Ax Mirali Purohit, Bimal Gajera, Irish Mehta, Bhanu Tokas, Jacob Adler, Steven Lu, Scott Dickenshied, Serina Diniega, Brian Bue, Umaa Rebbapragada, Hannah Kerner 1d ago

MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications

Multi-sensor foundation model merging HiRISE, CTX, and THEMIS Mars remote sensing data via equal validation loss alignment strategy.

Ax Puyu Zeng, Zhaoxi Wang, Zhixu Duan, Liang Feng, Shaobo Wang, Cunxiang Wang, Jinghang Wang, Bing Zhao, Hu Wei, Linfeng Zhang 1d ago

IndustryCode: A Benchmark for Industry Code Generation

Multi-domain benchmark for industry code generation across finance, automation, and aerospace using LLMs, addressing single-domain limitations.

Ax Giyeong Oh, Junghyun Lee, Jaehyun Park, Youngjae Yu, Wonho Bae, Junhyug Noh 1d ago

Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

Evaluation of active preference learning versus random sampling in online DPO for modern LLMs, showing random sampling is surprisingly competitive.

Ax KrishnaSaiReddy Patil 1d ago

SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

Formal framework for verifiable delegation chains in multi-agent AI systems, defining properties for authorization tracking and policy enforcement.

Ax Yongsu Ahn, Nam Wook Kim, Benjamin Bach 1d ago

Disrupting Cognitive Passivity: Rethinking AI-Assisted Data Literacy through Cognitive Alignment

Framework for improving data literacy in AI-assisted analysis by disrupting cognitive passivity through guided reasoning rather than direct answers.

Ax Shreshth Saini, Hakan Gedik, Neil Birkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik 1d ago

LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers

Diffusion transformer method for inverse tone-mapping, converting 8-bit SDR video content to perceptually accurate 10-bit HDR.

Ax Tianze Xu, Yanzhao Zheng, Pengrui Lu, Lyumanshan Ye, Yong Wu, Zhentao Zhang, Yuanqiang Yu, Chao Ma, Jihuai Zhu, Pengfei Liu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu 1d ago

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

Rubric-based RL framework bridging response-level and token-level rewards for LLM alignment in instruction following tasks.

Ax Dexiang Li, Zhenning Che, Haijun Zhang, Dongliang Zhou, Zhao Zhang, Yahong Han 1d ago

PaveBench: A Versatile Benchmark for Pavement Distress Perception and Interactive Vision-Language Analysis

Benchmark dataset for pavement distress assessment using vision-language models, requiring quantitative analysis and interactive decision support.

Ax Lik Tung Fu, Jie Zhou, Shaokai Ren, Mengli Zhang, Jia Xiong, Hugo Jiang, Nan Guan, Xi Wang, Jun Yang 1d ago

ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs

Task-specific LLM framework for generating SystemVerilog assertions for hardware verification, addressing data scarcity and accuracy challenges.

Ax Xinhao Wang, Zhonyu Xia, Zhiwei Lin, Zhe Li, Yongtao Wang 1d ago

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models

Quantization-aware vision token pruning for multimodal LLMs, optimizing coupled compression techniques for resource-constrained deployment.

Ax Hongbo Duan, Peiyu Zhuang, Yi Liu, Zhengyang Zhang, Yuxin Zhang, Pengting Luo, Fangming Liu, Xueqian Wang 1d ago

NavCrafter: Exploring 3D Scenes from a Single Image

Framework for synthesizing novel-view video sequences from single images using diffusion models with geometry-aware expansion strategy.

Ax Zhiyuan Li, Jingzheng Wu, Xiang Ling, Xing Cui, Tianyue Luo 1d ago

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

First comprehensive security analysis of Agent Skills, an open standard for modular LLM agent packages, covering threat taxonomy and vulnerabilities.

Ax Niloofar Asefi, Tianning Wu, Ruoying He, Ashesh Chattopadhyay 1d ago

High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observations

Conditional diffusion model for reconstructing 3D ocean states from sparse surface observations using satellite and in situ data.

Ax Allen He, Qi Liu, Kun Liu, Xinchen Liu, Wu Liu 1d ago

A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos

End-to-end training method for localizing temporal video segments matching sentence queries, addressing task discrepancy in video backbone optimization.

Ax Yixiang Fang, Arijit Khan, Tianxing Wu, Da Yan, Shu Wang 1d ago

LLM+Graph@VLDB'2025 Workshop Summary

Workshop on integrating LLMs with graph-structured data, covering algorithms and systems for bridging LLMs, graph databases, and ML for practical applications.

Ax Baban Gain, Asif Ekbal, Trilok Nath Singh 1d ago

One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging

Study of weight-space model merging for multilingual machine translation, evaluating behavior when combining independently fine-tuned models.

Ax Hai Nguyen-Truong, Alper Balbay, Tunga Bayrak 1d ago

Toward an Artificial General Teacher: Procedural Geometry Data Generation and Visual Grounding with Vision-Language Models

Procedural geometry data generation and visual grounding using vision-language models for geometry education as referring image segmentation.

Ax Gilad Abiri 1d ago

Corporations Constitute Intelligence

Legal analysis of Anthropic's AI constitution document as governance framework, discussing limitations in military and surveillance contexts.

Ax Inbal Rimon, Oren Gal, Haim Permuter 1d ago

Split and Conquer Partial Deepfake Speech

Split-and-conquer framework for detecting partial deepfake speech using boundary detection and segment-level classification stages.

Ax Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang 1d ago

Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus

Council Mode: multi-agent consensus approach mitigating hallucinations and bias in MoE LLMs through coordinated expert activation.

Ax Koshiro Nagano, Ryo Fujii, Ryo Hachiuma, Fumiaki Sato, Taiki Sekii, Hideo Saito 1d ago

Learning from Synthetic Data via Provenance-Based Input Gradient Guidance

Learning method using provenance-based input gradient guidance to improve model discrimination robustness with synthetic training data.

Ax Maciej Markiewicz, Beata Bajcar, Wiktoria Mieleszczenko-Kowszewicz, Aleksander Szcz\k{e}sny, Tomasz Adamczyk, Grzegorz Chodak, Karolina Ostrowska, Aleksandra Sawczuk, Jolanta Babiak, Jagoda Szklarczyk, Przemys{\l}aw Kazienko 1d ago

How Annotation Trains Annotators: Competence Development in Social Influence Recognition

Study of annotator competence development and subjective judgment changes during social influence recognition annotation tasks.

Ax Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang 1d ago

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation

LogicPoison attacks exploiting logical vulnerabilities in Graph-RAG systems that ground LLM reasoning in knowledge graphs.

Ax Cornelius Kummer, Lena Jurkschat, Michael F\"arber, Sahar Vahdati 1d ago

Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference

Measuring latency and quality tradeoffs of prompt compression techniques for accelerating LLM inference in RAG systems.

Ax Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori, Takashi Ishida, Masashi Sugiyama 1d ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Mitigating reward hacking in RLHF by analyzing and correcting flipped advantage signs in reward model parameters.

Ax Arthur C\^amara, Vincent Slot, Jakub Zavrel 1d ago

Self-Optimizing Multi-Agent Systems for Deep Research

Self-optimizing multi-agent system for deep research that iteratively plans, retrieves, and synthesizes evidence across documents.

Ax Cristian P\'erez-Corral, Jose I. Mestre, Alberto Fern\'andez-Hern\'andez, Manuel F. Dolz, Jos\'e Duato, Enrique S. Quintana-Ort\'i 1d ago

FedSQ: Optimized Weight Averaging via Fixed Gating

FedSQ algorithm optimizing weight averaging in federated learning across heterogeneous client data with fixed gating mechanisms.

Ax Wanlong Liu, Bo Zhang, Chenliang Li, Shaopeng Lai, Yuning Wu, Xuanyu Lei, Ming Yan 1d ago

R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning

R2-Write framework exploring deep reasoning with chain-of-thought for open-ended writing tasks using reasoning models.

Ax Jing Du, Zesheng Ye, Congbo Ma, Feng Liu, Flora. D. Salim 1d ago

User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation

Multi-modal recommendation system using generative learning to align visual and textual item content with user preferences.

Ax Hanyu Su, Huilin Zhang, Shihui Feng 1d ago

Comparing the Impact of Pedagogy-Informed Custom and General-Purpose GAI Chatbots on Students' Science Problem-Solving Processes and Performance Using Heterogeneous Interaction Network Analysis

Comparison of pedagogy-informed custom vs general-purpose AI chatbots for supporting students' science problem-solving using network analysis.

Ax KN Ajay Shastry, Ganesh Senrayan, Shrey Satapara, Pranoy Panda, Chaitanya Devaguptapu 1d ago

Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution

SWE-STEPS dataset and framework for evaluating coding agents on sequential, long-horizon software development tasks with accumulated technical debt.

Ax Aichen Cai, Anmeng Zhang, Anyu Li, Bo Zhang, Bohua Cai, Chang Li, Changjian Jiang, Changkai Lu, Chao Xue, Chaocai Liang, Cheng Zhang, Dongkai Liu, Fei Wang, Guoqiang Huang, Haijian Ke, Han Lin, Hao Wang, Ji Miao, Jiacheng Zhang, Jialong Shi, Jifeng Zhu, Jingjing Qian, Junhui Luo, Junwu Xiong, Lam So, Liang Huang, Ming Ke, Mingyang Li, Panfeng Shi, Peng Hao, Qi Wang, Qian Lai, Qiaoqiao Yuan, Qingyu Yin, Qiong Cao, Qixiang Wang, Rongcheng Bian, Rongduo Han, Shaoqiang Zheng, Shi Hu, Shi Suo, Shijie Ren, Shijin Zhang, Shiying Fan, Shuai Xie, Tianyi Zhang, Wei Liu, Wentao Tan, Xianghan Meng, Xiaodong He, Xing Pan, Xiran Wang, Xuyang Peng, Ya Zhang, Yang Liu, Yangyang Duan, Yanxu Chen, Yicheng Gong, Yidan Huang, Yifei Liu, Yinhao Bai, Yongqiang Liu, Yuesong Zhang, Yuqi Zhang, Zerui Xie, Zhenfang Wang, Zhennan Shen, Zheyuan Liu, Zhuwei Zeng 1d ago

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency

JoyAI-LLM Flash, an efficient mixture-of-experts mid-scale LLM with 20 trillion token pretraining optimized for token efficiency.

Ax Hongbin Chen, Jie Li, Wei Wang, Siyang Song, Xiao Gu, Jianqing Li, Wentao Xiang 1d ago

MECO: A Multimodal Dataset for Emotion and Cognitive Understanding in Older Adults

Multimodal emotion and cognitive understanding dataset for older adults addressing gap in emotion prediction research for aging populations.

Ax Hontan Valentin-Micu, Bunea Andrei-Alexandru, Tantaroudas Nikolaos Dimitrios, Popovici Dan-Matei 1d ago

Querying Structured Data Through Natural Language Using Language Models

Open-source methodology enabling natural language queries on structured data by training LLMs to generate executable queries with synthetic training data.

Ax Myra Cheng, Isabel Sieh, Humishka Zope, Sunny Yu, Lujain Ibrahim, Aryaman Arora, Jared Moore, Desmond Ong, Dan Jurafsky, Diyi Yang 1d ago

Verbalizing LLMs' assumptions to explain and control sycophancy

Framework for eliciting and verbalizing LLM assumptions to explain and mitigate sycophancy behavior in user interactions.

Ax Zhihao Chen, Ying Zhang, Yi Liu, Gelei Deng, Yuekang Li, Yanjun Zhang, Jianting Ning, Leo Yu Zhang, Lei Ma, Zhiqiang Li 1d ago

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study

Large-scale empirical study of credential leakage vulnerabilities in 17,022 LLM agent skills, identifying 520 vulnerable skills with taxonomy of 10 leakage patterns.

Ax Yubin Qu, Yi Liu, Tongcheng Geng, Gelei Deng, Yuekang Li, Leo Yu Zhang, Ying Zhang, Lei Ma 1d ago

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

Security study of supply-chain poisoning attacks against LLM coding agents through malicious third-party skills with system-level execution.

Ax David Mike-Ewewie, Panhapiseth Lim, Priyanka Kumar 1d ago

A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification

Vision transformer baseline for synthetic aperture radar sea ice classification addressing class imbalance.

Ax Xinyu Wang, Hanwei Wu, Jingwei Song, Shuyuan Zhang, Jiayi Zhang, Fanqi Kong, Tung Sum Thomas Kwok, Xiao-Wen Chang, Yuyu Luo, Chenglin Wu, Bang Liu 1d ago

Co-Evolution of Policy and Internal Reward for Language Agents

Self-Guide method for co-evolving policy and internal reward in LLM agents, addressing sparse reward bottleneck in long-horizon training.

Ax Zahra Makki Nayeri, Mohsen Rezvani 1d ago

AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs

Knowledge graph completion approach for network alert prediction modeling cyber-attacks as hyper-relational statements.

Ax Zhangyun Tan, Zeliang Zhang, Susan Liang, Yolo Yunlong Tang, Lisha Chen, Chenliang Xu 1d ago

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning

Benchmarking training-free unlearning methods for removing sensitive visual concepts from vision-language models.

Ax Zheng-Xin Yong, Parv Mahajan, Andy Wang, Ida Caspary, Yernat Yestekov, Zora Che, Mosh Levy, Elle Najt, Dennis Murphy, Prashant Kulkarni, Lev McKinney, Kei Nishimura-Gasparian, Ram Potham, Aengus Lynch, Michael L. Chen 1d ago

An Independent Safety Evaluation of Kimi K2.5

Safety evaluation of Kimi K2.5 open-weight LLM assessing CBRNE misuse, cybersecurity, alignment, and bias risks.

Ax Jinsook Lee, Kirk Vanacore, Zhuqian Zhou, Bakhtawar Ahtisham, Rene F. Kizilcec 1d ago

Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts

Domain-adapted RAG pipeline using fine-tuned embedding models for pedagogical dialogue act annotation without generative model fine-tuning.

Ax Yuhang Wang, Haichang Gao, Zhenxing Niu, Zhaoxiang Liu, Wenjing Zhang, Xiang Wang, Shiguo Lian 1d ago

A Systematic Security Evaluation of OpenClaw and Its Variants

Systematic security evaluation of six OpenClaw-series AI agent frameworks identifying vulnerabilities in tool-augmented LLM agents.

Ax Ema Smolic, Mario Brcic, Luka Hobor, Mihael Kovac 1d ago

AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study

Case study of AI-assisted unit test writing and test-driven refactoring for improving legacy codebase maintainability.

Ax Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Tuney Zheng, Fanglin Xu, Weicheng Gu, Lin Jing, Yaxin Du, Joseph Li, Yizhi Li, Yan Xing, Chuan Hao, Ran Tao, Ruihao Gong, Aishan Liu, Zhoujun Li, Mingjie Tang, Chenghua Lin, Siheng Chen, Wayne Xin Zhao, Xianglong Liu, Ming Zhou, Bryan Dai, Weifeng Lv 1d ago

InCoder-32B-Thinking: Industrial Code World Model for Thinking

InCoder-32B-Thinking model trained with Error-driven Chain-of-Thought for industrial code generation with reasoning traces.

Ax Lihao Sun, Lewen Yan, Xiaoya Lu, Andrew Lee, Jie Zhang, Jing Shao 1d ago

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

Method for identifying valence-arousal emotion subspace in LLM representations using steering vectors and PCA.

Ax Prakhar Bansal, Shivangi Agarwal 1d ago

Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

Survey of contextual enrichment strategies for LLMs from in-context prompting through retrieval-augmented generation and GraphRAG.

Ax Gengwei Zhang, Jie Peng, Zhen Tan, Mufan Qiu, Hossein Nourkhiz Mahjoub, Vaishnav Tadiparthi, Kwonjoon Lee, Yanyong Zhang, Tianlong Chen 1d ago

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

Analysis of hallucination effects in reinforcement learning post-training for multimodal LLMs, examining whether RL improves visual reasoning or merely exploits hallucinations.

Ax Nikita Vassilyev, William Berrios, Ruowang Zhang, Bo Han, Douwe Kiela, Shikib Mehri 1d ago

Reflective Context Learning: Studying the Optimization Primitives of Context Space

Research on optimization primitives in context space for AI agents, addressing credit assignment, overfitting, and learning signal challenges.