Ax Alakh Sharma, Gaurish Trivedi, Kartikey Singh Bhandari, Yash Sinha, Dhruv Kumar, Pratik Narang, Jagat Sesh Challa 3/10/2026

Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning

Surrogate-free multi-agent reinforcement learning framework using generative models instead of explicit policy populations.

Ax Giovanni Minelli, Giulio Turrisi, Victor Barasuol, Claudio Semini 3/10/2026

CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation

Transformer architecture using cross-state transition attention for robust robotic manipulation from demonstrations.

Ax He Zhang, Anzhou Zhang, Jian Dai 3/10/2026

FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

Prompting protocol combining objection-raising and revision mechanisms to improve LLM reasoning and self-correction.

Ax Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth 3/10/2026

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks

Multi-turn red-teaming approach using tree-based dialogue and reinforcement learning for discovering LLM vulnerabilities.

Ax Yilong Li, Shuai Zhang, Yijing Zeng, Hao Zhang, Xinmiao Xiong, Jingyu Liu, Pan Hu, Suman Banerjee 3/10/2026

Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices

Hardware-software co-design framework for efficient multimodal model inference on battery-powered edge devices.

Ax Meng Tong, Yuntao Du, Kejiang Chen, Weiming Zhang, Ninghui Li 3/10/2026

Membership Inference Attacks on Tokenizers of Large Language Models

Membership inference attacks on LLM tokenizers as privacy attack surface distinct from model attacks.

Ax Zonghuan Xu, Jiayu Li, Yunhan Zhao, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang 3/10/2026

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models

Backdoor attack on vision-language-action models demonstrating action-level behavioral manipulation vulnerabilities.

Ax Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath 3/10/2026

Ego-Vision World Model for Humanoid Contact Planning

World model and MPC framework for humanoid robot contact planning combining learned representations with sampling-based control.

Ax Yi Zhang, Bolin Ni, Xin-Sheng Chen, Heng-Rui Zhang, Yongming Rao, Houwen Peng, Qinglin Lu, Han Hu, Meng-Hao Guo, Shi-Min Hu 3/10/2026

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Open-source corpus and tools for training fully open multimodal LLMs with improved data quality and reasoning.

Ax Nikolaus Howe, Micah Carroll 3/10/2026

The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs

Study on unintended reasoning behaviors in reinforcement-learning-trained LLMs and chain-of-thought monitoring.

Ax Yuyang Hong, Qi Yang, Tao Zhang, Zili Wang, Zhaojin Fu, Kun Ding, Bin Fan, Shiming Xiang 3/10/2026

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Continual learning method for audio-visual segmentation addressing modality entanglement in sequential tasks.

Ax Pengxiang Cai, Zihao Gao, Wanchen Lian, Jintai Chen 3/10/2026

Reinforcing Numerical Reasoning in LLMs for Tabular Prediction via Structural Priors

Framework enabling LLMs to perform tabular prediction via structural priors and reasoning-focused optimization.

Ax Kai Zeng, Zhanqian Wu, Kaixin Xiong, Xiaobao Wei, Xiangyu Guo, Zhenxin Zhu, Kalok Ho, Lijun Zhou, Bohan Zeng, Ming Lu, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Wentao Zhang 3/10/2026

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Evaluates driving world models as synthetic data generators for autonomous vehicle perception tasks.

Ax Haotian Zhou, Xiaole Wang, He Li, Zhuo Qi, Jinrun Yin, Haiyu Kong, Jianghuan Xu, Huijing Zhao 3/10/2026

LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation

Navigation system using 3D Gaussian Splatting memory for multi-modal visual goal navigation in robotics.

Ax Edouard Lansiaux, Antoine Simonet, Eric Wiel 3/10/2026

SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications

SwiftEmbed: production text embedding system achieving 1.12ms latency and 50k req/s using static token lookup in Rust.

Ax Marcus Hoerger, Muhammad Sudrajat, Hanna Kurniawati 3/10/2026

Vectorized Online POMDP Planning

Research on vectorized online POMDP planning for autonomous robot decision-making under partial observability with parallelization.

Ax Mohd Ruhul Ameen, Akif Islam 3/10/2026

Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach

Research on detecting AI-generated images via diffusion model snap-back reconstruction forensics. Addresses Stable Diffusion and DALL-E detection.

Ax Farjana Aktar, Mohd Ruhul Ameen, Akif Islam, Md Ekramul Hamid 3/10/2026

Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet

Comparative study of interpretable fuzzy reasoning vs deep learning for motor-imagery EEG classification in brain-computer interfaces.

Ax Song Gao, Songyang Zhang, Shusen Jing, Shuai Zhang, Xiangwei Zhou, Yue Wang, Zhipeng Cai 3/10/2026

Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing

Research paper on federated learning of mixture-of-experts models for mobile edge computing and resource-constrained devices.

Ax Jiedong Jiang, Wanyi He, Yuefeng Wang, Guoxiong Gao, Yongle Hu, Jingting Wang, Nailin Guan, Peihao Wu, Chunbo Dai, Liang Xiao, Bin Dong 3/10/2026

FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels

FATE benchmark series for formal algebra theorem proving at multiple difficulty levels. Evaluates LLM capabilities on mathematical reasoning beyond contest problems.

Ax Minsuk Jang, Hyunseo Jeong, Minseok Son, Changick Kim 3/10/2026

Detecting AI-Generated Images via Contextual Anomaly Estimation in Masked AutoEncoders

Detection method for AI-generated images using contextual anomaly estimation in masked autoencoders. Extends DetectGPT approach from text to vision domain.

Ax Irina Proskurina, Marc-Antoine Carpentier, Julien Velcin 3/10/2026

HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection

HatePrototypes: Interpretable representations for hate speech detection covering implicit and explicit hate. Addresses content moderation with transferable embeddings.

Ax Chunming He, Rihan Zhang, Zheng Chen, Bowen Yang, Chengyu Fang, Yunlong Lin, Yulun Zhang, Fengyang Xiao, Sina Farsiu 3/10/2026

UnfoldLDM: Deep Unfolding-based Blind Image Restoration with Latent Diffusion Priors

UnfoldLDM combines deep unfolding networks with latent diffusion models for blind image restoration. Model-based interpretable approach to image processing.

Ax Adarsh Kumarappan, Ayushi Mehrotra 3/10/2026

Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM

Probabilistic certification framework improving SmoothLLM defense against LLM jailbreaking attacks. Addresses robustness guarantees with realistic assumptions.

Ax Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li 3/10/2026

Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion

Yo'City: Agentic framework using self-critic expansion for personalized, boundless 3D city generation. Demonstrates AI agent reasoning in creative generation tasks.

Ax Adarsh Kumarappan, Ananya Mujoo 3/10/2026

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

Automated pipeline for generating multi-turn conversational jailbreak attacks against LLMs using psychological principles like FITD without manual dataset creation.

Ax Selene Cerna, Sara Si-Moussi, Wilfried Thuiller, Hadrien Hendrikx, Vincent Miele 3/10/2026

BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data

Contrastive learning approach for adapting foundation models to domain-specific tasks in Earth observation without full retraining.

Ax Mansi Maheshwari, John C. Raisbeck, Bruno Castro da Silva 3/10/2026

AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning

AltNet addresses plasticity loss in RL-trained neural networks via parameter reset strategies. Research on continual learning for RL agents.

Ax Shuyang Liu, Yang Chen, Rahul Krishna, Saurabh Sinha, Jatin Ganhotra, Reyhan Jabbarvand 3/10/2026

Process-Centric Analysis of Agentic Software Systems

arXiv paper on evaluating agentic systems via process-centric analysis of trajectories and reasoning patterns rather than outcomes alone. Foundational agent analysis framework.

Ax Vegard Flovik 3/10/2026

SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks

SALVE framework for neural network interpretability and control using sparse autoencoders. Mechanistic interpretability research not focused on LLMs or agents.

Ax Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor, Maria Brbic 3/10/2026

Meta-RL Induces Exploration in Language Agents

LaMer: Meta-RL framework enabling LLM agents to actively explore and learn from trial-and-error in multi-turn tasks. Research on agent training methodology.

Ax Saurabh Deochake, Debajyoti Mukhopadhyay 3/10/2026

Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL

arXiv paper analyzing cost trade-offs between reasoning and non-reasoning LLMs for Text-to-SQL tasks on cloud platforms. Empirical efficiency comparison.

Ax Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander 3/10/2026

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

DrivingGen benchmark for generative video world models in autonomous driving. Research on agent simulation and synthetic data generation.

Ax Robert J. Moore, Sungeun An, Farhan Ahmed, Jay Pankaj Gala 3/10/2026

NC-Bench: An LLM Benchmark for Evaluating Conversational Competence

NC-Bench: arXiv benchmark evaluating LLM conversational competence on form/structure vs content. Research paper on LLM evaluation methodology.

Ax Jordan Taylor, William Agnew, Maarten Sap, Sarah E. Fox, Haiyi Zhu 3/10/2026

The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor

Audit of LAION-Aesthetics Predictor studying whose aesthetic values are embedded in visual generative AI training datasets.

Ax Pareesa Ameneh Golnari, Adarsh Kumarappan, Wen Wen, Xiaoyu Liu, Gabriel Ryan, Yuting Sun, Shengyu Fu, Elsie Nallipogu 3/10/2026

DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models

Benchmark with 1,800 code completion instances across 6 languages derived from real developer telemetry; avoids contamination, enables detailed diagnostics.

Ax Huanlin Gao, Ping Chen, Fuyuan Shi, Ruijia Wu, Li YanTao, Qiang Hui, Yuren You, Ting Lu, Chao Tan, Shaoan Zhao, Zhaoxiang Liu, Fang Zhao, Kai Wang, Shiguo Lian 3/10/2026

MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference

Training-free caching framework for Flow Matching inference using average-velocity perspective and Jacobian-vector products for acceleration.

Ax Naufal Suryanto, Muzammal Naseer, Pengfei Li, Syed Talal Wasim, Jinhui Yi, Juergen Gall, Paolo Ceravolo, Ernesto Damiani 3/10/2026

RedSage: A Cybersecurity Generalist LLM

Open-source cybersecurity LLM trained on 11.8B tokens of curated domain data; supports diverse security workflows while protecting sensitive data.

Ax Meng Ding, Zeqing Zhang, Di Wang, Lijie Hu 3/10/2026

In-Run Data Shapley for Adam Optimizer

Data Shapley attribution method for adaptive optimizers like Adam, extending in-run attribution beyond SGD's linear structure.

Ax V\'ictor Yeste, Paolo Rosso 3/10/2026

Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration

Multi-label classification study using Schwartz value hierarchies for sentence-level human value detection on sparse, imbalanced datasets.

Ax Wenze Lin, Zhen Yang, Xitai Jiang, Pony Ma, Gao Huang 3/10/2026

Thickening-to-Thinning: Reward Shaping via Human-Inspired Learning Dynamics for LLM Reasoning

Reward shaping method for LLM reasoning via reinforcement learning, addressing entropy collapse and exploration challenges in verification-based training.

Ax Tomer Kordonsky, Maayan Yamin, Noam Benzimra, Amit LeVi, Avi Mendelson 3/10/2026

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

Study of recurring vulnerabilities in LLM-generated code; introduces FSTab for black-box attacks predicting backend security issues from frontend patterns.

Ax Luke Alexander, Eric Leonen, Sophie Szeto, Artemii Remizov, Ignacio Tejeda, Jarod Alper, Giovanni Inchiostro, Vasily Ilin 3/10/2026

Semantic Search over 9 Million Mathematical Theorems

Semantic search system over 9M mathematical theorems using embeddings to retrieve specific results for mathematicians and theorem-proving agents.

Ax Yicheng Di, Zhanjie Zhang, Yun Wang, Jinren Liu, Jiaqi Yan, Jiyu Wei, Xiangyu Chen, Yuan Liu 3/10/2026

LMMRec: LLM-driven Motivation-aware Multimodal Recommendation

LLM-driven recommendation system using multimodal motivation modeling to improve content preference prediction by incorporating review text and heterogeneous data.

Ax Xinxu Wei, Rong Zhou, Lifang He, Yu Zhang 3/10/2026

Diffusion-Guided Pretraining for Brain Graph Foundation Models

Diffusion-guided pretraining for brain graph foundation models, using learnable augmentation for connectome data instead of random dropping.

Ax Koduvayur Subbalakshmi, Sabbir Hossain Ujjal, Venkata Krishna Teja Mangichetty, Nastaran Jamalipour Soofi 3/10/2026

Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement

CoCoA decoder mitigates LLM hallucinations by detecting representational instability across layers, requiring no training.

Ax Seo Hyun Kim, Jin Bok Park, Do Yeon Koo, Hogun Park, Il Yong Chun 3/10/2026

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving

SToRM token reduction technique optimizes multimodal LLMs for end-to-end autonomous driving with natural language interaction.

Ax Haojun Chen, Zili Zou, Chengdong Ma, Yaoxiang Pu, Haotong Zhang, Yuanpei Chen, Yaodong Yang 3/10/2026

Accelerating Robotic Reinforcement Learning with Agent Guidance

Uses agent guidance from learned policies to accelerate robotic RL, reducing sample inefficiency without 1:1 human supervision.

Ax Peng Cheng, Jiucheng Zang, Qingnan Li, Liheng Ma, Yufei Cui, Yingxue Zhang, Boxing Chen, Ming Jian, Wen Tong 3/10/2026

TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers

TrasMuon optimizer improves Muon-style methods by adding trust-region adaptive scaling for robust gradient updates.

Ax Jorge Carrasco-Pollo, Floor Eijkelboom, Jan-Willem van de Meent 3/10/2026

Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference

Variational flow-matching framework for simulation-based inference with structured domain constraints on posteriors.