Ax Shayan Kiyani, Sima Noorani, George Pappas, Hamed Hassani 2/20/2026

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning

Framework distinguishing weak verification (self-consistency, proxy rewards) from strong verification (human inspection) in LLM reasoning loops.

Ax Xinghong Fu, Yanhong Li, Georgios Papaioannou, Yoon Kim 2/20/2026

Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting

Reverso foundation model for efficient zero-shot time series forecasting across diverse domains.

Ax Keith Burghardt, Jienan Liu, Sadman Sakib, Yuning Hao, Bo Li 2/20/2026

FAMOSE: A ReAct Approach to Automated Feature Discovery

FAMOSE framework uses ReAct paradigm with LLM agents for autonomous feature engineering in tabular data.

Ax Dhruv Talwar, Harsh Desai, Wendong Yin, Goutam Mohanty, Rafael Reveles 2/20/2026

A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning

Deep learning system using YOLOx for automated e-waste classification and material sorting.

Ax Xiaohan Zhao, Zhaoyi Li, Yaxin Luo, Jiacheng Cui, Zhiqiang Shen 2/20/2026

Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting

Black-box adversarial attacks on large vision-language models using fine-grained detail targeting to overcome gradient-free optimization challenges.

Ax Sima Noorani, Shayan Kiyani, Hamed Hassani, George Pappas 2/20/2026

Multi-Round Human-AI Collaboration with User-Specified Requirements

Framework for multi-round human-AI collaboration using counterfactual harm and complementarity principles to ensure conversational AI reliably improves decision quality.

Ax Payel Bhattacharjee, Osvaldo Simeone, Ravi Tandon 2/20/2026

MARS: Margin-Aware Reward-Modeling with Self-Refinement

Margin-aware reward modeling framework with self-refinement for RLHF/RLAIF alignment pipelines, reducing reliance on human preference data through augmentation.

Ax Liang Mi, Weijun Wang, Jinghan Chen, Ting Cao, Haipeng Dai, Yunxin Liu 2/20/2026

Efficient Remote Prefix Fetching with GPU-native Media ASICs

Efficient KV cache prefetching for LLM inference using GPU-native media ASICs, addressing bandwidth limitations in remote cache reuse scenarios.

Ax Bjorn Johnson, Jared Levy 2/20/2026

Speech to Speech Synthesis for Voice Impersonation

Speech to Speech Synthesis Network for voice style transfer and impersonation combining speech recognition and synthesis.

Ax Hua Yan, Heng Tan, Yingxue Zhang, Yu Yang 2/20/2026

Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation

MobCache framework using LLMs for scalable large-scale human mobility simulation with caching optimization.

Ax Shahriar Golchin, Marc Wetter 2/20/2026

Intent Laundering: AI Safety Datasets Are Not What They Seem

Study showing AI safety datasets overrely on obvious triggering cues and fail to reflect realistic adversarial attacks.

Ax Rebin Saleh, Khanh Pham Dinh, Bal\'azs Vill\'anyi, Truong-Son Hy 2/20/2026

Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance

SEMAS self-evolving multi-agent system for industrial IoT predictive maintenance with real-time anomaly detection.

Ax Scott Thornton 2/20/2026

Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis

Empirical study of adversarial code comments manipulating LLM vulnerability detection across Python, JavaScript, and Java.

Ax Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan, Chathrie Wimalasooriya, Yakub Sebastian, Roshan G. Ragel, Zhongwei Liang 2/20/2026

U-FedTomAtt: Ultra-lightweight Federated Learning with Attention for Tomato Disease Recognition

Lightweight federated learning with attention mechanism for tomato disease recognition on edge devices.

Ax Simon Lermen, Daniel Paleka, Joshua Swanson, Michael Aerni, Nicholas Carlini, Florian Tram\`er 2/20/2026

Large-scale online deanonymization with LLMs

Large-scale deanonymization attack using LLM agents with internet access to re-identify pseudonymous online profiles.

Ax Kejian Shi, Yixin Liu, Peifeng Wang, Alexander R. Fabbri, Shafiq Joty, Arman Cohan 2/20/2026

References Improve LLM Alignment in Non-Verifiable Domains

Using reference-guided LLM-evaluators as soft verifiers to improve LLM alignment in non-verifiable domains.

Ax Yonatan Gideoni, Sebastian Risi, Yarin Gal 2/20/2026

Simple Baselines are Competitive with Code Evolution

Comparison of simple baselines against code evolution techniques across mathematical bounds, agentic scaffolds, and ML competitions.

Ax Yiqing Xie, Emmy Liu, Gaokai Zhang, Nachiket Kotalwar, Shubham Gandhi, Sathwik Acharya, Xingyao Wang, Carolyn Rose, Graham Neubig, Daniel Fried 2/20/2026

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

Hybrid-Gym environment for training coding agents on diverse software engineering tasks beyond single GitHub issues.

Ax Gen\'is Ruiz-Men\'arguez, Lloren\c{c} Badiella 2/20/2026

The Impact of Formations on Football Matches Using Double Machine Learning. Is it worth parking the bus?

Double Machine Learning framework to estimate causal impact of football formations on match outcomes.

Ax Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi 2/20/2026

NeST: Neuron Selective Tuning for LLM Safety

NeST selective neuron tuning approach for parameter-efficient LLM safety alignment without full fine-tuning overhead.

Ax Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani, Babak Khalaj 2/20/2026

MALLVI: a multi agent framework for integrated generalized robotics manipulation

MALLVi multi-agent framework combining LLMs and vision for closed-loop robotic manipulation with environmental feedback.

Ax Juliusz Ziomek, William Bankes, Lorenz Wolf, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic 2/20/2026

LLM-WikiRace: Benchmarking Long-term Planning and Reasoning over Real-World Knowledge Graphs

LLM-WikiRace benchmark for evaluating long-term planning, reasoning, and knowledge navigation in language models over Wikipedia.

Ax G. Laskaris, D. Morozov, D. Tarpanov, A. Seth, J. Procelewska, G. Sai Gautam, A. Sagingalieva, R. Brasher, A. Melnikov 2/20/2026

Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials on organic and inorganic compounds

Multi-objective optimization and quantum hybridization of Allegro interatomic potential model for molecular property prediction.

Ax Kiana Farhadyar, Maren Hackenberg, Kira Ahrens, Charlotte Schenk, Bianca Kollmann, Oliver T\"uscher, Klaus Lieb, Michael M. Plichta, Andreas Reif, Raffael Kalisch, Martin Wolkewitz, Moritz Hess, Harald Binder 2/20/2026

A statistical perspective on transformers for small longitudinal cohort data

Transformer architecture applied to longitudinal cohort data modeling with attention mechanisms for temporal dependencies.

Ax Junhui Cai, Ran Chen, Qitao Huang, Linda Zhao, Wu Zhu 2/20/2026

Poisson-MNL Bandit: Nearly Optimal Dynamic Joint Assortment and Pricing with Decision-Dependent Customer Arrivals

Dynamic joint assortment and pricing optimization with decision-dependent customer arrivals using bandit algorithms.

Ax Justin Albrethsen, Yash Datta, Kunal Kumar, Sharath Rajasekar 2/20/2026

DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs

DeepContext framework for stateful monitoring of multi-turn LLM conversations to detect adversarial intent drift and bypass safety guardrails.

Ax Mingzhe Cui, Tao Chen, Yang Jiao, Yiqin Wang, Lei Xie, Yi Pan, Luca Mainardi 2/20/2026

BrainRVQ: A High-Fidelity EEG Foundation Model via Dual-Domain Residual Quantization and Hierarchical Autoregression

BrainRVQ: EEG foundation model using dual-domain residual quantization and hierarchical autoregression for brain signal reconstruction.

Ax Hejia Zhang, Zhongming Yu, Chia-Tung Ho, Haoxing Ren, Brucek Khailany, Jishen Zhao 2/20/2026

LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation

LLM4Cov: offline agent learning framework for hardware verification testbench generation using execution-aware LLM agents without online reinforcement learning.

Ax Xinhao Deng, Jiaqing Wu, Miao Chen, Yue Xiao, Ke Xu, Qi Li 2/20/2026

Automating Agent Hijacking via Structural Template Injection

Phantom: automated agent hijacking attack via structural template injection, bypassing LLM safety measures with higher success rates and transferability.

Ax Rahul Thomas, Arka Pal 2/20/2026

Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling

Greedy multi-path verification algorithm accelerating speculative decoding by optimizing token acceptance in draft models.

Ax Srikumar Nayak 2/20/2026

HQFS: Hybrid Quantum Classical Financial Security with VQC Forecasting, QUBO Annealing, and Audit-Ready Post-Quantum Signing

Hybrid quantum-classical system combining variational quantum circuits, QUBO optimization, and post-quantum cryptography for finance.

Ax Divyam Madaan, Sumit Chopra, Kyunghyun Cho 2/20/2026

Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling

PRIMO model quantifying predictive importance of modalities in multimodal LLMs when data is incomplete or asynchronous.

Ax Rong Fu, Zijian Zhang, Haiyun Wei, Jiekai Wu, Kun Liu, Xianda Li, Haoyu Zhao, Yang Li, Yongtai Liu, Ziming Wang, Rui Lu, Simon Fong 2/20/2026

LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation

Neural ranking system for personalized exercise recommendation addressing long-tailed engagement distribution.

Ax Deepak Uniyal, Md Abul Bashar, Richi Nayak 2/20/2026

Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data

Cross-lingual text classification methods for analyzing multilingual social media discourse across multiple languages.

Ax Xinyu Dai, Daniel Chen, Yian Qian 2/20/2026

Dynamic Decision-Making under Model Misspecification: A Stochastic Stability Approach

Analysis of Thompson Sampling performance in Bayesian reinforcement learning under model misspecification.

Ax Srijan Sood, Kassiani Papasotiriou, Marius Vaiciulis, Tucker Balch 2/20/2026

Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization

Comparison of deep reinforcement learning versus mean-variance optimization for portfolio allocation.

Ax Sie Hendrata Dharmawan, Peter Chin 2/20/2026

Simplify to Amplify: Achieving Information-Theoretic Bounds with Fewer Steps in Spectral Community Detection

Streamlined spectral algorithm for community detection in stochastic block models with reduced preprocessing steps.

Ax Juntong Chen, Claire Donnat, Olga Klopp, Johannes Schmidt-Hieber 2/20/2026

Semi-Supervised Learning on Graphs using Graph Neural Networks

Theoretical analysis of when and why graph neural networks succeed in semi-supervised node regression tasks.

Ax Sorawit Saengkyongam, Juan L. Gamella, Andrew C. Miller, Jonas Peters, Nicolai Meinshausen, Christina Heinze-Deml 2/20/2026

Anti-causal domain generalization: Leveraging unlabeled data

Domain generalization approach leveraging unlabeled data in anti-causal settings where outcomes cause observed features.

Ax Etienne Lempereur, Nathana\"el Cuvelle--Magar, Florentin Coeurdoux, St\'ephane Mallat, Eric Vanden-Eijnden 2/20/2026

MGD: Moment Guided Diffusion for Maximum Entropy Generation

Diffusion-based method for generating high-dimensional samples from moment constraints with maximum entropy guarantees.

Ax Arka Pal, Louai Zahran, William Gvozdjak, Akilesh Potti, Micah Goldblum 2/20/2026

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs

Privacy-preserving mechanism enabling verification that LLM inference providers run the correct model without replacing it with a weaker one.

Ax Zeyu Zhang, Ryan Chen, Bradly C. Stadie 2/20/2026

All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection in LLM Backtesting

Framework for detecting temporal contamination in LLM backtesting by identifying post-cutoff knowledge leakage during training.

Ax Marcin P{\l}odzie\'n 2/20/2026

Quantum Scrambling Born Machine

Quantum generative modeling approach using fixed entangling unitaries with optimized single-qubit rotations.

Ax Evgeniia Tokarchuk, Maya K. Nachesa, Sergey Troshin, Vlad Niculae 2/20/2026

Representation Collapse in Machine Translation Through the Lens of Angular Dispersion

Analysis of representation collapse in Transformer-based neural machine translation models using angular dispersion metrics.

Ax Hui Min Wong, Philip Heesen, Pascal Janetzky, Martin Bendszus, Stefan Feuerriegel 2/20/2026

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions

AI agent for medical diagnosis that uses LLMs to ask follow-up questions and reason over differential diagnoses iteratively.

Ax Valdemar \v{S}v\'abensk\'y, Brendan Flanagan, Erwin Daniel L\'opez Zapata, Atsushi Shimada 2/20/2026

Open Datasets in Learning Analytics: Trends, Challenges, and Best PRACTICE

Survey of open datasets used in learning analytics, educational data mining, and AI in education research.

Ax Lorenzo Caselli, Marco Mistretta, Simone Magistri, Andrew D. Bagdanov 2/20/2026

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery

Spectral method for discovering novel categories in unlabeled data using cross-modal representation learning.

Ax Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj, David Skarbrevik 2/20/2026

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study

Taxonomy for uncertainty quantification in long-form LLM outputs to detect hallucinations, addressing limitations of existing short-form methods.

Ax Mateusz Nowak, Xavier Cadet, Peter Chin 2/20/2026

ABCD: All Biases Come Disguised

Study of position and label biases in LLM multiple-choice question answering via synthetic benchmark evaluation.

Ax Qilong Cheng, Matthew Mackay, Ali Bereyhi 2/20/2026

IRIS: Learning-Driven Task-Specific Cinema Robot Arm for Visuomotor Motion Control

Learning-based robotic camera system for autonomous cinematic motion control using visuomotor control.