Ax Jinxi Li, Tianyi Zhang, Yafei Yang, Zihui Zhang, Peng Huang, Koon Wing Macgyver Lin, Bo Yang 9d ago

NeoMap: Training-free Novel-View Synthesis from Single Images and Videos

Novel view video synthesis method from single images using pre-trained video models without task-specific fine-tuning.

Ax Jan Drchal 9d ago

Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization

Object Aligner provides configurable JSON schema similarity scoring for measuring LLM output structure alignment in tool calling and agentic systems.

Ax Sofiane Ouaari, Kevin Vorwalder, Nico Pfeifer 9d ago

Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias

Evaluates Vision-Language Model reliability for medical image quality assessment under corruption and bias conditions.

Ax Beile Ning, Jiayi Yu, Zitong Wang, Yufei Hu, Wenjun Xu, Yuanhang Qian, Zhongxin Bai, Gongping Huang 9d ago

A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification

DCASE 2026 Challenge system for audio classification using CLAP audio-text representations with taxonomy-aware hierarchy constraints.

Ax Wenda Wang, Yihan Tong, Yuwei Hu, Zhewei Wei 9d ago

MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding

MolSight vision-language model combines molecular LLMs with graph-aware visual understanding for molecular structure and drug discovery tasks.

Ax Tasnim Shahriar 9d ago

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Controlled study comparing nine lightweight CNN architectures across multiple datasets and hardware to assess efficiency claims.

Ax Shrikara Arun, Anjaly Parayil, Srikant Bharadwaj, Renee St. Amant, Victor R\"uhle 9d ago

Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving

Proposes load-aware prefill deflection technique to improve disaggregated LLM serving efficiency by balancing prefill and decode GPU pools.

Ax Rheeya Uppaal, Seungwoo Lyu, Selina Sung, Junjie Hu 9d ago

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets

OpenSafeIntent benchmark evaluates whether LLMs calibrate assistance appropriately across benign, dual-use, and malicious intent variants.

Ax Anna Chorna 9d ago

SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses

SPLIT benchmark evaluates LLM cross-lingual empathy and cultural grounding in emotional-support contexts across English and Ukrainian.

Ax Prathamesh Patil, Arpit Jain, Aswanth Krishnan 9d ago

Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains

Demonstrates performance evaluation failures in spatiotemporally correlated domains due to data leakage from non-i.i.d. splits.

Ax Florian Tambon, Michael Konstantinou, Cedric Richter, Charles Chenouard, Mark Harman, Mike Papadakis 9d ago

Prompt Coverage Adequacy

Proposes prompt coverage adequacy testing framework to guide LLM and autonomous agent testing when prompts replace traditional code.

Ax Yang Li, Pan Hu, Yan Zhang, Wenfan Yang, Tao Wu, Lianbo Guo 9d ago

SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition

Graph Neural Network model for EEG-based depression recognition using hyperbolic geometry to capture hierarchical brain network structure.

Ax Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan 9d ago

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

kNNGuard presents training-free guardrail for LLMs using activation space of off-the-shelf models to detect unsafe/adversarial prompts with minimal labeled data.

Ax Dipika Rajesh, Ahmed Khalifa, Julian Togelius 9d ago

Evolutionary Wave Function Collapse

Combines Wave Function Collapse procedural generation with evolutionary search to evolve input examples for level generation.

Ax Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, Cuong Tuan Nguyen, Hoang M. Le, Dat Nguyen, Phat Kim Huynh, Min Xu, Ulas Bagci 9d ago

ESC: Emotional Self-Correction for Reliable Vision-Language Models

Introduces emotional self-correction mechanism for vision-language models to improve reasoning reliability without post-training or engineered feedback.

Ax Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng, Zezhi Tang 9d ago

Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies

Proposes test-time guidance framework for vision-language-action policies using learned critic to guide flow-matching inference without retraining base models.

Ax Haoran Wang, Jinchuan Tian, Siddhant Arora, Shinji Watanabe 9d ago

An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation

Presents vLLM-based inference pipeline for unified audio understanding and generation in speech language models with multi-token prediction support.

Ax William Hackett, Peter Garraghan 9d ago

Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring

Develops behavioral monitoring techniques to detect and analyze guardrail activations in LLMs, enabling black-box security testing of production AI systems.

Ax Yilie Huang, Wenpin Tang, Xun Yu Zhou 9d ago

ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning

Proposes Adaptive Reparameterized Time (ART) continuous-time control for optimizing timestep allocation in score-based diffusion sampling via actor-critic learning.

Ax Debopriya Ghosh 9d ago

Predicting Early Stages Of Alzheimer's Disease And Identifying Key Biomarkers Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

Applies deep neural networks and ensemble methods to predict early-stage Alzheimer's disease and identify biomarkers from medical data.

Ax Di Wu, Huan Liu, Zhixiang Chi, Yuanhao Yu, Konstantinos N. Plataniotis, Yang Wang 9d ago

Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space

Develops neural graph encoding method for analyzing neural network weight spaces by capturing sequential layer-by-layer inference processes.

Ax Mohammad Amanour Rahman 9d ago

RadiomicNet: A Hybrid Radiomics-Guided Lightweight Architecture for Interpretable Medical Image Segmentation

Proposes RadiomicNet hybrid architecture integrating handcrafted radiomics features with deep learning for interpretable medical image segmentation.

Ax Javier Irigoyen, Roberto Daza, Aythami Morales, Julian Fierrez, Ruben Tolosana, Ruben Vera-Rodriguez, Francisco Jurado, Alvaro Ortigosa 9d ago

Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond

Reviews AI risk assessment and management methodologies under EU AI Act and other regulatory frameworks, covering identification, analysis, and mitigation approaches.

Ax Nathan Hughes, Ibrahim Habli 9d ago

What Types of Human-AI Teams Exist?

Systematically categorizes 53 human-AI team studies into five clusters using psychological teaming taxonomies to understand collaboration patterns and diversity.

Ax Gemma Galdon Clavell, Pablo Accuosto, Usman Gohar 9d ago

The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Audits

Presents open infrastructure for operationalizing AI audits by moving beyond taxonomies to actionable tests. Reviews 74 existing risk taxonomies and proposes executable evaluation framework.

Ax Haokun Liu, Zhaoqi Ma, Yicheng Chen, Wentao Zhang, Masaki Kitagawa, Zicen Xiong, Jinjie Li, Moju Zhao 9d ago

CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation

Proposes CoFL-S framework for vision-language navigation using language-conditioned flow fields for low-level robot action generation and trajectory planning.

Ax Mohammed Fahad Ali, Dominique Briechle, Marit Briechle-Mathiszig, Tobias Geger, Andreas Rausch 9d ago

Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting

Compares classification strategies for automated waste sorting using confidence-guided human-in-the-loop approaches for circular economy applications.

Ax A. Seza Do\u{g}ru\"oz, Xixian Liao, Verena Blaschke, Jakob Prange, Senyu Li, David Ifeoluwa Adelani 9d ago

Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages

Analyzes limitations of LLM-as-a-Judge evaluation paradigm for multilingual and low-resource language tasks, showing proficiency gaps and validation challenges.

Ax Ziyun Qiao, Yue Min, Ruining Chen, Yujun Li 9d ago

HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures

Proposes HERMES, a hierarchical multi-granularity labeling system for pre-training data mixtures to improve flexibility in corpus partitioning and semantic organization.

Ax Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya, Kanta Sawafuji, Hiroki Kajita, Shigeki Sakai, Hideo Saito, Ryo Hachiuma 9d ago

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

Introduces specialized benchmark for evaluating vision-language models on rare concepts and complex spatio-temporal video grounding beyond general datasets.

Ax Max Weltevrede, Matthijs T. J. Spaan, Wendelin B\"ohmer 9d ago

Generalization in offline RL: The structure is more important than the amount of pessimism

Analyzes how pessimism structure rather than magnitude affects generalization in offline reinforcement learning contextual MDPs.

Ax Ziyang Jiang, Yu Chen, Zexu Pan, Xinyuan Qian, Bowen Xing, Ivor W. Tsang, Xu-Cheng Yin, Haizhou Li 9d ago

SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios

Develops prompt-guided selective sound localization system combining multimodal learning for target sound source detection in complex audio environments.

Ax Dezheng Wang, Tong Chen, Wei Yuan, Congyan Chen, Shihua Li, Hongzhi Yin 9d ago

Self-Gating Attention for Efficient Time Series Forecasting

Proposes self-gating attention mechanism to reduce transformer complexity for time series forecasting, addressing quadratic memory/time costs.

Ax Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang 9d ago

SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

Research on security vulnerabilities in LLM-based agent skill marketplaces where benign skills can interact unexpectedly. Addresses fuzzing skill composition to discover implicit intent attacks.

Ax Yonglong Zhang, Yang Liu 9d ago

GAP-GDRNet: Geometry-Aware Monocular Visual Pose Sensing on a Single-Target Synthetic Spacecraft Dataset

Geometry-aware attention framework (GAP-GDRNet) for monocular 6D spacecraft pose estimation using synthetic training data.

Ax Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Yifeng Peng, Junghoon Justin Park, Huan-Hsin Tseng, Hsin-Yi Lin, Kuan-Cheng Chen, Chen-Yu Liu, Shinjae Yoo, Samuel Yen-Chi Chen 9d ago

Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates

Quantum fast-weight programmers with self-modulating gates and bounded memory for stable quantum sequence modeling.

Ax Yuan Yuan 9d ago

The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry

Analysis of LLM persona geometry using manifold methods shows persona representations are frame-dependent across different question orderings.

Ax Nina Begus 9d ago

World Wide Models: Literary Tools for Cultural AI

Essay on using literary analysis and translation frameworks to build culturally literate AI systems addressing monolingual LLM limitations.

Ax Batu Guan, Zirui Wang, Shaohua Li 9d ago

Understanding Agent-Based Patching of Compiler Missed Optimizations

Systematic study of AI agents patching compiler missed optimizations showing generalization beyond single cases is the key challenge.

Ax Cristian-Gabriel Florea, Stelian Sp\^inu 9d ago

VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval

Offline-first Android assistant application for people with visual impairment using multimodal models with personalized object retrieval.

Ax Gawon Seo, Dongwon Kim, Suha Kwak 9d ago

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

ACID method uses inverse dynamics to verify trajectory realizability during decision-time planning with world models for embodied control.

Ax Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li 9d ago

Neuron-Aware Active Few-Shot Learning for LLMs

Neuron-aware active learning method for LLMs identifies valuable unlabeled samples for annotation reducing human labeling costs in few-shot adaptation.

Ax Quoc Bao Phan, Tuy Tan Nguyen 9d ago

QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition

Quantum-enhanced federated learning for multi-agent activity recognition combining quantum circuits with distributed learning for robotic sensing.

Ax Achint Mehta 9d ago

Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

Observational study of 90 agentic code generation runs showing reasoning effort matters more than tool access for first-try reliability.

Ax Zhuowei Chen, Xiang Lorraine Li 9d ago

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Neuron-aware data selection approach for annotation-free LLM self-distillation in specialized domains without human supervision.

Ax Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda, Timo Mertens, Saurabh Shukla 9d ago

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Data-agnostic quantization method for diffusion transformers enabling efficient post-training quantization without calibration data recalibration.

Ax Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu 9d ago

Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

Task-agnostic pretraining approach for Vision-Language-Action models separates physical competence learning from semantic alignment to reduce expert demonstration requirements.

Ax Vivienne Ming 9d ago

Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting

Empirical study using real-money prediction market showing human-AI collaboration success depends on specific human capital metrics rather than model benchmarks.

Ax Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie 9d ago

TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

Executable benchmark for evaluating test generation agents on code-test co-evolution with real semantic verification of test-code relationships.

Ax Xuehui Wang, Xuankun Yang, Wei Shen 9d ago

Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning

Entropy-aware token pruning method for vision-language models to reduce redundant visual tokens while preserving critical information under dense instructions.