Ax Hyeongkeun Lee, Jongmin Choi, KiHyun Nam, Joon Son Chung 3/17/2026

LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence

LAMB: LLM-based audio captioning framework bridging modality gap between audio and text using Cauchy-Schwarz divergence.

Ax Zhankai Ye, Bofan Li, Yukai Jin, Shuoqiu Li, Wei Wang, Yanfu Zhang, Shangqian Gao, Xin Liu 3/17/2026

GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models

GeoMotionGPT: LLM framework for motion understanding using geometry-aligned discrete motion tokenization and embeddings.

Ax Youwei Liu, Jian Wang, Hanlin Wang, Beichen Guo, Wenjie Li 3/17/2026

Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

Imagine-then-Plan framework for agent learning using world models and adaptive lookahead for complex task planning.

Ax Yue Chang, Rufeng Chen, Zhaofan Zhang, Yi Chen, Yifan Tian, Sihong Xie 3/17/2026

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

RAG-3DSG: retrieval-augmented generation approach for constructing 3D scene graphs with uncertainty estimation for robotics tasks.

Ax Ibrahim Al Azher, Zhishuai Guo, Hamed Alhoori 3/17/2026

Multi-Agent LLMs for Generating Research Limitations

Multi-agent LLM framework for generating research limitations by identifying methodological issues beyond superficial statements.

Ax Jidong Jin 3/17/2026

Why Inference in Large Models Becomes Decomposable After Training

Research on decomposable inference in large models showing gradient updates are localized, reducing inference costs and complexity.

Ax Toni J. B. Liu, Baran Zadeo\u{g}lu, Nicolas Boull\'e, Rapha\"el Sarfati, Christopher J. Earls 3/17/2026

Jacobian Scopes: token-level causal attributions in LLMs

Jacobian Scopes: gradient-based methods for token-level causal attribution in LLMs to identify which prior tokens influence predictions across layers and attention heads.

Ax Zhiliang Peng, Jianwei Yu, Yaoyao Chang, Zilong Wang, Li Dong, Yingbo Hao, Yujie Tu, Chenyu Yang, Wenhui Wang, Songchen Xu, Yutao Sun, Hangbo Bao, Weijiang Xu, Yi Zhu, Zehua Wang, Ting Song, Yan Xia, Zewen Chi, Shaohan Huang, Liang Wang, Chuang Ding, Shuai Wang, Xie Chen, Furu Wei 3/17/2026

VIBEVOICE-ASR Technical Report

VibeVoice-ASR framework for speech understanding in long-form audio using single-pass processing to handle context fragmentation and multi-speaker scenarios.

Ax Weiye Zhu, Zekai Zhang, Xiangchen Wang, Hewei Pan, Teng Wang, Tiantian Geng, Rongtao Xu, Feng Zheng 3/17/2026

\textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation

NaVIDA improves vision-language navigation agents by explicitly modeling action-grounded visual dynamics for better planning and generalization in embodied environments.

Ax Kaustubh D. Dhole 3/17/2026

BabyReasoningBench: Generating Developmentally-Inspired Reasoning Tasks for Evaluating Baby Language Models

Benchmark for evaluating reasoning in baby language models trained on child-directed speech; developmentally-inspired evaluation methodology.

Ax Shinwoo Park, Yo-Sub Han 3/17/2026

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

Expert-panel study on human detection of LLM-generated Korean text using rubric-based calibration framework for attribution.

Ax Evandro S. Ortigossa, Eran Segal 3/17/2026

Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers

Mixture-of-Experts approach for time-series forecasting transformers using segment-wise routing to improve scaling and temporal dynamics.

Ax Jio Oh, Paul Vicinanza, Thomas Butler, Steven Euijong Whang, Dezhi Hong, Amani Namboori 3/17/2026

Should LLMs, like, Generate How Users Talk? Building Dialect-Accurate Dialog[ue]s Beyond the American Default with MDial

MDial framework for generating multi-dialectal dialogue data; addresses LLM performance gaps for non-standard English speakers.

Ax Haoran Ou, Kangjie Chen, Gelei Deng, Hangcheng Liu, Jie Zhang, Tianwei Zhang, Kwok-Yan Lam 3/17/2026

DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems

Adversarial attacks against search-enabled LLM fact-checking systems; proposes DECEIVE-AFC for testing robustness of retrieval-augmented verification.

Ax Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, Ying Zhang, Leo Yu Zhang 3/17/2026

Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study

First labeled dataset of 98,380 malicious agent skills characterizing security threats in LLM-based agent registries and ecosystems.

Ax Jiale Qian, Hao Meng, Tian Zheng, Pengcheng Zhu, Haopeng Lin, Yuhang Dai, Hanke Xie, Wenxiao Cao, Ruixuan Shang, Jun Wu, Hongmei Liu, Hanlin Wen, Jian Zhao, Zhonglin Jiang, Yong Chen, Shunshun Yin, Ming Tao, Jianguo Wei, Lei Xie, Xinsheng Wang 3/17/2026

SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Open-source singing voice synthesis system with zero-shot generalization and controllable generation capabilities.

Ax Maciej Besta, {\L}ukasz Jarmocik, Orest Hrycyna, Shachar Klaiman, Konrad M\k{a}czka, Robert Gerstenberger, J\"urgen M\"uller, Piotr Nyczyk, Hubert Niewiadomski, Torsten Hoefler 3/17/2026

GraphSeek: Next-Generation Graph Analytics with LLMs

System for natural language graph analytics over large property graphs using LLMs; enables querying complex heterogeneous datasets efficiently.

Ax Seo Hyun Kim, Jin Bok Park, Do Yeon Koo, Hogun Park, Il Yong Chun 3/17/2026

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

Token reduction method for multi-modal LLMs in autonomous driving to improve efficiency while maintaining human-vehicle interaction.

Ax Jiakang Shen, Qinghui Chen, Runtong Wang, Chenrui Xu, Jinglin Zhang, Cong Bai, Feng Zhang 3/17/2026

KAN-FIF: Spline-Parameterized Lightweight Physics-based Tropical Cyclone Estimation on Meteorological Satellite

Physics-based tropical cyclone estimation using spline-parameterized KAN for efficient edge device deployment on satellite data.

Ax Miaosen Zhang, Yishan Liu, Shuxia Lin, Xu Yang, Qi Dai, Chong Luo, Weihao Jiang, Peng Hou, Anxiang Zeng, Xin Geng, Baining Guo 3/17/2026

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

Framework for on-policy supervised fine-tuning of LLMs using Distribution Discriminant Theory to improve generalization over standard SFT.

Ax Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin 3/17/2026

GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture

Generic object tracking method using joint-embedding predictive architecture with model adaptation and occlusion reasoning.

Ax Weiwen Su, Yuhan Zhou, Zihan Wang, Naoki Yoshinaga, Masashi Toyoda 3/17/2026

Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation

Research on identifying missing persona dimensions for user simulation in dialogue systems to improve validity of simulation results.

Ax Yongzhong Xu 3/17/2026

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking

Geometric analysis of optimization dynamics in grokking; shows transformers train in low-dimensional subspaces with detailed PCA findings.

Ax Yongzhong Xu 3/17/2026

Early-Warning Signals of Grokking via Loss-Landscape Geometry

Research on early-warning signals for grokking phenomenon via loss-landscape geometry analysis across sequence learning benchmarks.

Ax Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel 3/17/2026

When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

Investigation of text-to-image diffusion models' effectiveness as synthetic data generators, revealing performance regression when used for training data generation.

Ax Peiliang Cai, Jiacheng Liu, Haowen Xu, Xinyu Wang, Chang Zou, Linfeng Zhang 3/17/2026

LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

LESA method for accelerating diffusion models through learnable stage-aware predictors that adapt to stage-dependent dynamics with feature caching.

Ax Yunpeng Ba, Xi Lin, Changliang Zhou, Ruihao Zheng, Zhenkun Wang, Xinyan Liang, Zhichao Lu, Jianyong Sun, Yuhua Qian, Qingfu Zhang 3/17/2026

Survey on Neural Routing Solvers

Survey of neural routing solvers that use deep learning to tackle vehicle routing problems by learning implicit heuristic rules from data.

Ax Ruihao Pan, Suhang Wang 3/17/2026

A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction

Study of LLM unlearning robustness in multi-turn interactive settings, addressing safety, privacy, and legal concerns in machine unlearning.

Ax Hossein Javidnia 3/17/2026

A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations

Discrete gauge-theoretic framework for understanding superposition in LLMs using sheaf theory and local semantic charts instead of global dictionaries.

Ax Tianxing Chen, Yuran Wang, Mingleyang Li, Yan Qin, Hao Shi, Zixuan Li, Yifan Hu, Yingsheng Zhang, Kaixuan Wang, Yue Chen, Hongcheng Wang, Renjing Xu, Ruihai Wu, Yao Mu, Yaodong Yang, Hao Dong, Ping Luo 3/17/2026

RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design

arXiv paper introducing RMBench robotic manipulation benchmark emphasizing memory-dependent tasks and policy design insights.

Ax Pratik Jawahar, Maurizio Pierini 3/17/2026

CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning

arXiv paper proposing Causal Hamiltonian Learning Unit as deep learning primitive for temporal dynamics addressing LSTM/Neural ODE tradeoffs.

Ax Romina Omidi, Yun Dong, Binghui Wang 3/17/2026

On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation

arXiv paper analyzing Google's SynthID-Text watermarking system for LLM-generated text detection using tournament-based methods.

Ax Grace Chang Yuan, Xiaoman Zhang, Sung Eun Kim, Pranav Rajpurkar 3/17/2026

Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?

arXiv paper evaluating multi-vendor LLM agent teams for clinical diagnosis, testing whether diversity reduces correlated failure modes.

Ax Jiafeng Lin, Mengren Zheng, Simeng Ye, Yuxuan Wang, Huan Zhang, Yuhui Liu, Zhongyi Pei, Jianmin Wang 3/17/2026

Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series

arXiv paper on time series forecasting with multi-dimensional exogenous integration for industrial applications like aviation.

Ax Leo Schwinn, Moritz Ladenburger, Tim Beyer, Mehrnaz Mofakhami, Gauthier Gidel, Stephan G\"unnemann 3/17/2026

A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Study showing LLM-as-a-Judge evaluation frameworks are unreliable for safety assessment, demonstrating vulnerability to distribution shifts in red-teaming.

Ax Sirui Li, Shuhan Xiao, Mihir Joshi, Ahmed Metwally, Daniel McDuff, Wei Wang, Yuzhe Yang 3/17/2026

HEARTS: Benchmarking LLM Reasoning on Health Time Series

HEARTS benchmark for evaluating LLM reasoning on health time series across multiple physiological modalities and temporal dependencies.

Ax Julien Amblard, Niklas Groll, Matthew Tait, Mark Law, G\"urkan Sin, Alessandra Russo 3/17/2026

Failure Detection in Chemical Processes Using Symbolic Machine Learning: A Case Study on Ethylene Oxidation

Symbolic ML approach for failure detection in chemical processes, emphasizing interpretability and safety over neural methods; includes ethylene oxidation case study.

Ax Suyash Fulay, Prerna Ravi, Om Gokhale, Eugene Yi, Michiel Bakker, Deb Roy 3/17/2026

Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

AI-powered platform using LLM personas to teach deliberative democratic skills and consensus-finding through simulated discussion scenarios.

Ax Mohammed Brahimi, Karim Laabassi, Mohamed Seghir Hadj Ameur, Aicha Boutorh, Badia Siab-Farsi, Amin Khouani, Omar Farouk Zouak, Seif Eddine Bouziane, Kheira Lakhdari, Abdelkader Nabil Benghanem 3/17/2026

AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision

ML competition for agricultural vision focusing on data-centric approaches and model generalization under distribution shifts in real field conditions.

Ax Jonas Landsgesell, Pascal Knoll 3/17/2026

Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules

Evaluation framework for tabular foundation models using proper scoring rules to assess full predictive distributions, not just point estimates.

Ax Yehonatan Elisha, Oren Barkan, Noam Koenigstein 3/17/2026

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness

Fine-tuning method for Vision Transformers using concept guidance to reduce spurious correlations and improve robustness to distribution shifts.

Ax Peter Brodeur, Jacob M. Koshy, Anil Palepu, Khaled Saab, Ava Homiar, Roma Ruparel, Charles Wu, Ryutaro Tanno, Joseph Xu, Amy Wang, David Stutz, Wei-Hung Weng, Hannah M. Ferrera, David Barrett, Lindsey Crowley, Jihyeon Lee, Spencer E. Rittner, Ellery Wulczyn, Selena K. Zhang, Elahe Vedadi, Christine G. Kohn, Kavita Kulkarni, Vinay Kadiyala, Sara Mahdavi, Wendy Du, Jessica M. Williams, David Feinbloom, Renee Wong, Tao Tu, Petar Sirkovic, Alessio Orlandi, Christopher Semturs, Yun Liu, Juraj Gottweis, Dale R. Webster, Jo\"elle Barral, Katherine Chou, Pushmeet Kohli, Avinatan Hassidim, Yossi Matias, James Manyika, Rob Fields, Jonathan X. Li, Marc L. Cohen, Vivek Natarajan, Mike Schaekermann, Alan Karthikesalingam, Adam Rodman 3/17/2026

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic

Clinical feasibility study of LLM-based conversational diagnostic AI (AMIE) in real primary care workflows with safety evaluation.

Ax Benjamin Reichman, Adar Avsian, Samuel Webster, Larry Heck 3/17/2026

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

Study of emotion as latent factor affecting LLM reasoning and attention mechanisms, rather than just a prediction target.

Ax Nicolas Schischka, Nikhil Gosala, B Ravi Kiran, Senthil Yogamani, Abhinav Valada 3/17/2026

Open-World Motion Forecasting

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

Ax Jiajun Cao, Xiaoan Zhang, Xiaobao Wei, Liyuqiu Huang, Wang Zijian, Hanzhen Zhang, Zhengyu Jia, Wei Mao, Hao Wang, Xianming Liu, Shuchang Zhou, Yang Wang, Shanghang Zhang 3/17/2026

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

Vision-language-action model for autonomous driving using perception-planning distillation to improve visual encoding and trajectory planning stability.

Ax Ruchira Dhar, Qiwei Peng, Anders S{\o}gaard 3/17/2026

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives

Research on how LLMs handle compositional language tasks (adjective-noun relationships), comparing external performance with internal model representations.

Ax David Fraile Navarro, Farah Magrabi, Enrico Coiera 3/17/2026

Evaluation format, not model capability, drives triage failure in the assessment of consumer health AI

Research comparing LLM performance in healthcare triage across evaluation formats. Shows evaluation methodology significantly affects model assessment outcomes.

Ax Qizhi Chen, Chao Qi, Yihong Huang, Muquan Li, Rongzheng Wang, Dongyang Zhang, Ke Qin, Shuang Liang 3/17/2026

KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation

KEPo: research on knowledge graph poisoning attacks against GraphRAG systems. Analyzes vulnerabilities when LLMs rely on external databases.

Ax Ruiying Li, Yunlang Zhou, YuYao Zhu, Kylin Chen, Jingyuan Wang, Sukai Wang, Kongtao Hu, Minhui Yu, Bowen Jiang, Zhan Su, Jiayao Ma, Xin He, Yongjian Shen, Yang Yang, Guanghui Ren, Maoqing Yao, Wenhao Wang, Yao Mu 3/17/2026

RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

RoboClaw: Agentic framework unifying data collection, policy learning, and deployment for long-horizon robotic manipulation using Vision-Language-Action systems.

Ax Konstantin Krestnikov 3/17/2026

Truth as a Compression Artifact in Language Model Training

Controlled experiments showing language models prefer correct answers due to data compressibility structure rather than truth, using small transformers on contradictory corpora.