Ax Yuan Fang, Yi Xie, Xuming Ran 5/12/2026

HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

Hopfield network-based approach for sequential model editing of LLMs preserving factual knowledge during updates.

Ax Fang Wu, Haokai Zhao, Da Xing, Hanqun Cao, Tinson Xu, Yanchao Li, Xiangru Tang, Zehong Wang, Aaron Tu, Kuan Pang, Hanchen Wang, Hongbin Lin, Zeqi Zhou, Yinxi Li, Peng Xia, Li Erran Li, Molei Tao, Jure Leskovec, Aditya Joshi, Yejin Choi 5/12/2026

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training

Meta-learning framework assigning importance scores to noise instances in diffusion model training.

Ax Yuriel Ryan, Hei Man Ip, Adriel Kuek, Paul Pu Liang, Roy Ka-Wei Lee 5/12/2026

Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models

Method for improving vision-language model robustness by analyzing multimodal redundancy and synergistic information.

Ax Zi-Yi Jia, Zi-Jian Cheng, Xin-Yue Zhang, Kun-Yang Yu, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo 5/12/2026

VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning

First unified benchmark for visual-tabular multimodal learning across 14 datasets in 9 domains.

Ax Jincheng Xie, Yawen Ling, Qi Xiao, Feiyu Zhang, Zhongyi Huang, Wen Hu, Yu Zheng 5/12/2026

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference

Speculative decoding serving framework for resource-efficient multi-model LLM inference using tail models as drafters.

Ax Divya Gupta 5/12/2026

Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures

Federated learning framework integrating zero-knowledge proofs for privacy-preserving distributed AI model training.

Ax Haopeng Jin, Hongzhu Yi, Wenlong Zhao, Jinwen Luo, Shani Ye, Zhenyu Guan, Shiquan Dong, Tiankun Yang, Tao Yu 5/12/2026

HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

Hierarchical video-language model reducing token growth and improving motion perception for long video understanding.

Ax Rebekah Lane, Logan Cummins, Andy Perkins, George Trawick, Ioana Banicescu, Sudip Mittal 5/12/2026

parHSOM: A novel parallel Hierarchical Self-Organizing Map implementation

Parallel implementation of Hierarchical Self-Organizing Maps for intrusion detection systems in cybersecurity.

Ax Ayoub Agouzoul 5/12/2026

Understanding Asynchronous Inference Methods for Vision-Language-Action Models

Methods for reducing inference latency in Vision-Language-Action models through inpainting, delay simulation, and residual correction techniques.

Ax Lurong Pan 5/12/2026

Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count

FFT-based neural network layers using circulant spectral machinery for improved Hessian conditioning with fewer parameters.

Ax Jingze Ge, Xue Geng, Yun Liu, Wanqi Dong, Wang Zhe Mark, Min Wu, Ngai-Man Cheung, Bharadwaj Veeravalli, Xulei Yang 5/12/2026

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning

CERSA parameter-efficient fine-tuning method reducing memory constraints by capturing full rank characteristics of weight updates.

Ax Yihang Peng, Peng Jin, Jie Gong, Xingyuan Chen, Lingjiao Xu, Ning Su, Yan Ran 5/12/2026

Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection

Echo-LoRA parameter-efficient fine-tuning technique injecting cross-layer representations to improve LLM adaptation with lower rank updates.

Ax Zhongzheng Yuan, Lianshuai Guo, Xunkai Li, Wenyu Wang, Meixia Qu 5/12/2026

Generalized Category Discovery in Federated Graph Learning

Federated graph learning framework for discovering novel categories in decentralized graph data without closed-world assumptions.

Ax Hrishikesh Dutta, Roberto Minerva, Reza Farahbakhsh, Noel Crespi 5/12/2026

Information Density as a Quantitative Measure for AI-enabled Virtual Sensing: Feasibility and Limits

Introduces Information Density metric to optimize sensor deployment and enable AI-driven virtual sensing in IoT networks.

Ax Weicai Yan, Xinhua Ma, Wang Lin, Tao Jin 5/12/2026

Text-Guided Multi-Scale Frequency Representation Adaptation

Parameter-efficient fine-tuning method operating in frequency domain with dynamic text-guided adaptation for pre-trained models.

Ax Zhaofan Zhang, Minghao Yang, Rufeng Chen, Sihong Xie, Hui Xiong 5/12/2026

Quantile Geometry Regularization for Distributional Reinforcement Learning

Proposes RQIQN, a Wasserstein distributionally robust enhancement for quantile-based distributional reinforcement learning.

Ax Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe, Helmut Grabner, Patrick Krauss, Achim Schilling 5/12/2026

Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers

Analyzes attention mechanisms in multimodal transformers through neuroscience lens to understand visual interestingness encoding.

Ax Youssef Saied, Fran\c{c}ois Fleuret 5/12/2026

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

Characterizes normalization equivariance in image-to-image prediction networks for improved robustness to distribution shift.

Ax Serafim Batzoglou 5/12/2026

ReplaySCM: A Benchmark for Executable Causal Mechanism Induction from Interventions

Benchmark of 1,300 items for evaluating causal mechanism induction from interventions using executable Boolean DSL.

Ax Farjana Yesmin 5/12/2026

FairHealth: An Open-Source Python Library for Trustworthy Healthcare AI in Low-Resource Settings

Open-source Python library for fairness auditing, privacy preservation, and trustworthy ML in healthcare applications, especially low-resource settings.

Ax Sparsh Tiwari, Bettina Finzel, Gesina Schwalbe 5/12/2026

Weakly Supervised Concept Learning for Object-centric Visual Reasoning

Neurosymbolic framework combining neural networks with symbolic reasoning for visual understanding using weak supervision.

Ax Qingjun Wang, Hongtu Zhou, Hang Yu, Junqiao Zhao, Yanping Zhao, Chen Ye, Ziqiao Wang, Guang Chen 5/12/2026

Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning

Proposes diffusion-based method for detecting out-of-distribution actions in offline reinforcement learning without penalization-based suppression.

Ax Mohammed Aman Bhuiyan, Md Sazzad Hossain Adib, Samiul Basir Bhuiyan, Amit Chakraborty, Aritra Islam Saswato, Ahmed Faizul Haque Dhrubo, Mohammad Ashrafuzzaman Khan 5/12/2026

Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization

Fine-tuning Whisper and PyAnnote models for Bangla speech recognition and speaker diarization on long-form recordings.

Ax Michael Jerge, David Evans 5/12/2026

NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning

Inference-time method improving LLM reliability by injecting controlled noise into latent representations to generate diverse counterfactual outputs.

Ax Chang Meng, Hanyu Wang, Yuyang Ye, Mingfei Yu, Wayne Burleson, Giovanni De Micheli 5/12/2026

TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators

Joint optimization of approximate multiplier structures and AI model training for power-efficient accelerators.

Ax Ruijie Zhang, Haozhe Liang, Da Chang, Li Hu, Fanqi Kong, Huaxiao Yin, Yu Li 5/12/2026

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression

Diagnostic framework for KV cache compression in long-context LLM inference identifying why value-aware eviction selectors succeed or fail.

Ax Bibin Wilson 5/12/2026

TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models

Self-supervised learning approach for microcontroller models under 500K parameters using teacher-guided distillation.

Ax Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu 5/12/2026

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Mechanistic analysis of hallucination in vision-language models caused by geometric over-alignment between visual and language representations.

Ax Andrea Valenzuela Ramirez, Cristian Gutierrez-Gomez, Marta Barroso, Dario Garcia-Gasulla, Sara Royuela 5/12/2026

LLM Translation of Compiler Intermediate Representation

LLM-based translation of compiler intermediate representations between GCC and LLVM for cross-toolchain interoperability.

Ax Yuchu Liu, Rui Zhu, Jingwei Xiong, Haixu Tang 5/12/2026

Can LLMs Predict Polymer Physics Just by Reading Synthesis and Processing Prose?

Study of LLM performance on predicting polymer physical properties from synthesis and processing descriptions.

Ax Saisai Hu 5/12/2026

Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks

Security framework for adversarial robustness in medical decision-making LLM agents with full-link enhancement pipeline.

Ax Pierluca D'Oro, Sneha Silwal, William Wong, Yuxuan Sun, Fanyi Xiao, Manchen Wang, Eric Gan, Allen Bolourchi, Joseph Tighe 5/12/2026

Computer Use at the Edge of the Statistical Precipice

Methodological analysis exposing benchmarking flaws in computer use agents, showing static evaluation metrics fail to measure genuine interactive reasoning.

Ax Krti Tallam 5/12/2026

Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requests

Standardized admission contract framework for heterogeneous AI execution requests including inference, evaluation, and agentic workflows in enterprise systems.

Ax Xiaolin Sun, Zixuan Liu, Yibin Hu, Zizhan Zheng 5/12/2026

Insider Attacks in Multi-Agent LLM Consensus Systems

Analysis of security vulnerabilities in multi-agent LLM systems where malicious agents exploit consensus formation mechanisms.

Ax Jiazheng Li, Chi-Hao Wu, Yunze Liu, Kaize Ding, Jundong Li, Chuxu Zhang 5/12/2026

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning

Memory-augmented agentic approach for understanding ultra-long videos using multimodal LLMs with structured memory retrieval across modalities.

Ax Qianru Zhang, Xinyi Gao, Alexander Zhou, Reynold Cheng, Siu-Ming Yiu, Hongzhi Yin 5/12/2026

Efficient Prompt Learning for Traffic Forecasting

Graph neural network approach for traffic forecasting using prompt learning to improve generalization across spatio-temporal distribution shifts.

Ax Kejia Chen, Jiawen Zhang, Boheng Li, Pengcheng Li, Jian Lou, Zunlei Feng, Mingli Song, Ruoxi Jia, Tianwei Zhang 5/12/2026

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

Technique to mitigate many-shot jailbreak attacks on safety-aligned LLMs by detecting progressive activation drift from harmful demonstrations.

Ax Fan Yang, Binyan Xu, Di Tang, Kehuan Zhang 5/12/2026

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Defense mechanism against backdoor attacks on Graph Neural Networks by analyzing trigger correlations and dependencies rather than surface-level patterns.

Ax Qixin Xiao, Maani Ghaffari 5/12/2026

LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations

World models for embodied AI that learn predictive models from visual observations with physical consistency constraints for reinforcement learning and robotic planning.

Ax Xincheng Yao, Ruoqi Li, Cheng Chen, Daoxin Zhang, Yi Wu, Yao Hu, Chongyang Zhang 5/12/2026

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control

HTPO: Hierarchical token-level RL objective control for balanced exploration-exploitation in LLM reasoning via Chain-of-Thought.

Ax Hyunmog Kim 5/12/2026

Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation

Task-aligned GNN analysis for Electronic Design Automation, aligning graph propagation with native task algebra.

Ax Gleb Molodtsov, Alexander Miasnikov, Aleksandr Beznosikov 5/12/2026

Hierarchical Mixture-of-Experts with Two-Stage Optimization

Hi-MoE: Hierarchical Mixture-of-Experts with two-stage routing optimization balancing load distribution and expert specialization.

Ax Ming Liu 5/12/2026

In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification

In-Context Fixation: LLM label-slot fixation phenomenon where homogeneous demonstration labels collapse few-shot classification accuracy across models.

Ax Daning Cheng, Zeyu Liu, Jun Sun, Fen Xia, Boyang Zhang, Dongping Liu, Yunquan Zhang 5/12/2026

A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks

Theoretical analysis of scaling behavior in normalized residual networks through depth expansion and test-risk mechanisms.

Ax Andrea Gurioli, Federico Pennino, Maurizio Gabbrielli 5/12/2026

Do not copy and paste! Rewriting strategies for code retrieval

Code retrieval via embedding-based methods using LLM rephrasing strategies at varying levels: stylistic, pseudo-code, and natural language transcription.

Ax Abdulvahap Mutlu, \c{S}eng\"ul Do\u{g}an, T\"urker Tuncer 5/12/2026

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters

mHC-SSM: Manifold-constrained hyper-connections for State Space language models with stream-specialized adapters.

Ax Aditya Chattopadhyay, Elvis Nunez, Prannay Kaul, Benjamin Bowman, Evan Becker, Luca Zancato, David Thomas, Wei Xia, Stefano Soatto 5/12/2026

Priming: Hybrid State Space Models From Pre-trained Transformers

Priming: Method to initialize hybrid State-Space models from pre-trained Transformers, achieving faster decoding and smaller caches.

Ax Siyu Wu, Yulong Ye, Zezhen Xiang, Pengzhou Chen, Gangda Xiong, Tao Chen 5/12/2026

LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems

LLMSYS-HPOBench: Hyperparameter optimization benchmark for LLM systems addressing compound configuration spaces and AutoML challenges.

Ax Zhichao Liu, Wenbo Pan, Haining Yu, Ge Gao, Tianqing Zhu, Xiaohua Jia 5/12/2026

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

WebTrap: Security vulnerabilities in browser agents exploited through mid-task prompt injection attacks during navigation, exposing gaps in real-world deployment robustness.

Ax Ziyang You, Xiaoke Yang, Zhanling Fan, Feng Guo, Xiaogen Zhou, Xuxing Lu 5/12/2026

Seed Hijacking of LLM Sampling and Quantum Random Number Defense

SeedHijack demonstrates a backdoor attack exploiting PRNG manipulation in LLM sampling and proposes quantum RNG defense mechanisms.