Ax Chin-Chia Michael Yeh, Uday Singh Saini, Xin Dai, Xiran Fan, Shubham Jain, Yujie Fan, Jiarui Sun, Junpeng Wang, Menghai Pan, Yingtong Dou, Yuzhong Chen, Vineeth Rakesh, Liang Wang, Yan Zheng, Mahashweta Das 20d ago

TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding

TREASURE foundation model for transaction understanding in payment networks, enabling anomaly detection and consumer insights at scale.

Ax Run Shao, Ziyu Li, Zhaoyang Zhang, Linrui Xu, Xinran He, Hongyuan Yuan, Bolei He, Yongxing Dai, Yiming Yan, Yijun Chen, Wang Guo, Haifeng Li 20d ago

Asking like Socrates: Socrates helps VLMs understand remote sensing images

Socratic questioning framework improving VLM understanding of remote sensing images by addressing pseudo-reasoning and incomplete perception issues.

Ax Huangsen Cao, Qin Mei, Zhiheng Li, Yuxi Li, Zhan Meng, Ying Zhang, Chen Li, Zhimeng Zhang, Xin Ding, Yongwei Wang, Jing Lyu, Fei Wu 20d ago

REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

REVEAL framework for detecting AI-generated images with forensic explainability through structured reasoning rather than post-hoc rationalizations.

Ax Junnan Liu, Hongwei Liu, Songyang Zhang, Kai Chen 20d ago

Rectifying LLM Thought from Lens of Optimization

Analysis of chain-of-thought reasoning in LLMs from optimization lens, addressing overthinking and performance issues in long-CoT prompting.

Ax Chihyeon Song, Jaewoo Lee, Jinkyoo Park 20d ago

Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning

Adaptive Replay Buffer for offline-to-online reinforcement learning that dynamically balances fixed offline data with new online experiences.

Ax Yuqun Zhang, Yuxuan Zhao, Sijia Chen 20d ago

PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents

PyFi framework for financial image understanding using vision-language models with adversarial agents and 600K QA dataset organized in reasoning pyramid.

Ax Carla Crivoi, Radu Tudor Ionescu 20d ago

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study

First empirical study of machine unlearning in hybrid quantum-classical neural networks, adapting classical unlearning methods to variational quantum circuits.

Ax Tianxin Xie, Wentao Lei, Kai Jiang, Guanjie Huang, Pengfei Zhang, Chunhui Zhang, Fengji Ma, Haoyu He, Han Zhang, Jiangshan He, Jinting Wang, Linghan Fang, Lufei Gao, Orkesh Ablet, Peihua Zhang, Ruolin Hu, Shengyu Li, Weilin Lin, Xiaoyang Feng, Xinyue Yang, Yan Rong, Yanyun Wang, Zihang Shao, Zelin Zhao, Chenxing Li, Shan Yang, Wenfu Wang, Meng Yu, Dong Yu, Li Liu 20d ago

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

Benchmark for evaluating physics-grounded audio in text-to-audio-video generation models.

Ax Md Ajoad Hasan, Dipayan Saha, Khan Thamid Hasan, Nashmin Alam, Azim Uddin, Sujan Kumar Saha, Mark Tehranipoor, Farimah Farahmandi 20d ago

LAsset: An LLM-assisted Security Asset Identification Framework for System-on-Chip (SoC) Verification

LLM-assisted framework for identifying security assets in SoC designs to improve pre-silicon security verification.

Ax Nelvin Tan, Yaowen Zhang, James Asikin Cheung, Fusheng Liu, Yu-Ching Shih, Dong Yang 20d ago

Improved Evidence Extraction and Metrics for Document Inconsistency Detection with LLMs

LLM-based framework for document inconsistency detection with improved evidence extraction capabilities and metrics.

Ax Xiang Li, Xueheng Li, Yu Wang, Xuanhua He, Zhangchi Hu, Weiwei Yu, Chengjun Xie 20d ago

Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing

RL-enhanced MLLM approach for high-resolution image quality assessment using context-aware multi-scale visual probing.

Ax Md Nabi Newaz Khan, Abdullah Arafat Miah, Yu Bi 20d ago

BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack

Multi-targeted backdoor attack method for graph neural networks using injection-based trigger mechanisms.

Ax Daixuan Cheng, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen, Furu Wei 20d ago

Computer Environments Elicit General Agentic Intelligence in LLMs

Framework virtualizing computer environments as interactive tools to elicit general agentic intelligence capabilities in LLMs.

Ax Evangelos Georganas, Alexander Heinecke, Pradeep Dubey 20d ago

Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple

Space filling curves applied to communication-avoiding matrix multiplication for efficient HPC and deep learning workloads.

Ax Jun Xue, Yi Chai, Yanzhen Ren, Jinshen He, Zhiqiang Tang, Zhuolin Yi, Yihuan Huang, Yuankun Xie, Yujie Chen 20d ago

Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs

Audio LLM-based approach for detecting speech editing and localizing manipulated content without frame-level supervision.

Ax Shiyu Liu, Xinyi Wen, Zhibin Lan, Ante Wang, Jinsong Su 20d ago

Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework

Self-validation framework mitigating object hallucination in Large Vision-Language Models via structured analysis.

Ax Powei Chang, Jinpeng Zhang, Bowen Chen, Chenyu Wang, Chenlu Guo, Yixing Zhang, Yukang Gao, JianXiang Xiang, Yue Gao, Chaoqun Sun, Yiyi Chen, Dongying Kong 20d ago

SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training

Submodular-based data selection for efficient LLM instruction tuning by addressing gradient conflicts in Fisher information.

Ax Basile Terver, Randall Balestriero, Megi Dervishi, David Fan, Quentin Garrido, Tushar Nagarajan, Koustuv Sinha, Wancong Zhang, Mike Rabbat, Yann LeCun, Amir Bar 20d ago

A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures

Open-source library for learning representations and world models using Joint-Embedding Predictive Architectures.

Ax J Rosser, Robert Kirk, Edward Grefenstette, Jakob Foerster, Laura Ruis 20d ago

Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions

Framework using influence functions to craft training data perturbations that induce targeted behavior changes in models.

Ax Paul Tschisgale, Peter Wulff 20d ago

Daily and Weekly Periodicity in Large Language Model Performance and Its Implications for Research

Longitudinal study revealing daily and weekly performance variations in LLMs, impacting research reproducibility and reliability.

Ax Jose Rojas, Aristotelis Papatheodorou, Sergi Martinez, Andrea Patrizi, Ioannis Havoutis, Carlos Mastalli 20d ago

ODYN: An All-Shifted Non-Interior-Point Method for Quadratic Programming in Robotics and AI

Quadratic programming solver for robotics and AI using shifted primal-dual methods with strong warm-start capabilities.

Ax Bowei Zhang, Jin Xiao, Guanglei Yue, Qianyu He, Yanghua Xiao, Deqing Yang, Jiaqing Liang 20d ago

What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty

System for recommending quotations that are semantically unexpected yet rational in writing contexts.

Ax Alex Morehead, Miruna Cretu, Antonia Panescu, Rishabh Anand, Maurice Weiler, Tynan Perez, Samuel Blau, Steven Farrell, Wahid Bhimji, Anubhav Jain, Hrushikesh Sahasrabuddhe, Pietro Lio, Tommi Jaakkola, Rafael Gomez-Bombarelli, Rex Ying, N. Benjamin Erichson, Michael W. Mahoney 20d ago

Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials

Open-source foundation model for 3D chemical systems combining generative and predictive capabilities for molecules and materials.

Ax Yinghong Yu, Guangyuan Li, Jiancheng Yang 20d ago

PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters

Training-free adapter-free operator for lifting 2D foundation models to 3D volumetric data without retraining.

Ax Dmitriy Rivkin, Parker Ewen, Lili Gao, Julian Ost, Stefanie Walz, Rasika Kangutkar, Mario Bijelic, Felix Heide 20d ago

ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation

Proposes truncated backpropagation method to reduce memory costs in video diffusion model training with pixel-wise losses.

Ax Chien-Ping Lu 20d ago

Modernizing Amdahl's Law: How AI Scaling Laws Shape Computer Architecture

Reformulates Amdahl's Law for modern heterogeneous AI systems with constrained resource allocation across diverse hardware.

Ax Lekshmi P, Neha Karanjkar 20d ago

On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins

Proposes design principles for integrating resilience and human oversight into LLM-assisted digital twin modeling workflows.

Ax Xianyong Xu, Yuanjun Zuo, Zhihong Huang, Yihan Qin, Haoxian Xu, Leilei Du, Haotian Wang 20d ago

MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations

MR-CDM: Multi-resolution time series forecasting framework using hierarchical decomposition and diffusion-based generation.

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 20d ago

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

JoyAI-LLM Flash: Efficient Mixture-of-Experts language model in sub-50B parameter range, pretrained on 20 trillion tokens with optimized post-training.

Ax Xiaoan Liu, DaeHo Lee, Eric J Gonzalez, Mar Gonzalez-Franco, Ryo Suzuki 20d ago

VisionClaw: Always-On AI Agents through Smart Glasses

VisionClaw: Always-on wearable AI agent on Meta Ray-Ban glasses, integrating egocentric perception with speech-driven OpenClaw task execution.

Ax Yunyao Yu, Zhengxian Wu, Zhuohong Chen, Hangrui Xu, Zirui Liao, Xiangwen Deng, Zhifang Liu, Senyuan Shi, Haoqian Wang 20d ago

Stabilizing Unsupervised Self-Evolution of MLLMs via Continuous Softened Retracing reSampling

Continuous Softened Retracing reSampling method for stabilizing unsupervised self-evolution of multimodal LLMs during post-training.

Ax Jonas De Schouwer, Haitz S\'aez de Oc\'ariz Borde, Xiaowen Dong 20d ago

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS

k-Maximum Inner Product Attention mechanism for graph transformers, addressing quadratic complexity and analyzing expressive power of GraphGPS.

Ax Hanbin Ko, Kyungmin Jeon, Doowoong Choi, Chang Min Park 20d ago

Temporal Inversion for Learning Interval Change in Chest X-Rays

TILA: Vision-language pretraining method for analyzing temporal changes in chest X-rays rather than individual images.

Ax Bohao Li, Tao Zou, Junchen Ye, Yan Gong, Bowen Du 20d ago

A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs

Deep learning approach for in-hospital mortality prediction from incomplete multimodal EHRs using point cloud paradigm.

Ax James Hu, Mahdi Ghelichi 20d ago

Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms

Empirical robustness analysis of TabPFN tabular foundation model's in-context learning under noisy conditions.

Ax William Yicheng Zhu, Lei Zhu 20d ago

The Planetary Cost of AI Acceleration, Part II: The 10th Planetary Boundary and the 6.5-Year Countdown

Discusses environmental and computational costs of scaling LLM agents beyond human cognitive capacity, framing AI acceleration as paradigm shift.

Ax Xinhong Xu, Yimeng Zhang, Qichen Qian, Yuanlong Zhang 20d ago

Self-Supervised Foundation Model for Calcium-imaging Population Dynamics

CalM: Self-supervised foundation model for calcium-imaging neural data, adaptable to multiple neuroscience analysis tasks.

Ax Chan-Wei Hu, Zhengzhong Tu 20d ago

Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking

Region-R1: Framework for multi-modal retrieval-augmented generation re-ranking using query-side region cropping to improve image-question relevance.

Ax Dominik Blain, Maxime Noiseux 20d ago

Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code

Formal verification study of 3,500 code artifacts from 7 LLMs across 500 security-critical prompts, quantifying exploitable vulnerabilities in AI-generated code.

Ax Tinko Sebastian Bartels, Ruixiang Wu, Xinyu Lu, Yikai Lu, Fanzeng Xia, Haoxiang Yang, Yue Chen, Tongxin Li 20d ago

Bridging Natural Language and Microgrid Dynamics: A Context-Aware Simulator and Dataset

OpenCEM: Open-source digital twin simulator and dataset integrating natural language with renewable energy microgrid dynamics for intelligent energy management.

Ax Amit Vaisman, Gal Pomerants, Raz Lapid 20d ago

On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors

Analyzes robustness of diffusion-based image compression to bit-flip errors, comparing against classical and learned codecs.

Ax Uloma Okoro, Tammy Mackenzie, Branislav Radeljic 20d ago

Governance and Regulation of Artificial Intelligence in Developing Countries: A Case Study of Nigeria

Qualitative case study examining Nigerian legal professionals' perceptions of AI governance, regulatory gaps, and institutional readiness.

Ax Tashreef Muhammad, Tahsin Ahmed, Meherun Farzana, Md. Mahmudul Hasan, Abrar Eyasir, Md. Emon Khan, Mahafuzul Islam Shawon, Ferdous Mondol, Mahmudul Hasan, Muhammad Ibrahim 20d ago

A Benchmark of Classical and Deep Learning Models for Agricultural Commodity Price Forecasting on A Novel Bangladeshi Market Price Dataset

Introduces AgriPriceBD, a benchmark dataset of 1,779 daily commodity prices from Bangladesh, comparing classical and deep learning forecasting models.

Ax Gregory Magarshak 20d ago

Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse

Probabilistic language tries (PLTs) unify prefix structure representation serving as lossless compressor, decision policy, and execution reuse framework.

Ax Gaurav Narasimhan 20d ago

FLeX: Fourier-based Low-rank EXpansion for multilingual transfer

FLeX: Fourier-based low-rank expansion for parameter-efficient cross-lingual code generation transfer from Python to Java using Code Llama 7B.

Ax Yongzhong Xu 20d ago

Spectral Edge Dynamics Reveal Functional Modes of Learning

Analysis of grokking training dynamics showing spectral edge reveals functional modes invisible to mechanistic interpretability tools.

Ax Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Asad Aali, Muhammad Usman Khanzada, Muhammad Usman Rafique, Zihao He, Emily Fox, Dean F. Hougen 20d ago

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

S³: stratified scaling search for test-time inference in diffusion language models using classical verifiers to improve generation without additional training.

Ax Apimuk Sornsaeng, Si Min Chan, Wenxuan Zhang, Swee Liang Wong, Joshua Lim, Dario Poletti 20d ago

SMT-AD: a scalable quantum-inspired anomaly detection approach

Quantum-inspired tensor network anomaly detection (SMT-AD) using superposition of bond-dimension-1 matrix product operators with Fourier feature embeddings.

Ax Zixuan Chen, Heng Zhang, YuPeng Qin, WenPeng Xing, Qiang Wang, Da Wang, Changting Lin, Meng Han 20d ago

MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE

Multimodal VAE framework for survival risk modeling in multiple myeloma integrating heterogeneous omics and clinical data with improved latent regularization.

Ax Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li 20d ago

RAGEN-2: Reasoning Collapse in Agentic RL

RAGEN-2 identifies reasoning collapse in RL-trained multi-turn LLM agents where models use input-agnostic templates despite stable entropy metrics.