Ax Hye Sun Yun, Karen Y. C. Zhang, Ramez Kouzy, Iain J. Marshall, Junyi Jessy Li, Byron C. Wallace 4/23/2026

Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?

Evaluates whether LLMs are susceptible to biased framing in medical literature abstracts that employ spin techniques.

Ax Yixuan Even Xu, Yash Savani, Fei Fang, J. Zico Kolter 4/23/2026

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

PODS decouples rollout generation from policy updates in LLM reinforcement learning, addressing compute and memory asymmetry.

Ax Revanth Gangi Reddy, Tarun Suresh, JaeHyeok Doo, Ye Liu, Xuan Phi Nguyen, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Heng Ji, Shafiq Joty 4/23/2026

SweRank: Software Issue Localization with Code Ranking

SweRank uses code ranking with LLMs for software issue localization, reducing latency and cost versus multi-step agentic approaches.

Ax Changjiang Jiang, Wenhui Dong, Zhonghao Zhang, Fengchang Yu, Wei Peng, Xinbin Yuan, Yifei Bi, Ming Zhao, Zian Zhou, Chenyang Si, Caifeng Shan 4/23/2026

IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection

IVY-FAKE provides explainable framework and benchmark for detecting AI-generated images and videos with multidimensional annotations.

Ax Debanjan Dutta, Anish Chakrabarty, Faizanuddin Ansari, Swagatam Das 4/23/2026

On the Existence of Universal Simulators of Attention

Theoretical analysis of transformer attention mechanisms, investigating whether universal simulators of attention exist and are learnable.

Ax Xenia Heilmann, Luca Corbucci, Mattia Cerrato, Anna Monreale 4/23/2026

FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation

Addresses fairness issues in federated learning, proposing FeDa4Fair to evaluate bias at client level across multiple sensitive attributes.

Ax Samuel J. Weisenthal 4/23/2026

Treatment, evidence, imitation, and chat

Investigates LLM capabilities for medical decision-making, comparing approaches including evidence-based medicine and experimental data.

Ax Matthew Anderson Hendricks, Alice Cicirello 4/23/2026

Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams

Automated generation of dynamical system computational models from natural language text using enhanced SysML diagrams and LLMs.

Ax Ioannis Lamprou, Alexander Shevtsov, Ioannis Arapakis, Sotiris Ioannidis 4/23/2026

White-Basilisk: A Hybrid Model for Code Vulnerability Detection

White-Basilisk proposes a hybrid model combining Mamba layers, linear self-attention, and Mixture of Experts for code vulnerability detection.

Ax Ren Zhuang 4/23/2026

The Ratchet Effect in Silico through Interaction-Driven Cumulative Intelligence in Large Language Models

POLIS framework enables LLMs to accumulate knowledge through multi-agent interaction and inference, mimicking cumulative cultural evolution.

Ax David J Goetze, Dahlia J Felten, Jeannie R Albrecht, Rohit Bhattacharya 4/23/2026

FLOSS: Federated Learning with Opt-Out and Straggler Support

FLOSS framework enables federated learning with user opt-out and stragglers support, addressing data privacy in heterogeneous distributed systems.

Ax Wenhan Liu, Xinyu Ma, Weiwei Sun, Yutao Zhu, Yuchen Li, Dawei Yin, Zhicheng Dou 4/23/2026

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

ReasonRank method empowering passage ranking with reasoning ability by leveraging large reasoning models for improved listwise ranking in complex scenarios.

Ax Chenxi Zhou, Pengfei Cao, Jiang Li, Bohan Yu, Jinyu Ye, Jun Zhao, Kang Liu 4/23/2026

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models

Establishes task-stratified knowledge scaling laws for post-training quantized LLMs, analyzing quantization impact on memorization, application, and reasoning capabilities.

Ax Huy Nghiem, Advik Sachdeva, Hal Daum\'e III 4/23/2026

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models

SMARTER framework for explainable toxicity detection using LLMs with synthetic explanation generation and preference optimization for content moderation.

Ax Amit Roy, Abulhair Saparov 4/23/2026

Transformers Can Learn Connectivity in Some Graphs but Not Others

Studies transformer capability to learn transitive relation reasoning in graphs, essential for LLM factual correctness and causal inference tasks.

Ax Shaan Shah, Meenakshi Khosla 4/23/2026

Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport

Multi-Level Optimal Transport (MOT) framework for aligning representational structures across model layers and brain regions with global alignment scoring.

Ax Yikun Ji, Yan Hong, Bowen Deng, Jun Lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang 4/23/2026

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

Locate-Then-Examine two-stage VLM-based forensic framework for detecting AI-generated images using grounded region reasoning for artifact identification.

Ax Shanshan Xu, Santosh T. Y. S. S, Barbara Plank 4/23/2026

From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP

Reframes human label variation in NLP from noise to signal for improving model robustness, particularly relevant for post-training methods with human feedback.

Ax Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang 4/23/2026

LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X

Pilot study testing hypothesis that continual exposure to junk web text induces cognitive decline in LLMs using controlled Twitter/X corpus experiments.

Ax Xue Jiang, Yihong Dong, Mengyang Liu, Hongyi Deng, Tian Wang, Yongding Tao, Rongyu Cao, Binhua Li, Zhi Jin, Wenpin Jiao, Fei Huang, Yongbin Li, Ge Li 4/23/2026

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment

CodeRL+ improves LLM code generation using reinforcement learning with execution semantics alignment, bridging gap between text patterns and functional correctness.

Ax Michal \v{S}tef\'anik, Timothee Mickus, Marek Kadl\v{c}\'ik, Bertram H{\o}jer, Michal Spiegel, Ra\'ul V\'azquez, Aman Sinha, Josef Kucha\v{r}, Philipp Mondorf, Pontus Stenetorp 4/23/2026

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care

Analysis showing LLMs develop universal sinusoidal representations of numbers across different families, with representations largely interchangeable across models.

Ax Xingyao Wang, Simon Rosenberg, Juan Michelini, Calvin Smith, Hoang Tran, Engel Nyst, Rohit Malhotra, Xuhui Zhou, Valerie Chen, Robert Brennan, Graham Neubig 4/23/2026

The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents

OpenHands Software Agent SDK provides a composable, extensible toolkit for building production-ready software engineering agents with flexible implementation and secure execution.

Ax Sunwoo Kim, Geon Lee, Kyungho Kim, Jaemin Yoo, Kijung Shin 4/23/2026

ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation

ItemRAG applies retrieval-augmented generation with item-based similarity to improve LLM-based recommendation systems, addressing cold-start problems.

Ax Georgios Anyfantis, Pere Barlet-Ros 4/23/2026

AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders

AutoGraphAD uses variational graph autoencoders for unsupervised network intrusion detection without requiring labeled datasets.

Ax Shady Agwa, Yikang Shen, Shiwei Wang, Themis Prodromakis 4/23/2026

DISCA: A Digital In-memory Stochastic Computing Architecture Using A Compressed Bent-Pyramid Format

Digital in-memory stochastic computing architecture using compressed bent-pyramid format to optimize AI model matrix multiplication operations.

Ax Bram Silue, Santiago Amaya-Corredor, Patrick Mannion, Lander Willem, Pieter Libin 4/23/2026

Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance

Hybrid-AIRL method combining adversarial inverse reinforcement learning with supervised expert guidance, evaluated on poker game with imperfect information.

Ax Yiming Tang, Harshvardhan Saini, Zhaoqian Yao, Zheng Lin, Yizhen Liao, Qianxiao Li, Mengnan Du, Dianbo Liu 4/23/2026

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima

Research on sparse dictionary learning in mechanistic interpretability, analyzing how neural networks represent concepts as linear directions and encode multiple concepts.

Ax Joyjit Roy, Samaresh Kumar Singh 4/23/2026

Device-Native Autonomous Agents for Privacy-Preserving Negotiations

Device-native autonomous agent system for privacy-preserving automated negotiations in insurance and B2B commerce without centralized servers.

Ax Rishiraj Saha Roy, Chris Hinze, Luzian Hahn, Fabian Kuech 4/23/2026

CEDAR: Context Engineering for Agentic Data Science

CEDAR agentic system automating data science tasks via context engineering, handling complexity, data size, and computational constraints.

Ax Tim Baumg\"artner, Iryna Gurevych 4/23/2026

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

SciCoQA dataset of 635 paper-code discrepancies to evaluate LLM capability for cross-modal verification and research reproducibility auditing.

Ax Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zheyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong 4/23/2026

KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?

KOCO-BENCH benchmark evaluating how LLMs acquire and apply domain knowledge in specialized software development tasks.

Ax Mikael M{\o}ller H{\o}gsgaard, Chirag Pabbaraju 4/23/2026

Agnostic Language Identification and Generation

Theoretical work relaxing realizability assumptions in language identification and generation tasks, establishing statistical rates without distribution constraints.

Ax Jun Han, Shuo Zhang, Wei Li, Zhi Yang, Yifan Dong, Tu Hu, Jialuo Yuan, Xiaomin Yu, Yumo Zhu, Fangqi Lou, Xin Guo, Zhaowei Liu, Tianyi Jiang, Ruichuan An, Jingping Liu, Biao Wu, Rongze Chen, Kunyi Wang, Yifan Wang, Sen Hu, Xinbing Kong, Liwen Zhang, Ronghao Chen, Huacan Wang 4/23/2026

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

QuantaAlpha is an evolutionary LLM-driven agentic framework for financial alpha mining with multi-round search and experience reuse capabilities.

Ax Rong Fu, Yang Li, Zeyu Zhang, Jiekai Wu, Yaohua Liu, Shuaishuai Cao, Yangchen Zeng, Yuhang Zhang, Xiaojing Du, Simon Fong 4/23/2026

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

NeuroSymActive combines neural-symbolic reasoning with knowledge graphs for complex multi-hop question answering, integrating LLMs with structured knowledge.

Ax Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang 4/23/2026

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics

CAST system for stable LLM-based text analysis of tabular data with algorithmic prompting to ensure output consistency for data analytics tasks.

Ax Lei Shu, Dong Zhao, Jianli Chen, Armin Yeganeh, Sinem Mollaoglu, Jiayu Zhou 4/23/2026

Catalyzing Informed Residential Energy Retrofit Decisions via Domain-Specific LLM

Domain-specific LLM application for residential energy retrofit decision-making, guiding homeowners through building energy assessments.

Ax Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu 4/23/2026

veScale-FSDP: Flexible and High-Performance FSDP at Scale

Developer tool for flexible and high-performance fully sharded data parallel training, enabling block-wise quantization and structure-aware methods at scale.

Ax Denis Musinguzi, Caren Han, Prasenjit Mitra 4/23/2026

Location-Aware Pretraining for Medical Difference Visual Question Answering

Medical imaging application of vision-language models with pretraining for differential VQA tasks requiring fine-grained visual comparison.

Ax Tianyang Xu, Marcelo Sandoval-Castaneda, Karen Livescu, Greg Shakhnarovich, Kanishka Misra 4/23/2026

Cross-Modal Taxonomic Generalization in (Vision-) Language Models

Study analyzing semantic representation alignment between language models and vision encoders in vision-language models for taxonomic generalization.

Ax Ruoxi Cheng, Yizhong Ding, Jian Zhao, Hongyi Zhang, Haoxuan Ma, Tianle Zhang, Yiyan Huang, Xuelong Li 4/23/2026

Membership Inference for Contrastive Pre-training Models with Text-only PII Queries

Research on membership inference attacks against contrastive pretraining models like CLIP to audit PII memorization in multimodal backbones.

Ax Ahmet Kaplan 4/23/2026

Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization

AutoML approach combining automated machine learning with deep unfolding for wireless beamforming optimization using learned proximal gradient descent layers.

Ax Maria Conchita Agana Navarro, Geng Li, Theo Wolf, Maria Perez-Ortiz 4/23/2026

Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts

Research evaluates robustness of climate foundation models under distribution shift, testing generalization beyond training data.

Ax Shushanta Pudasaini, Luis Miralles-Pechu\'an, David Lillis, Marisa Llorens Salvador 4/23/2026

Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy

Explainable AI analysis revealing why AI-generated text detectors fail despite high benchmark accuracy, exploiting dataset-specific artifacts.

Ax PengYu Chen, Shang Wan, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das 4/23/2026

VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection

Visual Masked Autoencoder with Normalizing Flow for time series anomaly detection using foundation models for improved generalization.

Ax Tianle Zeng, Yanci Wen, Hong Zhang 4/23/2026

CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence

CARLA-Air: Unified simulation infrastructure for air-ground embodied AI combining drone and vehicle dynamics in single environment.

Ax Yubo Li, Lu Zhang, Tianchong Jiang, Ramayya Krishnan, Rema Padman 4/23/2026

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning

Causal analysis showing LLMs fail reasoning when surface heuristics conflict with implicit constraints, studied through car wash problem.

Ax Yunwen Lei, Yufeng Xie 4/23/2026

Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks

Theoretical analysis of generalization bounds for overparameterized shallow neural networks related to distance from initialization.

Ax Florian Kelber, Matthias Jobst, Yuni Susanti, Michael F\"arber 4/23/2026

Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models

Investigation of whether smaller language models with task-aware retrieval can match larger proprietary models for scientific knowledge discovery applications.

Ax Ali Slim, Haydar Hamieh, Jawad Kotaich, Yehya Ghosn, Mahdi Chehimi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem 4/23/2026

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

QuanBench+: Unified benchmark for evaluating LLMs on quantum code generation across Qiskit, PennyLane, and Cirq frameworks with 42 aligned tasks.

Ax Jinlong Liu, Wanggui He, Peng Zhang, Mushui Liu, Hao Jiang, Pipei Huang 4/23/2026

PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning

PromptEcho: Reward construction method using vision-language models for text-to-image model RL without human annotations or additional training.