Ax Ning Li 4/7/2026

The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics Research

Decomposes quality gap in AI-generated economics papers into research idea quality and execution quality using fine-tuned LMs.

Ax Hangxing Wei, Xiaoyu Chen, Chuheng Zhang, Tim Pearce, Jianyu Chen, Alex Lamb, Li Zhao, Jiang Bian 4/7/2026

Learning Additively Compositional Latent Actions for Embodied AI

Method for learning compositional latent actions from video for embodied AI using structural priors on physical motion.

Ax Paul Saves, Matthieu Mastio, Nicolas Verstaevel, Benoit Gaudou 4/7/2026

From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models

Multi-stage pipeline integrating experimental design with ML surrogates for systematic exploration of agent-based models.

Ax Mete Ismayilzada, Renqing Cuomao, Daniil Yurshevich, Anna Sotnikova, Lonneke van der Plas, Antoine Bosselut 4/7/2026

CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge

Benchmark for evaluating creative problem-solving in LLMs combining logical reasoning, lateral thinking, and commonsense knowledge.

Ax Kenan Tang, Praveen Arunshankar, Andong Hua, Anthony Yang, Yao Qin 4/7/2026

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro

Multi-modal agentic systems for iterative image editing; addresses quality degradation in multi-turn edits through image replication methods.

Ax Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit 4/7/2026

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

Privacy-preserving classroom attention analysis pipeline using OpenPose and gaze estimation. LLM evaluates student engagement from skeletal data without storing video.

Ax Vahidullah Tac, Ellen Kuhl 4/7/2026

Generative AI for material design: A mechanics perspective from burgers to matter

Connects generative AI (diffusion, SDEs) to computational mechanics for material design. Reviews mechanisms and interpretability of generative models.

Ax Daniele Solombrino, Antonio Andrea Gargiulo, Adrian Robert Minut, Luca Zhou, Alessandro Zirilli, Emanuele Rodol\`a 4/7/2026

Zero-Shot Quantization via Weight-Space Arithmetic

Weight-space arithmetic enables zero-shot quantization robustness transfer between models without training. Novel ML technique for model optimization.

Ax Zhaoting Gong, Ran Ran, Fan Yao, Wujie Wen 4/7/2026

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

AEGIS: Scaling homomorphic encrypted transformer inference via hybrid parallelism on multi-GPU. Privacy-preserving ML optimization, niche application.

Ax Matthew Levinson 4/7/2026

MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents

MetaSAEs: Introduces decomposability penalty for training sparse autoencoders with atomic latents. Improves alignment and safety-relevant applications.

Ax Lamyea Maha, Tajmilur Rahman, Chanchal Roy 4/7/2026

Agile Story-Point Estimation: Is RAG a Better Way to Go?

Compares RAG vs standard approaches for Agile story point estimation in sprint planning. arXiv study on LLM application.

Ax Noshin Ulfat, Ahsanul Ameen Sabit, Soneya Binta Hossain 4/7/2026

Measuring LLM Trust Allocation Across Conflicting Software Artifacts

TRACE: Study on how LLMs allocate trust between conflicting code, documentation, and tests. Evaluates trustworthiness in AI-assisted software engineering.

Ax Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou 4/7/2026

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

Introduces vocabulary dropout technique to solve diversity collapse in co-evolutionary LLM self-play curriculum learning. arXiv paper with novel method.

Ax Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii, Oleg Somov, Alexander Panchenko, Elena Tutubalina 4/7/2026

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

LLM-powered evolutionary search automatically discovers unsupervised uncertainty quantification methods as Python programs for claim verification.

Ax Haocheng Tang, Xingyu Dang, Junmei Wang 4/7/2026

Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

Fine-tuning approach adapting DeepSeek-OCR-2 for optical chemical structure recognition by formulating task as image-to-text.

Ax Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce, Badr AlKhamissi, Antoine Bosselut, Antonio Laverghetta Jr., Lonneke van der Plas, Roger E. Beaty 4/7/2026

Large Language Models Align with the Human Brain during Creative Thinking

Study of brain-LLM alignment during creative divergent thinking tasks, measuring correlation between model performance and human neural activity.

Ax Xiaoan Liu, DaeHo Lee, Eric J Gonzalez, Mar Gonzalez-Franco, Ryo Suzuki 4/7/2026

VisionClaw: Always-On AI Agents through Smart Glasses

VisionClaw wearable AI agent on Meta Ray-Ban glasses combining egocentric perception with speech-driven task execution via OpenClaw agents.

Ax Zilin Huang, Zhengyang Wan, Zihao Sheng, Boyue Wang, Junwei You, Yue Leng, Sikai Chen 4/7/2026

Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

Sim2Real-AD framework for zero-shot sim-to-real transfer of VLM-guided RL policies from CARLA simulation to physical autonomous vehicles.

Ax Michael Caosun, Sinan Aral 4/7/2026

The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading

Dynamic model analyzing productivity-skill tradeoffs when workers use AI tools, decomposing productivity effects into expertise-dependent and independent channels.

Ax Benjamin Rombaut 4/7/2026

Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

Taxonomy of LLM-based coding agent architectures analyzing scaffolding code patterns including control loops, tool definitions, and context strategies.

Ax Sing Hieng Wong, Hassan Sajjad, A. B. Siddique 4/7/2026

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

LangFIR uses sparse autoencoders on monolingual data to discover language-specific features for steering LLM output language without parallel corpora.

Ax Daniel Ogenrwot, John Businge 4/7/2026

AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub

AgenticFlict dataset of merge conflicts from AI coding agent pull requests on GitHub, studying integration challenges in collaborative AI-assisted development.

Ax Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita 4/7/2026

CRAFT: Video Diffusion for Bimanual Robot Data Generation

Video diffusion framework (CRAFT) for generating synthetic bimanual robot manipulation demonstrations with temporal coherence.

Ax Sohyeon Kim, Sang Yeon Yoon, Kyeongbo Kong 4/7/2026

Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Models

Phase-aware suppression method to reduce hallucinations in Vision-Language Models without iterative optimization overhead.

Ax Hao Wang, Niels M\"undler, Mark Vero, Jingxuan He, Dawn Song, Martin Vechev 4/7/2026

SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization

SecPI framework for secure code generation using reasoning LLMs through security reasoning internalization, addressing inference-time vulnerability mitigation.

Ax Qusay Muzaffar, David Levin, Michael Werman 4/7/2026

Neural Global Optimization via Iterative Refinement from Noisy Samples

Neural method for black-box global optimization using iterative refinement from noisy samples, addressing multi-modal function optimization.

Ax Ruwei Pan, Junlei Shen, Linhao Wu, Yueheng Zhu, Zixiong Yang, Yakun Zhang, Lu Zhang, Hongyu Zhang 4/7/2026

Toward Executable Repository-Level Code Generation via Environment Alignment

LLM-based approach for multi-file repository code generation with executable validation, addressing dependency resolution and integration challenges.

Ax Ruwei Pan, Jiangshuai Wang, Qisheng Zhang, Yueheng Zhu, Linhao Wu, Zixiong Yang, Yakun Zhang, Lu Zhang, Hongyu Zhang 4/7/2026

Persistent Cross-Attempt State Optimization for Repository-Level Code Generation

LiveCoder framework for repository-level code generation preserving and reusing task-specific state across multiple LLM attempts.

Ax Jinxi Xiang, Mingjie Li, Siyu Hou, Yijiang Chen, Xiangde Luo, Yuanfeng Ji, Xiang Zhou, Ehsan Adeli, Akshay Chaudhari, Curtis P. Langlotz, Kilian M. Pohl, Ruijiang Li 4/7/2026

A Generative Foundation Model for Multimodal Histopathology

Generative foundation model for multimodal histopathology that imputes missing modalities from incomplete medical data.

Ax Yunyao Yu, Zhengxian Wu, Zhuohong Chen, Hangrui Xu, Zirui Liao, Xiangwen Deng, Zhifang Liu, Senyuan Shi, Haoqian Wang 4/7/2026

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

Method for stable unsupervised self-evolution of multimodal LLMs using continuous softened retracing resampling for feedback quality.

Ax Vladimir Beskorovainyi 4/7/2026

AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services

Microservice system using NLP and deep learning to automate classification of citizen appeals in government services.

Ax Yoshinari Fujinuma, Keisuke Sakaguchi 4/7/2026

Unlocking Prompt Infilling Capability for Diffusion Language Models

Unlocks prompt infilling in masked diffusion language models by applying full-sequence masking during supervised finetuning.

Ax Yuqi Zhu, Jintian Zhang, Zhenjie Wan, Yujie Luo, Shuofei Qiao, Zhengke Gui, Da Zheng, Lei Liang, Huajun Chen, Ningyu Zhang 4/7/2026

LightThinker++: From Reasoning Compression to Memory Management

LightThinker++ enables LLMs to dynamically compress intermediate reasoning thoughts into compact representations for efficiency.

Ax Zhifu Wei, Yizhou Dang, Guibing Guo, Chuang Zhao, Zhu Sun 4/7/2026

Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation

Uses LLMs to capture semantic relationships for tail-item sequential recommendation, addressing sparse interaction problem.

Ax Baicheng Chen, Yu Wang, Ziheng Zhou, Xiangru Liu, Juanru Li, Yilei Chen, Tianxing He 4/7/2026

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

CREBench evaluates LLMs on cryptographic binary reverse engineering, assessing capabilities for vulnerability discovery and malware analysis.

Ax Angelos Poulis, Mark Crovella, Evimaria Terzi 4/7/2026

Testing the Limits of Truth Directions in LLMs

Research identifying limitations in universality of linear truth directions in LLM activation spaces across different settings.

Ax Alexander Loth, Martin Kappes, Marc-Oliver Pahl 4/7/2026

Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News

Study measuring human ability to distinguish LLM-generated news from human-written content across six LLM models.

Ax Ragib Shahariar Ayon, Shibbir Ahmed 4/7/2026

AutoReSpec: A Framework for Generating Specification using Large Language Models

AutoReSpec uses LLMs to generate formal specifications for programs, addressing syntax and logic errors through techniques for complex control flow.

Ax Pierrick Lorang, Johannes Huemer, Timothy Duggan, Kai Goebel, Patrik Zips, Matthias Scheutz 4/7/2026

Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulation

Neuro-symbolic framework for robot manipulation using vision-language models and autonomous domain construction.

Ax Jonathan Katzy, Razvan-Mihai Popescu, Erik Mekkes, Arie van Deursen, Maliheh Izadi 4/7/2026

Automated Attention Pattern Discovery at Scale in Large Language Models

Method for discovering repeated attention patterns in large language models at scale for mechanistic interpretability.

Ax Haocheng Ju, Guoxiong Gao, Jiedong Jiang, Bin Wu, Zeming Sun, Leheng Chen, Yutong Wang, Yuefeng Wang, Zichen Wang, Wanyi He, Peihao Wu, Liang Xiao, Ruochuan Liu, Bryan Dai, Bin Dong 4/7/2026

Automated Conjecture Resolution with Formal Verification

Automated framework for research-level mathematical problem solving combining LLMs with formal verification to reliably resolve conjectures and verify proofs.

Ax Dipkumar Patel 4/7/2026

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus

Representational collapse in multi-agent LLM committees: measurement of similarity showing agents produce redundant rationales despite different role prompts, with diversity-aware consensus.

Ax Jonas De Schouwer, Haitz S\'aez de Oc\'ariz Borde, Xiaowen Dong 4/7/2026

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

k-Maximum Inner Product Attention for efficient graph transformers, reducing quadratic complexity while maintaining expressiveness for large-scale graphs.

Ax Hope McGovern, Caroline Craig, Thomas Lippincott, Hale Sirin 4/7/2026

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs

Analysis of analogical reasoning in LLMs comparing probed representations with prompted performance, revealing limitations in latent abstraction and generalization.

Ax Zonghan Li, Yi Liu, Chunyan Wang, Song Tong, Kaiping Peng, Feng Ji 4/7/2026

Enhancing behavioral nudges with large language model-based iterative personalization: A field experiment on electricity and hot-water conservation

Field experiment on LLM agent providing iterative personalized behavioral nudges for electricity and hot-water conservation across intervention rounds.

Ax Haotian Zong, Binze Li, Yufei Long, Sinyin Chang, Jialong Wu, Gillian K. Hadfield 4/7/2026

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation

I-CALM: prompt-only intervention reducing LLM hallucinations by incentivizing confidence-aware abstention through reward scheme announcements and humility principles.

Ax Saad Alqithami 4/7/2026

DC-Ada: Reward-Only Decentralized Observation-Interface Adaptation for Heterogeneous Multi-Robot Teams

DC-Ada: reward-only decentralized adaptation for heterogeneous multi-robot teams, adapting frozen policies to mismatched sensor configurations.

Ax Dalal Alharthi, Ivan Roberto Kawaminami Garcia 4/7/2026

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

Secure-by-design GenAI framework for cloud security and forensics using LLMs with defenses against prompt injection and forensic rigor requirements.

Ax Atahan Dokme, Sriram Vishwanath 4/7/2026

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders

Spatio-temporal sparse autoencoders for interpretable video representation learning, using contrastive objectives and hierarchical grouping to preserve temporal coherence.

Ax Xinyi Ling, Ye Liu, Reza Averly, Xia Ning 4/7/2026

Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation

Multi-turn decision making framework for goal-oriented conversational systems balancing information acquisition and target commitment under user intent uncertainty.