Ax Reshabh K Sharma, Shraddha Barke, Benjamin Zorn 3/26/2026

Willful Disobedience: Automatically Detecting Failures in Agentic Traces

AgentPex: Framework for detecting procedural failures in agentic traces including workflow routing and tool usage violations.

Ax Joshua Rozner, Cory Shain 3/26/2026

Perturbation: A simple and efficient adversarial tracer for representation learning in language models

Method for finding representations in language models via adversarial perturbation without implausible constraints.

Ax Rohan Khetan, Ashna Khetan 3/26/2026

PoliticsBench: Benchmarking Political Values in Large Language Models with Multi-Turn Roleplay

Benchmark (PoliticsBench) measuring political bias in eight LLMs using multi-turn roleplay evaluation.

Ax Yunrui Yu, Hang Su, Jun Zhu 3/26/2026

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness

Research on activation function curvature role in adversarial robustness using Recursive Curvature-Tunable Activation Family.

Ax Xiaoming Zhai 3/26/2026

Generative AI User Experience: Developing Human--AI Epistemic Partnership

Discussion of user experience design for generative AI in education emphasizing human-AI epistemic partnership.

Ax Weixin Chen, Antonio Vergari, Han Zhao 3/26/2026

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

Investigation of vision-language model robustness under distribution shifts using visual deductive reasoning tasks.

Ax Ken Ding 3/26/2026

HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation

HDPO method augmenting RL with privileged self-distillation for LLM mathematical reasoning on unsolvable cliff prompts.

Ax Henry LeCates, Haoze Wu 3/26/2026

The Luna Bound Propagator for Formal Analysis of Neural Networks

Luna: C++ implementation of alpha-CROWN bound propagation for neural network formal verification.

Ax Xiangyi Wei, Fei Wang, Haotian Zhang, Xin An, Haitian Zhu, Lianrui Hu, Yang Li, Changbo Wang, Xiao He 3/26/2026

AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control

Multi-agent robotic platform using AI agents for adaptive chemical laboratory automation handling diverse experimental tasks.

Ax Omar Anwar, Aaron S. G. Robotham, Luca Cortese, Kevin Vinsen 3/26/2026

SM-Net: Learning a Continuous Spectral Manifold from Multiple Stellar Libraries

SM-Net model generating stellar spectra from physical parameters using combined stellar library data.

Ax Junkai Yang, Qirui Wang, Yaoqing Jin, Shuai Ma, Minghan Xu, Shanmin Pang 3/26/2026

Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval

Knowledge-refined network for retrieving partially relevant video segments using semantic context awareness.

Ax Weiming Chen, Qifan Liu, Siyi Liu, Yushun Tang, Yijia Wang, Zhihan Zhu, Zhihai He 3/26/2026

Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation

Latent bias alignment technique for improving diffusion model inversion quality in real-world image reconstruction.

Ax Guoliang Zhao, Ruobing Xie, An Wang, Shuaipeng Li, Huaibing Xie, Xingwu Sun 3/26/2026

Self-Distillation for Multi-Token Prediction

Self-distillation method for multi-token prediction in LLMs to improve inference efficiency and MTP head acceptance rates.

Ax Jiajian Huang, Dongliang Zhu, Zitong YU, Hui Ma, Jiayu Zhang, Chunmei Zhu, Xiaochun Cao 3/26/2026

DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

Multimodal deception detection system using schema-driven approach with multicultural datasets and explainable reasoning.

Ax Wooje Park, Insu Lee, Soohyun Kim, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim 3/26/2026

Revealing Multi-View Hallucination in Large Vision-Language Models

MVH-Bench dataset and analysis of multi-view hallucination in vision-language models processing diverse viewpoint images.

Ax Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong Chang 3/26/2026

High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking

Watermarking system for face content protection against AIGC manipulation and deepfakes with high fidelity recovery.

Ax Hongjie Chen, Hanyu Meng, Huimin Zeng, Ryan A. Rossi, Lie Lu, Josh Kimball 3/26/2026

Variable-Length Audio Fingerprinting

Variable-length audio fingerprinting method using deep learning for robust recognition of distorted recordings.

Ax Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasadan, Sumit Kumar Tetarave, Rod Soto 3/26/2026

Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage

LLM-enabled framework for automated threat hunting using Splunk SOC logs to assist security analysts with APT detection.

Ax Lingjiao Chen, Chi Zhang, Yeye He, Ion Stoica, Matei Zaharia, James Zou 3/26/2026

The Price Reversal Phenomenon: When Cheaper Reasoning Models End Up Costing More

Systematic study of reasoning LLM inference costs revealing pricing reversal phenomenon where cheaper models cost more across 9 diverse tasks.

Ax Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang, Donghan Koo 3/26/2026

SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating

Physics-guided text-to-motion framework for humanoid control using rectified flow and safety gating to prevent kinematic hallucinations.

Ax Nizam Kadir 3/26/2026

From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring

Ensemble of specialized LLMs architecture for adaptive tutoring that separates pedagogical decision-making from response generation.

Ax Allen Nie, Xavier Daull, Zhiyi Kuang, Abhinav Akkiraju, Anish Chaudhuri, Max Piasevoli, Ryan Rong, YuCheng Yuan, Prerit Choudhary, Shannon Xiao, Rasool Fakoor, Adith Swaminathan, Ching-An Cheng 3/26/2026

Understanding the Challenges in Iterative Generative Optimization with LLMs

Analysis of challenges in iterative generative optimization with LLMs for self-improving agents, identifying hidden design choices limiting adoption.

Ax Chinmay Soni, Shivam Chourasia, Gaurav Kumar, Hitesh Kapoor 3/26/2026

Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale

Fine-tuned 8B model for text-to-SQL at scale, reducing API costs and latency for production deployment in conversational applications.

Ax Xiaoyong Guo, Nanjie Li, Zijie Zeng, Kai Wang, Hao Huang, Haihua Xu, Wei Shi 3/26/2026

From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs

Training framework addressing contextual exposure bias in speech-LLMs using teacher error knowledge and contrastive learning.

Ax Han Sun, Qin Li, Peixin Wang, Min Zhang 3/26/2026

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

Method to reduce object hallucinations in LVLMs by rectifying attention imbalance across and within vision-language modalities.

Ax Ye Leng, Junjie Chu, Mingjie Li, Chenhao Lin, Chao Shen, Michael Backes, Yun Shen, Yang Zhang 3/26/2026

When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm

Safety analysis of MLLMs for image generation, identifying semantic understanding capabilities that may introduce new risks compared to diffusion models.

Ax Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov, Dmitry Yudin, Aleksandr Panov 3/26/2026

Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning

Multi-task robotic manipulation framework using knowledge graphs and dynamic relation mechanisms for vision-grounded policy learning.

Ax Fei Bai, Zhipeng Chen, Chuan Hao, Ming Yang, Ran Tao, Bryan Dai, Wayne Xin Zhao, Jian Yang, Hongteng Xu 3/26/2026

Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization

Dual-guidance RL framework for LLMs that combines external execution feedback with internal experience for improved reasoning task learning.

Ax Peng Xu, Yapeng Li, Tinghuan Chen, Tsung-Yi Ho, Bei Yu 3/26/2026

KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits

Graph representation learning method for analog circuit design automation using DC electrical equivalence principles.

Ax Iris Dumeur (CB), J\'er\'emy Anger (CB), Gabriele Facciolo (CB) 3/26/2026

Comparative analysis of dual-form networks for live land monitoring using multi-modal satellite image time series

Comparative study of dual-form attention networks for multi-modal satellite time series analysis in land monitoring applications.

Ax Mingyi Liu 3/26/2026

The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation

Analysis of response homogenization in RLHF-aligned LLMs and its impact on uncertainty estimation methods, identifying alignment-robustness tradeoffs.

Ax Shubham Kumar Nigam, Suparnojit Sarkar, Piyush Patel 3/26/2026

MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare

Multilingual multi-turn medical dialogue dataset for training conversational AI systems in healthcare with improved realism and accessibility.

Ax Cansu Sancaktar, David Zhang, Gabriel Synnaeve, Taco Cohen 3/26/2026

A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula

Scaling RL for LLM code generation using synthetic data pipelines and curriculum learning, addressing data diversity over volume.

Ax Yulin Shen, Xudong Pan, Geng Hong, Min Yang 3/26/2026

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Security analysis of Model Context Protocol (MCP) tool-augmented LLM agents, demonstrating stealthy injection attacks on tool responses.

Ax Xin Zhang, Jianyang Xu, Hao Peng, Dongjing Wang, Jingyuan Zheng, Yu Li, Yuyu Yin, Hongbo Wang 3/26/2026

Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement

Knowledge distillation method using dual-modality (vision + text/CLIP) teacher models to improve student model efficiency and quality.

Ax Faiz Taleb, Ivan Gazeau, Maryline Laurent 3/26/2026

Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage

Privacy analysis of time series imputation models, demonstrating membership inference and attribute leakage vulnerabilities in black-box settings.

Ax Mahbub Ul Alam 3/26/2026

Where Do Your Citations Come From? Citation-Constellation: A Free, Open-Source, No-Code, and Auditable Tool for Citation Network Decomposition with Complementary BARON and HEROCON Scores

Open-source tool for decomposing citation networks and measuring researcher influence through bibliometric scoring (BARON/HEROCON).

Ax Mahdi Dehghan, Graham McDonald 3/26/2026

Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias

Study of fairness impacts in RAG-augmented LLMs, examining if certain demographic groups receive systematically different response quality.

Ax Michael Somma, Markus Gro{\ss}pointner, Paul Zabalegui, Eppu Heilimo, Branka Stojanovi\'c 3/26/2026

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

Multi-agent LLM workflow for automated penetration testing of networked cyber-physical systems and robotic infrastructure using environment grounding.

Ax Jingzhi Fang, Xiong Gao, Renwei Zhang, Zichun Ye, Lei Chen, Jie Zhao, Chengnuo Huang, Hui Xu, Xuefeng Jin 3/26/2026

DVM: Real-Time Kernel Generation for Dynamic AI Models

DVM runtime kernel generation system for efficient compilation of dynamic AI models with variable tensor shapes and control flows.

Ax Yijun Wang, Qiyuan Zhuang, Xiu-Shen Wei 3/26/2026

Embracing Heteroscedasticity for Probabilistic Time Series Forecasting

Probabilistic time series forecasting method embracing heteroscedasticity for uncertainty quantification.

Ax Tianyi Liu, Ye Lu, Linfeng Zhang, Chen Cai, Jianjun Gao, Yi Wang, Kim-Hui Yap, Lap-Pui Chau 3/26/2026

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

Heterogeneous caching accelerates diffusion-based video editing by reusing features across denoising timesteps.

Ax Camilo Chac\'on Sartori 3/26/2026

The Specification Gap: Coordination Failure Under Partial Knowledge in Code Agents

Studies coordination failures when multiple LLM-based code agents implement parts of same class without explicit specification.

Ax Eyal Weiss 3/26/2026

Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?

Graph neural network layer (CSNA) for heterophilous graphs with cost-sensitive neighborhood aggregation.

Ax Davood Soleymanzadeh, Ivan Lopez-Sanchez, Hao Su, Yunzhu Li, Xiao Liang, Minghui Zheng 3/26/2026

Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities

Reviews neural motion planning approaches for robotic manipulators, discussing challenges in generalist manipulation policies.

Ax Dogan Urgun, Gokhan Gungor 3/26/2026

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

Automated reward design framework using LLMs for cooperative multi-agent reinforcement learning with aligned incentives.

Ax Cheng Cui, Ting Sun, Suyin Liang, Tingquan Gao, Zelun Zhang, Jiaxuan Liu, Xueqing Wang, Changda Zhou, Hongen Liu, Manhui Lin, Yue Zhang, Yubo Zhang, Jing Zhang, Jun Zhang, Xing Wei, Yi Liu, Dianhai Yu, Yanjun Ma 3/26/2026

Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

Coarse-to-fine visual processing reduces computational costs in document parsing with vision-language models.

Ax Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun 3/26/2026

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

GameplayQA benchmark for evaluating multimodal LLMs as perceptual backbones for autonomous agents in 3D environments.

Ax Yupei Li, Shuaijie Shao, Manuel Milling, Bj\"orn Schuller 3/26/2026

Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level dropin & Neuroplasticity Mechanisms

Improves deepfake audio detection using neuron-level mechanisms and neuroplasticity. Builds on Wav2Vec and LLMs.

Ax Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson 3/26/2026

Evidence of an Emergent "Self" in Continual Robot Learning

Studies emergent self-awareness in continual robot learning by quantifying invariant cognitive structures.