Ax Bhada Yun, Evgenia Taranova, Dana Feng, Renn Su, April Yi Wang 3/11/2026

AI Phenomenology for Understanding Human-AI Experiences Across Eras

AI phenomenology framework examining subjective human-AI experiences beyond performance metrics and usability scales.

Ax Tony Mason 3/11/2026

The Missing Memory Hierarchy: Demand Paging for LLM Context Windows

Research framing LLM context windows as L1 cache; proposes demand paging and virtual memory hierarchy for efficient token reuse.

Ax Janakan Sivaloganathan, Ainaz Jamshidi, Andriy Miranskyy, Lei Zhang 3/11/2026

Automating Detection and Root-Cause Analysis of Flaky Tests in Quantum Software

Automated detection and root-cause analysis pipeline for flaky tests in quantum software systems.

Ax Tenny Yin, Zhiting Mei, Zhonghe Zheng, Miyu Yamane, David Wang, Jade Sceats, Samuel M. Bateman, Lihan Zha, Apurva Badithela, Ola Shorinwa, Anirudha Majumdar 3/11/2026

PlayWorld: Learning Robot World Models from Autonomous Play

PlayWorld: autonomous pipeline training action-conditioned video models for robot simulators from large-scale datasets.

Ax Zekun Long, Ali Zia, Guanyiman Fu, Vivien Rolland, Jun Zhou 3/11/2026

WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion

WS-Net uses state-space modeling and attention mechanisms for hyperspectral image unmixing, addressing weak signal collapse in abundance estimation tasks.

Ax Hongyu Cao, Jinghan Zhang, Kunpeng Liu, Dongjie Wang, Feng Xia, Haifeng Chen, Xiaohua Hu, Yanjie Fu 3/11/2026

Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation

Sim2Act improves simulation-to-reality transfer for robot policies using adversarial calibration and perturbation methods to handle prediction errors in decision-critical regions.

Ax Xingyu Bruce Liu, Mira Dontcheva, Dingzeyu Li 3/11/2026

A Text-Native Interface for Generative Video Authoring

Doki is a text-native interface for generative video creation, enabling users to author videos through natural language writing instead of specialized video editing tools.

Ax Md Selim Sarowar, Omer Tariq, Sungho Kim 3/11/2026

GST-VLA: Structured Gaussian Spatial Tokens for 3D Depth-Aware Vision-Language-Action Models

GST-VLA introduces Gaussian spatial tokenization for vision-language-action models, adding 3D geometric structure awareness to improve robot perception and decision-making.

Ax Alvaro Paredes Amorin, Andre Python, Christoph Weisser 3/11/2026

Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting

Finetuned LLMs extract sentiment signals from textual data to forecast aluminum commodity prices, exploring when these signals are most predictive.

Ax Rongxiang Zeng, Yongqi Dong 3/11/2026

Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges

Survey paper on latent world models and vision-language-action systems for autonomous driving, covering taxonomy, evaluation frameworks, and challenges.

Ax Yuheng Wang, Yuji Lin, Dongrun Zhu, Jiayue Cai, Sunil Kalia, Harvey Lui, Chunqi Chang, Z. Jane Wang, Tim K. Lee 3/11/2026

Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations

Vision-language retrieval framework for skin cancer case search using composed image-text queries with global and local representation alignment.

Ax Xiyao Wang, Xiaoyu Tan, Yang Dai, Yuxuan Fu, Shuo Li, Xihe Qiu 3/11/2026

VIVID-Med: LLM-Supervised Structured Pretraining for Deployable Medical ViTs

VIVID-Med uses frozen LLMs as structured semantic teachers for pretraining medical vision transformers, improving clinical image analysis.

Ax Jiang Gao, Xiangyu Dong, Haozhou Li, Haoran Zhao, Yaoming Zhou, Xiaoguang Ma 3/11/2026

PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings

Language-driven embodied navigation system using semantic priori-maps and chain-of-thought prompting for functional buildings.

Ax Yifan Han, Zhongxi Chen, Yuxuan Zhao, Congsheng Xu, Yanming Shao, Yichuan Peng, Yao Mu, Wenzhao Lian 3/11/2026

DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation

Human-in-the-loop framework for post-training vision-language-action models in robotic dexterous manipulation tasks.

Ax Zhen Zhang, Jielei Chu, Tianrui Li 3/11/2026

Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning

Research on mitigating catastrophic forgetting in class-incremental learning using causal feature expansion methods.

Ax Tzu-Heng Huang, Sirajul Salekin, Javier Movellan, Frederic Sala, Manjot Bilkhu 3/11/2026

RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning

Rubric-guided reinforcement learning framework for dense image captioning that improves diversity and generalization over supervised distillation from VLMs.

Ax Siyang Cai, Cangyuan Li, Yinhe Han, Ying Wang 3/11/2026

Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL

Method learning netlist representations from LLM-generated imperfect RTL code, scaling beyond small circuits using self-correction and structural learning.

Ax Jianing Yang, Yusuke Fujita, Yui Sudo 3/11/2026

DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization

Full-duplex speech-to-speech dialogue system combining cascaded ASR-LLM-TTS without VAD segmentation, enabling natural conversational interaction.

Ax Lina Berrayana, Ahmed Heakl, Abdullah Sohail, Thomas Hofmann, Salman Khan, Wei Chen 3/11/2026

Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning

Framework bridging discrete diffusion language models with autoregressive models to enable non-sequential global reasoning and plan revision in multi-agent systems.

Ax Benjamin Reichman, Adar Avasian, Samuel Webster, Larry Heck 3/11/2026

Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing

Study analyzing emotion as a latent representational factor in LLM reasoning and attention mechanisms, rather than just a prediction target.

Ax SangYeop Jeong, Yeongseo Na, Seung Gyu Jeong, Jin-Woo Jeong, Seong-Eun Kim 3/11/2026

Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents

VR agent pipeline that integrates prosodic emotional context from speech into LLM dialogue processing for emotionally-aware conversational responses.

Ax Yang Li, Xing Chen, Yutao Liu, Gege Qi, Yanxian BI, Zizhe Wang, Yunjian Zhang, Yao Zhu 3/11/2026

Beyond Scaling: Assessing Strategic Reasoning and Rapid Decision-Making Capability of LLMs in Zero-sum Environments

Research evaluating LLMs as interactive agents in adversarial, time-sensitive zero-sum environments, assessing strategic reasoning and decision-making beyond static benchmarks.

Ax Jiashuo Sun, Yixuan Xie, Jimeng Shi, Shaowen Wang, Jiawei Han 3/11/2026

TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation

TaSR-RAG uses taxonomy-guided structured reasoning to improve retrieval-augmented generation systems, addressing context redundancy and multi-hop reasoning challenges in LLM-based knowledge systems.

Ax Xiong Zhang, Hong Peng, Changlong Fu, Xin Jin, Yun Yang, Cheng Xie 3/11/2026

TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection

Testing-time adaptive graph neural network for cross-domain anomaly detection addressing domain shift challenges.

Ax Anshul Thakur, Soheila Molaei, Pafue Christy Nganjimi, Joshua Fieggen, Andrew A. S. Soltan, Danielle Belgrave, Lei Clifton, David A. Clifton 3/11/2026

Democratising Clinical AI through Dataset Condensation for Classical Clinical Models

Dataset condensation technique for classical clinical models enabling privacy-preserving synthetic data generation.

Ax Yanshan Li, Ke Ma, Miaomiao Wei, Linhui Dai 3/11/2026

M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition

Contrastive learning method for skeleton-based action recognition using multi-view mini-max game framework.

Ax Nikola Jovi\v{s}i\'c, Milica \v{S}kipina, Nicola Dall'Asen, Dubravko \'Culibrk 3/11/2026

MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification

Multiple instance learning approach for mammography classification using foundation model features with weak supervision.

Ax Swaminathan S K, Aritra Hazra 3/11/2026

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space

Offline-to-online reinforcement learning method for safe robot policy alignment using action space constraints.

Ax Yaping Zhang, Yupu Liang, Zhiyang Zhang, Zhiyuan Chen, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong 3/11/2026

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

Competition for end-to-end document image translation combining OCR and NLP for complex layout preservation.

Ax Taesung Kwon, Lorenzo Bianchi, Lennart Wittke, Felix Watine, Fabio Carrara, Jong Chul Ye, Romann Weber, Vinicius Azevedo 3/11/2026

Reviving ConvNeXt for Efficient Convolutional Diffusion Models

Fully convolutional diffusion model using ConvNets for efficient generative modeling compared to transformer alternatives.

Ax Zirui Zhang, Yaping Zhang, Lu Xiang, Yang Zhao, Feifei Zhai, Yu Zhou, Chengqing Zong 3/11/2026

PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue

Prompt-based document layout analysis framework using domain-specific descriptive knowledge for improved multi-domain generalization.

Ax Trung Hieu Ngo, Adrien Bazoge, Solen Quiniou, Pierre-Antoine Gourraud, Emmanuel Morin 3/11/2026

Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health

Benchmark evaluating gender stereotypes in LLMs across healthcare contexts with intersectional social determinants of health factors.

Ax Nicolas Schischka, Nikhil Gosala, B Ravi Kiran, Senthil Yogamani, Abhinav Valada 3/11/2026

Open-World Motion Forecasting

Motion forecasting system for autonomous vehicles handling open-world scenarios with imperfect perception and evolving object taxonomy.

Ax Saugata Purkayastha, Pranav Kushare, Pragya Paramita Pal, Sukannya Purkayastha 3/11/2026

Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs

Benchmark dataset and analysis of LLM bias showing models prioritize moral reasoning over commonsense knowledge.

Ax Yoon Jo Kim, Wonyoung Cho, Jongmin Lee, Han Joo Chae, Hyunki Park, Sang Hoon Seo, Noh Jae Myung, Kyungmi Yang, Dongryul Oh, Jin Sung Kim 3/11/2026

A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation

AI agent framework for automated clinical target volume delineation in radiotherapy that adapts to guideline changes without retraining.

Ax Jiajun Cao, Xiaoan Zhang, Xiaobao Wei, Liyuqiu Huang, Wang Zijian, Hanzhen Zhang, Zhengyu Jia, Wei Mao, Hao Wang, Xianming Liu, Shuchang Zhou Liu, Yang Wang, Shanghang Zhang 3/11/2026

EvoDriveVLA: Evolving Autonomous Driving Vision-Language-Action Model via Collaborative Perception-Planning Distillation

Vision-language-action model for autonomous driving combining perception and planning distillation to improve stability.

Ax David Baumgartner, Helge Langseth, Kenth Eng{\o}-Monsen, Heri Ramampiaro 3/11/2026

Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection

Normalizing flows framework for time series anomaly detection with temporal conditioning and uncertainty quantification.

Ax Enming Zhang, Jiayang Li, Yanru Wu, Zhenyu Liu, Yang Li 3/11/2026

Evolving Prompt Adaptation for Vision-Language Models

Vision-language model adaptation method using evolutionary prompt learning to prevent catastrophic forgetting while maintaining parameter efficiency.

Ax Cosmo Santoni 3/11/2026

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

Research on portable O(1) autoregressive caching for state-space models via XLA compilation, removing hardware-specific kernel dependencies.

Ax Alessio Masano, Giovanni Bellitto, Dipam Goswani, Joost Van de Weijer, Concetto Spampinato 3/11/2026

Routing without Forgetting

Research on online continual learning in transformers using routing mechanisms without catastrophic forgetting in non-stationary data streams.

Ax Simon Brandt, Paul Haider, Walter Senn, Federico Benitez, Mihai A. Petrovici 3/11/2026

A Variational Latent Equilibrium for Learning in Cortex

Research on biologically-inspired learning algorithm addressing backpropagation limitations for complex temporal pattern recognition in cortex-like systems.

Ax \"Umit Mert \c{C}a\u{g}lar, Alptekin Temizel 3/11/2026

Grounding Synthetic Data Generation With Vision and Language Models

Framework for interpretable synthetic data generation using vision-language models with grounded evaluation metrics for downstream tasks.

Ax Anupam Purwar, Aditya Choudhary 3/11/2026

MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings

Research on persona-adaptive prompting for evaluating multi-modal LLM agents in customer experience scenarios with dual-control interactions.

Ax Tianyi Zeng, Jincheng Gao, Tianyi Wang, Zijie Meng, Miao Zhang, Jun Yin, Haoyuan Sun, Junfeng Jiao, Christian Claudel, Junbo Tan, Xueqian Wang 3/11/2026

When to Lock Attention: Training-Free KV Control in Video Diffusion

Training-free KV-Lock framework for video diffusion models improving foreground quality while maintaining background consistency.

Ax Federico Bello, Gonzalo Chiarlone, Marcelo Fiori, Gast\'on Garc\'ia Gonz\'alez, Federico Larroca 3/11/2026

GNNs for Time Series Anomaly Detection: An Open-Source Framework and a Critical Evaluation

Open-source framework for time series anomaly detection using graph neural networks with critical evaluation and standardized benchmarks.

Ax Jacopo Vitale, David Della Morte, Luca Bacco, Mario Merone, Mark de Groot, Saskia Haitjema, Leandro Pecchia, Bram van Es 3/11/2026

Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health Records

ML research benchmarking three paradigms for automated cardiac risk classification from unstructured electronic health records using large-context LLMs.

Ax Nguyen Anh Tuong, Phan Ba Duc, Nguyen Trung Quoc, Tran Dac Thinh, Dang Duy Lan, Nguyen Quoc Thinh, Tung Le 3/11/2026

AutoViVQA: A Large-Scale Automatically Constructed Dataset for Vietnamese Visual Question Answering

Large-scale Vietnamese VQA dataset automatically constructed using pre-trained transformers.

Ax Dechuan Teng, Chunlin Lu, Libo Qin, Wanxiang Che 3/11/2026

ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling

Unified instruction-tuning framework for task-oriented dialog systems using schema-aware prompting.

Ax Davit Melikidze, Marian Schneider, Jessica Lam, Martin Wertich, Ido Hakimi, Barna P\'asztor, Andreas Krause 3/11/2026

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

Active learning pipeline for efficient preference data generation to improve RLHF alignment of LLMs.

Ax Chih-Kai Yang, Yun-Shao Tsai, Yu-Kai Guo, Ping-Le Tsai, Yen-Ting Piao, Hung-Wei Chen, Ting-Lin Hsiao, Yun-Man Hsu, Ke-Han Lu, Hung-yi Lee 3/11/2026

MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models

Benchmark and improvement strategies for multi-audio understanding in large audio-language models.