Ax Alberto Olivares-Alarcos, Sergi Foix, J\'ulia Borr\`as, Gerard Canal, Guillem Aleny\`a 3/18/2026

Ontological foundations for contrastive explanatory narration of robot plans

Ontological framework for robots to explain competing plans through contrastive reasoning for human-robot interaction.

Ax Han Zhou, Jinjin Cao, Liyuan Ma, Xueji Fang, Guo-jun Qi 3/18/2026

Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer

Co-denoising framework for transferring manipulation skills from human videos to robots by bridging morphological differences.

Ax L\'eo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nazanin Sepahvand, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, Krishnamurthy Dj Dvijotham, Alexandre Drouin 3/18/2026

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Security research identifying backdoor vulnerabilities in AI agent supply chains through data poisoning across multiple pipeline stages.

Ax Pierre Lison, Mark Anderson 3/18/2026

Protecting De-identified Documents from Search-based Linkage Attacks

Technique to prevent search-based linkage attacks on de-identified documents using perturbation methods.

Ax Jingyu Peng, Maolin Wang, Hengyi Cai, Yuchen Li, Kai Zhang, Shuaiqiang Wang, Dawei Yin, Xiangyu Zhao 3/18/2026

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching

Knowledge distillation method balancing exploration and guidance for training efficient small language models with reduced exposure bias.

Ax Xinhu Li, Ayush Jain, Zhaojing Yang, Yigit Korkmaz, Erdem B{\i}y{\i}k 3/18/2026

When a Robot is More Capable than a Human: Learning from Constrained Demonstrators

Learning framework enabling robots to learn from constrained human demonstrations where demonstrators have fewer degrees of freedom.

Ax Jiachi Zhao, Zehong Wang, Yamei Liao, Chuxu Zhang, Yanfang Ye 3/18/2026

Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance

Inference-time tree search guidance method for controllable graph generation using diffusion models across knowledge graphs and drug discovery.

Ax Tuhin Chakrabarty, Jane C. Ginsburg, Paramveer Dhillon 3/18/2026

Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers

Empirical study showing frontier LLMs trained on copyrighted books produce preferred literary text matching award-winning authors' styles.

Ax Bingyu Li, Feiyu Wang, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li 3/18/2026

MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment

Benchmark for open-vocabulary underwater instance segmentation with geometric and semantic alignment enhancements.

Ax Zebin Yang, Sunjian Zheng, Tong Xie, Tianshi Xu, Bo Yu, Fan Wang, Jie Tang, Shaoshan Liu, Meng Li 3/18/2026

EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

On-device object-goal navigation agent system using small LLMs with navigation map caching for zero-shot embodied AI.

Ax Prajit Bhaskaran, Tom Viering 3/18/2026

Transformers can do Bayesian Clustering

Transformer-based model extending Prior-Data Fitted Networks for Bayesian clustering with uncertainty quantification on synthetic data.

Ax Mingchen Tu, Zhiqiang Liu, Juan Li, Liangyurui Liu, Junjie Wang, Lei Liang, Wen Zhang 3/18/2026

Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models

Self-evolution framework for LLMs using ontology rules to reduce hallucinations in specialized domains like healthcare and law.

Ax Daichi Nagai, Ryugo Morita, Shunsuke Kitada, Hitoshi Iyatomi 3/18/2026

TAUE: Training-free Noise Transplant and Cultivation Diffusion Model

Training-free diffusion model enhancement for multi-layer text-to-image generation without fine-tuning.

Ax Yubo Wang, Haoyang Li, Fei Teng, Lei Chen 3/18/2026

AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs

Graph-based retrieval-augmented generation system addressing hallucination, reasoning transparency, and answer quality for LLMs.

Ax Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li 3/18/2026

Exploring the Underwater World Segmentation without Extra Training

Large-scale underwater segmentation dataset and open-vocabulary segmentation models for marine organism recognition.

Ax Xuan Yu, Tianyang Xu 3/18/2026

Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network

Deep learning method for geometric representation learning on Grassmannian manifolds using multi-subspace fusion.

Ax Zhenyuan Huang, Hui Zhang, Wenzhong Tang, Haijun Yang 3/18/2026

FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OOD

Federated learning approach addressing data distribution shifts using causal inference for out-of-distribution robustness.

Ax Niranjan Chebrolu, Kokil Jaidka, Gerard Christopher Yeo 3/18/2026

From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation

Method for steering LLM behavior through activation injection to enhance empathy and negotiation capabilities using attribution patching.

Ax Yuxuan Gu, Weimin Bai, Yifei Wang, Weijian Luo, He Sun 3/18/2026

Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

Research on masked auto-regressive diffusion models optimizing inference speed for reinforcement learning applications through architectural improvements.

Ax Alper Y{\i}ld{\i}r{\i}m, \.Ibrahim Y\"uceda\u{g} 3/18/2026

Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks

PRISM complex-valued encoder with phase-based spectral filtering shows semantic relationships correlate with phase angles in neural sequence models.

Ax Zhou Tao, Shida Wang, Yongxiang Hua, Haoyu Cao, Linli Xu 3/18/2026

DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model

DiG differential grounding proxy task enhances fine-grained visual perception in MLLMs by learning differences between image pairs for precise spatial reasoning.

Ax Raktim Gautam Goswami, Amir Bar, David Fan, Tsung-Yen Yang, Gaoyue Zhou, Prashanth Krishnamurthy, Michael Rabbat, Farshad Khorrami, Yann LeCun 3/18/2026

World Models for Learning Dexterous Hand-Object Interactions from Human Videos

DexWM world model predicts latent environmental states for fine-grained dexterous hand-object interactions from human videos.

Ax Ellie Y. Cheng, Logan Weber, Tian Jin, Michael Carbin 3/18/2026

Sharing State Between Prompts and Programs

Programming abstraction for shared state between prompts and programs, enabling interoperability between natural language and traditional programming with LLMs.

Ax Ignacio Heredia, \'Alvaro L\'opez Garc\'ia, Fernando Aguilar G\'omez, Diego Aguirre, Caterina Alarc\'on Mar\'in, Khadijeh Alibabaei, Lisana Berberi, Miguel Caballer, Amanda Calatrava, Pedro Castro, Alessandro Costantini, Mario David, Jaime D\'iez Stefan Dlugolinsky, Borja Esteban Sanchis, Giacinto Donvito, Leonhard Duda, Sa\'ul Fernandez, Andr\'es Heredia Canales, Valentin Kozlov, Sergio Langarita, Jo\~ao Machado, Germ\'an Molt\'o, Daniel San Mart\'in, Martin \v{S}eleng, Giang Nguyen, Marcin P{\l}\'ociennik, Marta Obreg\'on Ruiz, Susana Rebolledo Ruiz, Vicente Rodriguez, Judith S\'ainz-Pardo D\'iaz, Viet Tran 3/18/2026

AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

AI4EOSC federated cloud platform for AI in scientific research with reproducible ML lifecycle management across distributed e-Infrastructures.

Ax Junli Liang, Pengfei Zhou, Wangqiu Zhou, Wenjie Qing, Qi Zhao, Ziwen Wang, Qi Song, Xiangyang Li 3/18/2026

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering

SentGraph hierarchical sentence graph enables multi-hop retrieval-augmented generation by constructing coherent evidence chains from multiple documents for complex QA.

Ax Adib Sakhawat, Tahsin Islam, Takia Farhin, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan 3/18/2026

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias

Audits political alignment in 26 LLMs using psychometric inventories and news bias labeling across prompt variants to evaluate behavioral bias.

Ax Yu Wang, Yi Wang, Rui Dai, Yujie Wang, Kaikui Liu, Xiangxiang Chu, Yansheng Li 3/18/2026

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

Vision-language reasoning for urban socio-semantic segmentation from satellite imagery, distinguishing socially-defined categories beyond physical attributes.

Ax Vatsal Venkatkrishna, Indraneil Paul, Iryna Gurevych 3/18/2026

Aletheia: What Makes RLVR For Code Verifiers Tick?

Ablates RLVR pipeline components for code verifiers: intermediate thinking traces, negative samples, and on-policy training to reduce adoption cost barriers.

Ax Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer 3/18/2026

CFM: Language-aligned Concept Foundation Model for Vision

CFM language-aligned concept foundation model decomposes vision model representations into human-interpretable concepts with spatial grounding for diverse downstream tasks.

Ax Shinwoo Park, Yo-Sub Han 3/18/2026

From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text

LREAD rubric-based framework with three-phase expert study calibrates human detection of LLM-generated Korean text to improve attribution accuracy beyond surface-level assessment.

Ax Jingxuan Wu, Zhenglin Wan, Xingrui Yu, Yuzhe Yang, Yiqiao Huang, Ivor Tsang, Yang You 3/18/2026

Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models

Time-annealed perturbation sampling for diffusion language models enables diverse generation across semantic and reasoning paths by controlling temporal denoising.

Ax Weiming Sheng, Jinlang Wang, Manuel Barros, Aldrin Montana, Jacopo Tagliabue, Luca Bigon 3/18/2026

Building a Correct-by-Design Lakehouse. Data Contracts, Versioning, and Transactional Pipelines for Humans and Agents

Bauplan code-first lakehouse with data contracts, versioning, and transactional pipelines for concurrent AI/analytics workloads supporting both human and agent workflows.

Ax William Lugoloobi, Thomas Foster, William Bankes, Chris Russell 3/18/2026

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

Predicts LLM success from pre-generation internal activations using linear probes to enable efficient inference routing on math and coding tasks.

Ax Yixuan Shen, Peng He, Honglu Liu, Jinxuan Fan, Yuyang Ji, Tingting Li, Tianlong Chen, Kaidi Xu, Feng Liu 3/18/2026

Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos

Benchmark evaluating multimodal LLMs' ability to understand pedagogical reasoning and science instruction in K-12 classroom videos with model-based explanations.

Ax Shan Yang, Yang Liu 3/18/2026

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

Descent-guided policy gradient method addresses cross-agent noise scaling in multi-agent reinforcement learning, improving sample complexity from O(N/ε) to sublinear bounds.

Ax Zebin Yang, Tong Xie, Baotong Lu, Shaoshan Liu, Bo Yu, Meng Li 3/18/2026

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

KEEP system optimizes KV-cache memory management for memory-augmented LLMs in embodied planning, reducing prompt length and prefill latency for long-horizon tasks.

Ax Magda Dubois, Cozmin Ududec, Christopher Summerfield, Lennart Luettgau 3/18/2026

Ask don't tell: Reducing sycophancy in large language models

Experimental study of sycophancy in LLMs—tendency to favor user-affirming over critical responses—with controlled interventions to identify and prevent the alignment failure.

Ax Shravani Hariprasad 3/18/2026

Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare

Evaluates 5 open-source small LLMs (Gemma, Phi, Llama, Mistral, Meditron) for clinical QA reliability and prompt sensitivity in low-resource healthcare settings.

Ax Pei Yang, Wanyi Chen, Asuka Yuxi Zheng, Xueqian Li, Xiang Li, Haoqin Tu, Jie Xiao, Yifan Pang, Dongdong Zhang, Fuqiang Li, Alfred Long, Lynn Ai, Eric Yang, Bill Shi 3/18/2026

AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis

AOI: Trainable multi-agent LLM framework for autonomous cloud diagnosis and SRE automation learning from failed trajectories.

Ax Jialong Chen, Xander Xu, Hu Wei, Chuan Chen, Bing Zhao 3/18/2026

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

SWE-CI: Benchmark evaluating LLM agent capabilities in continuous integration for long-term codebase maintenance and feature iterations.

Ax Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang 3/18/2026

Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection

Optimizes KV cache in transformers by reducing key dimensionality to log(N) while preserving value information for efficiency.

Ax Mohammed Baharoon, Thibault Heintz, Siavash Raissi, Mahmoud Alabbad, Mona Alhammad, Hassan AlOmaish, Sung Eun Kim, Oishi Banerjee, Pranav Rajpurkar 3/18/2026

CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation

CRIMSON: Clinically-grounded LLM metric for evaluating chest X-ray report generation on diagnostic correctness and patient safety.

Ax Yuanyuan Sun, Timothy Parker, Lara Gierschmann, Sana Shams, Teo Canmetin, Mathieu Duteil, Rokas Gipi\v{s}kis, Ze Shen Chin 3/18/2026

Defining AI Models and AI Systems: A Framework to Resolve the Boundary Problem

Systematic framework defining boundaries between AI models and AI systems for regulatory and policy compliance purposes.

Ax Ali Raza, Gurang Gupta, Nikolay Matyunin, Jibesh Patra 3/18/2026

Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models

Amnesia: Adversarial semantic activation steering technique for controlling harmful content generation in large language models.

Ax Alejandro Pradas-Gomez, Arindam Brahma, Ola Isaksson 3/18/2026

DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice

DUCTILE: Agentic LLM orchestration framework for automating engineering analysis and tool coordination in product development.

Ax Omar Coser 3/18/2026

ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics

ELISA: Interpretable AI agent combining scGPT embeddings with BioBERT for expression-grounded discovery in single-cell genomics.

Ax Reva Schwartz, Gabriella Waters 3/18/2026

Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma

FRAME: Systematic framework for real-world AI evaluation generating contextual evidence on model behavior in organizational environments.

Ax Kun Chen, Qingchao Kong, Zhao Feifei, Wenji Mao 3/18/2026

APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution

APEX-Searcher: LLM agent with agentic planning for multi-hop retrieval-augmented generation to enhance complex question answering.

Ax Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang, Shao-Yi Chien, Yu Tsao, Fan-Gang Zeng 3/18/2026

LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement

Audio-visual speech enhancement using RL with LLM-based interpretable reward model for perceptual quality optimization.

Ax Sumedha Chugh, Ranjitha Prasad, Nazreen Shah 3/18/2026

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

arXiv: Post-hoc model-agnostic explanation method using perturbation selection for uncertainty-aware surrogate model approximations.