addressing premature convergence through exploration coordination across structural and spectral spaces.

Ax Fuda van Diggelen 29d ago

Robots Need Some Education: On the complexity of learning in evolutionary robotics

Analysis of learning complexity in evolutionary robotics versus robot learning, examining optimization time scales and what is being optimized in robotic systems.

Ax Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao 29d ago

ClawArena: Benchmarking AI Agents in Evolving Information Environments

ClawArena benchmark evaluating AI agents' ability to maintain correct beliefs in evolving information environments with contradictory sources and changing evidence.

Ax Mir Tafseer Nayeem, Davood Rafiei 29d ago

Which English Do LLMs Prefer? Triangulating Structural Bias Towards American English in Foundation Models

Postcolonial analysis of structural bias toward American English in foundation models, examining geopolitical data curation and linguistic standardization in LLM development.

Ax Xiaohang Yu, William Knottenbelt 29d ago

LOCARD: An Agentic Framework for Blockchain Forensics

LOCARD: agentic framework modeling blockchain forensics as sequential decision-making, enabling dynamic iterative investigations instead of static inference pipelines.

Ax Aniruddh G. Puranic, Sebastian Schirmer, John S. Baras, Calin Belta 29d ago

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair

Formal framework using Temporal Behavior Trees to repair suboptimal trajectories from imperfect demonstrations before downstream imitation and reinforcement learning.

Ax Linyao Chen, Bo Huang, Qinlao Zhao, Shuai Shao, Zhi Han, Zicai Cui, Ziheng Zhang, Guangtao Zeng, Wenzheng Tang, Yikun Wang, Yuanjian Zhou, Zimian Peng, Yong Yu, Weiwen Liu, Hiroki Kobayashi, Weinan Zhang 29d ago

Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark

Framework and benchmark for converting web elements into autonomous agents as foundational primitives for the Agentic Web, enabling automated agent generation from digital assets.

Ax Donghuo Zeng, Hao Niu, Masato Taya 29d ago

Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning

Dual-path teacher-student framework for learning aligned multimodal embeddings from weakly paired audio-visual corpora using hierarchical semantic consistency.

Ax Charafeddine Mouzouni 29d ago

Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training

Analysis of Mixture-of-Experts token routing across training phases using congestion game modeling, tracking three-phase trajectory in OLMoE and OpenMoE models.

Ax Sajad Ghawami 29d ago

Good Rankings, Wrong Probabilities: A Calibration Audit of Multimodal Cancer Survival Models

Systematic audit of probability calibration in multimodal deep learning models combining histopathology images and genomic data for cancer survival prediction.

Ax Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki 29d ago

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs

Federated reinforcement learning from human feedback method for aligning LLMs with diverse human preferences while preserving privacy and achieving fair reward aggregation.

Ax Ali Akarma, Toqeer Ali Syed, Abdul Khadar Jilani, Salman Jan, Hammad Muneer, Muazzam A. Khan, Changli Yu 29d ago

Agents for Agents: An Interrogator-Based Secure Framework for Autonomous Internet of Underwater Things

Interrogator-based framework for behavioral trust monitoring in autonomous underwater vehicles and IoT sensor networks with decentralized coordination.

Ax Francesco Salvi, Alejandro Cuevas, Manoel Horta Ribeiro 29d ago

Commercial Persuasion in AI-Mediated Conversations

Two preregistered experiments (N=2,012) measuring how LLM agents embed commercial persuasion into conversational recommendations compared to traditional search engines.

Ax Ali Akarma, Toqeer Ali Syed, Salman Jan, Hammad Muneer, Abdul Khadar Jilani 29d ago

Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring

Framework combining blockchain-enforced oversight with AI agents for wildfire monitoring, ensuring human control and cryptographic verification in safety-critical autonomous systems.

Ax Luis Guzm\'an Lorenzo 29d ago

Poisoned Identifiers Survive LLM Deobfuscation: A Case Study on Claude Opus 4.6

Study on Claude Opus 4.6's ability to preserve poisoned identifier names during JavaScript deobfuscation across 192 inference runs, revealing consistent persistence patterns.

Ax Prachi Kudeshia, Jiju Poovvancheri, Amr Ghoneim, Dong Chen 29d ago

A Persistent Homology Design Space for 3D Point Cloud Deep Learning

Integration of persistent homology into deep learning architectures for 3D point cloud analysis capturing multi-scale topological structure invariants.

Ax Stella Girtsou, Konstantinos Alexis, Giorgos Giannopoulos, Harris Kontoes 29d ago

HighFM: Towards a Foundation Model for Learning Representations from High-Frequency Earth Observation Data

HighFM foundation model for learning representations from high-frequency satellite earth observation data for climate disaster monitoring and early warning.

Ax Yedong Shen, Shiqi Zhang, Sha Zhang, Yifan Duan, Xinran Zhang, Wenhao Yu, Lu Zhang, Jiajun Deng, Yanyong Zhang 29d ago

GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

GA-GS method using generative models to assist Gaussian splatting for 3D static scene reconstruction from monocular video with dynamic objects.

Ax Zequn Chen, Wesley J. Marrero 29d ago

Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications

Distributional reinforcement learning approach for optimization in robotics and healthcare addressing decision-making under uncertainty with heterogeneous groups.

Ax Donghoon Shin, Bingcan Guo, Jaewook Lee, Lucy Lu Wang, Gary Hsieh 29d ago

ReFinE: Streamlining UI Mockup Iteration with Research Findings

ReFinE Figma plugin connecting HCI research papers to design workflows by surfacing contextualized insights during UI mockup iteration.

Ax Tianyi Zhang, Andreas Marfurt 29d ago

GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering

GroundedKG-RAG system using knowledge graph indexing for retrieval-augmented generation in long-document question answering with LLMs.

Ax Emerson Lopes Machadoa, Cristiano Jacques Miosso, Ricardo Pezzuol Jacobi 29d ago

Integer-Only Operations on Extreme Learning Machine Test Time Classification

Techniques for reducing computational cost of extreme learning machine classifiers using integer-only operations without accuracy loss at test time.

Ax Yuanchen Bai, Zijian Ding, Ruixiang Han, Niti Parikh, Wendy Ju, Angelique Taylor 29d ago

Towards Considerate Human-Robot Coexistence: A Dual-Space Framework of Robot Design and Human Perception in Healthcare

Framework for human-robot coexistence in healthcare settings examining robot design and human perception in collaborative environments.

Ax Gregory N. Frank 29d ago

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Research identifying sparse routing mechanisms in alignment-trained language models, localizing gate attention and amplifier heads controlling policy behavior.

Ax Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Sekitoshi Kanai, Masanori Yamada, Kosuke Nishida, Kazutoshi Shinoda 29d ago

Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment

Method for stable language model alignment using relative density ratio optimization with statistical consistency guarantees beyond Bradley-Terry assumptions.

Ax Haruka Kawasaki, Ryota Tanaka, Kyosuke Nishida 29d ago

Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding

Study revealing gaps between internal representations and responses in vision language models for visual document understanding tasks.

Ax Xiaoyuan Zhu, Kimberly Le Truong, Riccardo Fogliato, Gokul Swamy, Weijian Zhang, Minglai Yang, Longtian Ye, Bangya Liu, Minghao Liu, Andrew Ilyas, Steven Wu 29d ago

Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality

Metric framework formalizing error verifiability to measure whether LLM justifications help users distinguish correct from incorrect answers.

Ax Seoyoung Park, Haemin Lee, Hankook Lee 29d ago

Is Prompt Selection Necessary for Task-Free Online Continual Learning?

Investigation of prompt selection necessity in task-free online continual learning with non-stationary data streams and no task boundaries.

Ax Mohamed Amine Bergach 29d ago

Training Transformers in Cosine Coefficient Space

Training approach for transformers using discrete cosine transform domain parameterization with reduced coefficients for efficient weight matrix representation.

Ax Barbara Gendron, Ga\"el Guibon, Mathieu d'Aquin 29d ago

Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation

Framework for constrained LLM generation using ontological definitions to enable modular and explainable control in conversational agents.

Ax Fatemeh Khadem, Sajad Mousavi, Yi Fang, Yuhong Liu 29d ago

DP-OPD: Differentially Private On-Policy Distillation for Language Models

Method for differentially private LLM compression via on-policy distillation, balancing privacy guarantees with model deployment efficiency.

Ax Hyunwoo Cho, Yeeun Kwon, Min Jung Kim, Yangmo Yoo 29d ago

MC-GenRef: Annotation-free mammography microcalcification segmentation with generative posterior refinement

Framework for mammography microcalcification segmentation using generative posterior refinement without dense pixel-level annotations.

Ax Zhe Feng, Shilong Tao, Haonan Sun, Shaohan Chen, Zhanxing Zhu, Yunhuai Liu 29d ago

MAVEN: A Mesh-Aware Volumetric Encoding Network for Simulating 3D Flexible Deformation

Neural network architecture using volumetric encoding for simulating 3D flexible deformation with graph neural networks on mesh structures.

Ax Liwei Deng, Qingxiang Liu, Xinhe Niu, Shengchao Chen, Sheng Sun, Yuankai Wu, Guodong Long, Yuxuan Liang 29d ago

Discrete Prototypical Memories for Federated Time Series Foundation Models

Research on federated time series foundation models using discrete prototypical memories to align time-series data with LLM latent space.

Ax Arjuna Scagnetto 29d ago

ECG Biometrics with ArcFace-Inception: External Validation on MIMIC and HEEDB

Study validating ECG biometric identification using Inception-v1 with ArcFace on large clinical datasets with temporal gaps and domain shift.

Ax Anuvab Sen, Mir Sayeed Mohammad, Saibal Mukhopadhyay 29d ago

RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation

Deep learning architecture for radar-based object detection and segmentation using efficient chirp-wise processing with early-exit mechanism.

Ax Ziwei Li, Yuang Ma, Yi Kang 29d ago

SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models

Paper presenting SLaB framework for LLM compression via sparse-lowrank-binary decomposition, maintaining performance at high compression ratios.

Ax Qiang He, Yucheng Yang, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy, Setareh Maghsudi 29d ago

One Model for All: Multi-Objective Controllable Language Models

Research paper on controllable LLMs with multi-objective alignment to varying human preferences, extending beyond fixed reward RLHF approaches.

Ax Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang 29d ago

GAIN: Multiplicative Modulation for Domain Adaptation

GAIN method uses multiplicative modulation for domain adaptation in LLMs, re-emphasizing existing features instead of injecting new directions.

Ax Ole Delzer, Sidney Bender 29d ago

Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

Reproducibility study on detecting and fixing spurious correlations, shortcut learning, and group-distributional non-robustness in DNNs.

Ax Hohyun Sim, Hyeonjoong Cho, Ali Shokri, Zhoulai Fu, Binoy Ravindran 29d ago

ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation

ENCRUST pipeline for safe C-to-Rust translation using agentic LLM refinement with whole-program reasoning on live scaffolds.