Ax Igor Urbanik, Pawe{\l} Gajewski 3/19/2026

SatSOM: Saturation Self-Organizing Maps for Continual Learning

Self-organizing maps extension addressing catastrophic forgetting in continual learning through saturation mechanisms.

Ax Yuanzhe Hu, Yu Wang, Julian McAuley 3/19/2026

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

Benchmark evaluating memory capabilities in LLM agents including memorization, updating, and retrieval of long-term information across multi-turn interactions.

Ax Peng Ding 3/19/2026

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs

Protocol-agnostic tool management library for function-calling LLMs that reduces fragmentation and development overhead in LLM applications.

Ax Jinhyeok Jang, Jaehong Kim, Jung Uk Kim 3/19/2026

Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting

Method for predicting better pre-trained weights via retrodiction of forgetting to encapsulate more knowledge beyond training datasets.

Ax Kazuki Irie, Samuel J. Gershman 3/19/2026

Fast weight programming and linear transformers: from machine learning to neurobiology

Analysis of fast weight programmers and 2D-state RNNs as linear transformers with connections to neurobiology and language modeling advances.

Ax Xiaolu Chen, Haojie Wu, Jie Bao, Zhen Chen, Yong Liao, Hu Huang 3/19/2026

Role-Augmented Intent-Driven Generative Search Engine Optimization

Framework for optimizing content for generative search engines powered by LLMs and RAG by modeling user intent and role-based search patterns.

Ax Woojung Song, Dongmin Choi, Yoonah Park, Jongwook Han, Eun-Ju Lee, Yohan Jo 3/19/2026

Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior

Study showing psychometric questionnaires designed for humans mischaracterize LLM psychology compared to behavior in real user interactions.

Ax Tianyu Chen, Yasi Zhang, Zhi Zhang, Peiyu Yu, Shu Wang, Zhendong Wang, Kevin Lin, Xiaofei Wang, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Jianwen Xie, Oscar Leong, Lijuan Wang, Ying Nian Wu, Mingyuan Zhou 3/19/2026

EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing

Object-centric evaluation framework for automated fine-grained assessment of multi-turn instruction-based image editing using VLMs.

Ax Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu 3/19/2026

Tree Search for LLM Agent Reinforcement Learning

Tree-based group relative policy optimization for LLM agent reinforcement learning addressing sparse supervision in long-horizon multi-turn tasks.

Ax Aayush Mishra, Daniel Khashabi, Anqi Liu 3/19/2026

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning

Method aligning supervised fine-tuning with in-context learning activations to improve LLM generalization and calibration in data-scarce settings.

Ax Qiushui Xu, Yuhao Huang, Yushu Jiang, Lei Song, Jinyu Wang, Wenliang Zheng, Jiang Bian 3/19/2026

In-Context Compositional Q-Learning for Offline Reinforcement Learning

Offline RL framework using linear Transformers for compositional Q-function estimation across diverse subtasks via in-context learning.

Ax Arpit Garg, Hemanth Saratchandran, Ravi Garg, Simon Lucey 3/19/2026

Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models

Parameter-efficient machine unlearning method for foundation models addressing weight unbounding in privacy removal.

Ax Langqi Yang, Tianhang Zheng, Yixuan Chen, Kedong Xiu, Hao Zhou, Wangze Ni, Lei Chen, Zhan Qin, Kui Ren 3/19/2026

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment

Benchmark evaluating metrics and judges for assessing harmful content generation in LLMs.

Ax Ziyan Wang, Zheng Wang, Xingwei Qu, Qi Cheng, Jie Fu, Shengpu Tang, Minjia Zhang, Xiaoming Huo 3/19/2026

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Slow-Fast Policy Optimization framework improving LLM reasoning via RL with better gradient stability and exploration.

Ax Yongding Tao, Tian Wang, Yihong Dong, Huanyu Liu, Kechi Zhang, Xiaolong Hu, Ge Li 3/19/2026

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

Methods for detecting data contamination in LLM evaluation during reinforcement learning post-training phases.

Ax Xuwang Yin, Claire Zhang, Julie Steele, Nir Shavit, Tony T. Wang 3/19/2026

Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation

Scalable energy-based models via adversarial training unifying classification and generative modeling using EBM framework.

Ax Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames 3/19/2026

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

CBF-RL integrates control barrier functions into reinforcement learning training for enforcing safety constraints during policy training.

Ax L\'ivia Dutra, Arthur Lorenzi, La\'is Berno, Franciany Campos, Karoline Biscardi, Kenneth Brown, Marcelo Viridiano, Frederico Belcavello, Ely Matos, Ol\'ivia Guaranha, Erik Santos, Sofia Reinach, Tiago Timponi Torrent 3/19/2026

Frame Semantic Patterns for Identifying Underreporting of Notifiable Events in Healthcare: The Case of Gender-Based Violence

Frame semantic patterns methodology for identifying underreported gender-based violence in e-medical records using NLP.

Ax Andy Dimnaku, Abdullah Yusuf Kavranoglu, Yaser Abu-Mostafa 3/19/2026

Generative Hints

Generative hints training methodology enforcing functional invariances in vision models beyond empirical training data.

Ax Awwab A. Azam, Lexu Zhao, Jiabin Yu 3/19/2026

Reduced Density Matrices Through Machine Learning

Neural network approach to accelerate computation of n-particle reduced density matrices for strongly-correlated quantum states.

Ax Jorge Paz-Ruza, Jo\~ao Gama, Amparo Alonso-Betanzos, Bertha Guijarro-Berdi\~nas 3/19/2026

A robust methodology for long-term sustainability evaluation of Machine Learning models

Methodology for sustainable ML model evaluation addressing gaps in Green AI auditing practices and standardization.

Ax Nathan Breslow, Aayush Mishra, Mahler Revsine, Michael C. Schatz, Anqi Liu, Daniel Khashabi 3/19/2026

Genomic Next-Token Predictors are In-Context Learners

Research showing genomic sequence models exhibit in-context learning similar to LLMs, demonstrating ICL emerges across sequence domains.

Ax Yara Bahram, Melodie Desbos, Mohammadhadi Shateri, Eric Granger 3/19/2026

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

Uni-DAD: Unified method for distilling and adapting diffusion models for few-step image generation in new domains.

Ax Di Feng, Kaixin Ma, Feng Nan, Haofeng Chen, Bohan Zhai, David Griffiths, Mingfei Gao, Zhe Gan, Eshan Verma, Yinfei Yang, Zhifeng Chen, Afshin Dehghan 3/19/2026

SO-Bench: A Structural Output Evaluation of Multimodal LLMs

Benchmark for evaluating multimodal LLMs on schema-grounded visual information extraction and reasoning tasks in agentic settings.

Ax Saad Alqithami 3/19/2026

Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scale

Framework for runtime monitoring of multi-agent systems using cryptographic provenance and drift detection to mitigate emergent norms at scale.

Ax Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron Courville 3/19/2026

A Comedy of Estimators: On KL Regularization in RL Training of LLMs

Analysis of KL divergence estimators used in RL training of LLMs, evaluating different approximation methods for reverse KL regularization.

Ax Zhehao Huang, Baijiong Lin, Jingyuan Zhang, Jingying Wang, Yuhang Liu, Ning Lu, Tao Li, Xiaolin Huang 3/19/2026

VL-RouterBench: A Benchmark for Vision-Language Model Routing

Benchmark for evaluating vision-language model routing systems across quality and cost dimensions using real inference logs.

Ax Yuxuan Li, Harshith Reddy Kethireddy, Srijita Das 3/19/2026

Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning

Study on feature-dependent noise in preference-based reinforcement learning, examining how observation-dependent uncertainty affects learning.

Ax Mingyang Wei, Dehai Min, Zewen Liu, Yuzhang Xie, Guanchen Wu, Ziyang Zhang, Carl Yang, Max S. Y. Lau, Qi He, Lu Cheng, Wei Jin 3/19/2026

EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning

Diagnostic benchmark for evaluating epidemiological reasoning in large language models, focusing on evidence-grounded inference over clinical knowledge.

Ax Abhi Kottamasu, Chirag Mahapatra, Sam Lee, Ben Pan, Aakash Barthwal, Akul Datta, Ajay Arun, Silas Alberti, Adarsh Hiremath, Brendan Foody, Bertie Vidgen 3/19/2026

APEX-SWE

Benchmark for evaluating frontier AI models on real-world software engineering tasks including integration and end-to-end system construction.

Ax Zhengyang Zhao, Lu Ma, Yizhen Jiang, Xiaochen Ma, Zimo Meng, Chengyu Shen, Lexiang Tang, Haoze Sun, Peng Pei, Wentao Zhang 3/19/2026

GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization

Reformulation of supervised fine-tuning to reconcile post-training objectives in large reasoning models using Gibbs initialization before reinforcement learning.

Ax Xiaoxuan Liu, Jiaxiang Yu, Jongseok Park, Ion Stoica, Alvin Cheung 3/19/2026

Speculative Decoding: Performance or Illusion?

Systematic evaluation of speculative decoding acceleration techniques on production-grade vLLM inference engine, assessing real-world effectiveness.

Ax Ahmed Attia, Alham Fikri Aji 3/19/2026

Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning

Self-supervised reinforcement learning approach for improving low-resource machine translation using round-trip bootstrapping with NLLB models.

Ax Sudip Chakrabarty 3/19/2026

YOLO26: An Analysis of NMS-Free End to End Framework for Real-Time Object Detection

Analysis of YOLO26 object detection framework that eliminates NMS post-processing for native end-to-end learning strategy.

Ax Donghee Lee, Rui Cai, Zhe Zhao 3/19/2026

CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models

Method to improve vision-centric capabilities of multimodal LLMs through context-aware image representation prioritization via ensemble approach.

Ax Hongbo Bo, Jingyu Hu, Debbie Watson, Weiru Liu 3/19/2026

Failing on Bias Mitigation: A Case Study on the Challenges of Fairness in Government Data

Case study examining why bias mitigation techniques fail on government data, using crime rate prediction with Bristol City Council data as test case.

Ax Archer Wang, Emile Anand, Yilun Du, Marin Solja\v{c}i\'c 3/19/2026

Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models

Unsupervised method for decomposing complex data into factorized components using diffusion models, enabling reusable component recombination for images and robotic videos.

Ax Qiuming Luo, Yuebing Li, Feng Li, Chang Kong 3/19/2026

PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification

Knowledge distillation framework from vision-language models into lightweight networks for fine-grained visual classification using prompt-aware semantic calibration.

Ax Wei Chen, Xingyu Guo, Shuang Li, Zhao Zhang, Yan Zhong, Fuzhen Zhuang, Deqing wang 3/19/2026

Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation

Graph domain adaptation method using neural characteristic functions to align distributional shifts across labeled source and unlabeled target graphs.

Ax Vishak K Bhat, Prateek Chanda, Vijval Ekbote, Ashmit Khandelwal, Maitreyi Swaroop, Vineeth N. Balasubramanian, Subbarao Kambhampati, Nagarajan Natarajan, Amit Sharma 3/19/2026

interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors

Framework for test-time verification of LLM reasoning traces using single-trajectory monitoring to catch errors without exploring multiple branches.

Ax Zunkai Dai, Ke Li, Jiajia Liu, Jie Yang, Yuanyuan Qiao 3/19/2026

No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection

Zero-shot video anomaly detection framework using multimodal large language models without requiring real anomaly examples, addressing dataset diversity limitations.

Ax Harry Amad, Mihaela van der Schaar 3/19/2026

Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport

Method for inferring hyperparameter trajectories using optimal transport to adapt neural network behavior post-deployment without expensive retraining.

Ax Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu 3/19/2026

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Research on continual learning in pretrained Vision-Language-Action models for robot policy learning, showing resistance to catastrophic forgetting when acquiring new skills.

Ax Jialong Chen, Xander Xu, Hu Wei, Chuan Chen, Bing Zhao 3/19/2026

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

Benchmark evaluating LLM agent capabilities in long-term codebase maintenance via continuous integration, beyond static bug fixing.

Ax Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang 3/19/2026

Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection

Technique to reduce KV cache in transformers by using low-dimensional attention selection for keys while maintaining full-dimensional values.

Ax Tao Zhang, Rui Ma, Shuotao Xu, Yongqiang Xiong, Peng Cheng 3/19/2026

LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis

LLM-guided GPU architecture exploration for LLM inference workloads via bottleneck analysis and design space optimization.

Ax Reva Schwartz, Gabriella Waters 3/19/2026

Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma

FRAME methodology for systematic evaluation of AI systems in real-world organizational contexts beyond abstract capability measures.

Ax Shaily Roy, Harshit Sharma, Daniel A. Adler, Tanzeem Choudhury, Asif Salekin 3/19/2026

Ethical Fairness without Demographics in Human-Centered AI

Method for achieving ethical fairness in AI systems without relying on demographic attributes in human-centered applications.

Ax Carlos Rafael Catalan, Lheane Marie Dizon, Patricia Nicole Monderin, Emily Kuang 3/19/2026

"I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants

Study on software engineers' cognitive engagement with agentic coding assistants, examining over-reliance risks and critical thinking impacts.

Ax Madhulatha Mandarapu, Sandeep Kunkunuru 3/19/2026

Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database

Open-source biomedical knowledge graphs (pathways, clinical trials, drug interactions) with federated access and AI agent integration.