Isolater - Feed

Ax Simon Lermen, Daniel Paleka, Joshua Swanson, Michael Aerni, Nicholas Carlini, Florian Tram\`er 2/20/2026

Large-scale online deanonymization with LLMs

LLM agent with internet access performs large-scale deanonymization of Hacker News users and other pseudonymous profiles.

Ax Kejian Shi, Yixin Liu, Peifeng Wang, Alexander R. Fabbri, Shafiq Joty, Arman Cohan 2/20/2026

References Improve LLM Alignment in Non-Verifiable Domains

Using reference-guided LLM evaluators as soft verifiers to improve LLM alignment in non-verifiable domains through RLVR.

Ax Charalampos Mastrokostas, Nikolaos Giarelis, Nikos Karacapilidis 2/20/2026

Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark

DemosQA benchmark evaluating monolingual and multilingual LLMs on Greek question answering tasks.

Ax Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal, Sheel Shah, Jerry Huang, Aditi Raghunathan, Seunghoon Hong, Nicholas M. Boffi, Jinwoo Kim 2/20/2026

One-step Language Modeling via Continuous Denoising

Flow-based continuous denoising language models outperform discrete diffusion in generation speed and quality with fewer steps.

Ax Xinyi Lu, Kexin Phyllis Ju, Mitchell Dudley, Larissa Sano, Xu Wang 2/20/2026

AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course

Randomized trial showing AI-mediated feedback via FeedbackWriter improves student revisions compared to human-only feedback.

Ax Elan Schonfeld, Elias Wisnia 2/20/2026

Learning under noisy supervision is governed by a feedback-truth gap

Two-timescale analysis showing feedback-truth gap arises when noisy feedback is absorbed faster than task structure evaluation.

Ax Zhicheng Zhang, Ziyan Wang, Yali Du, Fei Fang 2/20/2026

VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study

Verbalized Action Masking technique for controlling exploration in RL post-training of LLMs with iterative action-space pruning.

Ax Madeleine Grunde-McLaughlin, Hussein Mozannar, Maya Murad, Jingya Chen, Saleema Amershi, Adam Fourney 2/20/2026

Overseeing Agents Without Constant Oversight: Challenges and Opportunities

User studies on designing informative but non-overwhelming trace interfaces for human oversight of agentic AI systems.

Ax Geunbin Yu 2/20/2026

AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence

AdaptOrch framework for optimizing multi-agent orchestration topology over individual model selection as LLM performance converges.

Ax Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani, Babak Khalaj 2/20/2026

MALLVI: a multi agent framework for integrated generalized robotics manipulation

MALLVi multi-agent framework combines LLMs and vision for closed-loop robotic manipulation. Integrated planning with environmental feedback.

Ax Shlok Mishra, Tsung-Yu Lin, Linda Wang, Hongli Xu, Yimin Liu, Michael Hsu, Chaitanya Ahuja, Hao Yuan, Jianpeng Cheng, Hong-You Chen, Haoyuan Xu, Chao Li, Abhijeet Awasthi, Jihye Moon, Don Husa, Michael Ge, Sumedha Singla, Arkabandhu Chowdhury, Phong Dingh, Satya Narayan Shukla, Yonghuan Yang, David Jacobs, Qi Guo, Jun Xiao, Xiangjun Fan, Aashu Singh 2/20/2026

Xray-Visual Models: Scaling Vision models on Industry Scale Data

Xray-Visual: unified vision model trained on 15B image-text and 10B video-hashtag pairs from Meta. Large-scale multimodal ML.

Ax Zun Li, John Schultz, Daniel Hennes, Marc Lanctot 2/20/2026

Discovering Multiagent Learning Algorithms with Large Language Models

Uses LLMs to automatically discover multi-agent RL algorithms for imperfect-information games. Automates MARL algorithm design.

Ax Farnaz Zamiri Zeraati, Yang Trista Cao, Yuehan Qiao, Hal Daum\'e III, Hernisa Kacorri 2/20/2026

Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Users

Explores user control in conversational VQA systems for blind users. Studies customization and steering in assistive AI.

Ax Jinming Nian, Fangchen Li, Dae Hoon Park, Yi Fang 2/20/2026

RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution

RankEvolve uses LLM-driven evolutionary search to discover improved retrieval algorithms. Automates algorithm discovery for information retrieval.

Ax Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si 2/20/2026

Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

Proposes symbolic alternative to message-passing GNNs for interpretability. Addresses expressivity limits and explainability in graph learning.

Ax Hasan Can Biyik, Libby Barak, Jing Peng, Anna Feldman 2/20/2026

When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English

Cross-lingual study of euphemism detection between Turkish and English. Multilingual NLP research.

Ax Kourosh Shahnazari, Seyed Moein Ayyoubzadeh, Mohammadali Keshtparvar 2/20/2026

Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry

Spectral graph analysis framework for psychological patterns in Persian poetry using ML annotation. NLP application to literary analysis.

Ax Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen 2/20/2026

A Unified Framework for Locality in Scalable MARL

Unified framework for exploiting locality in scalable multi-agent RL. Addresses dimensionality curse in MARL systems.

Ax Yongzhong Xu 2/20/2026

Early-Warning Signals of Grokking via Loss-Landscape Geometry

Studies early-warning signals of grokking in neural networks using loss-landscape geometry. Analyzes generalization phase transitions.

Ax Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde 2/20/2026

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

DDiT proposes dynamic patch scheduling for efficient diffusion transformers. Reduces computational cost via adaptive tokenization.

Ax Diego Firmenich, Leandro Antonelli, Bruno Pazos, Fabricio Lozada, Leonardo Morales 2/20/2026

Exploring LLMs for User Story Extraction from Mockups

Research on using LLMs to extract user stories from UI mockups. Explores automated requirement generation via ML.

Ax Serin Kim, Sangam Lee, Dongha Lee 2/20/2026

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History

Persona2Web benchmark for evaluating personalized web agents using LLMs with user context. First benchmark for personalization in web agents.

Ax Takyoung Kim, Jinseok Nam, Chandrayee Basu, Xing Fan, Chengyuan Ma, Heng Ji, Gokhan Tur, Dilek Hakkani-T\"ur 2/20/2026

ReIn: Conversational Error Recovery with Reasoning Inception

LLM-powered conversational agents with error recovery through dialogue diagnosis and recovery planning, improving robustness beyond error prevention.

Ax Paimon Goulart, Jordan Steinhauser, Dawon Ahn, Kylene Shuler, Edward Korzus, Jia Chen, Evangelos E. Papalexakis 2/20/2026

Transforming Behavioral Neuroscience Discovery with In-Context Learning and AI-Enhanced Tensor Methods

AI-enhanced tensor methods and in-context learning applied to behavioral neuroscience discovery pipelines, automating data preparation and annotation.

Ax Hyeongwon Kang, Jinwoo Park, Seunghun Han, Pilsung Kang 2/20/2026

Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles

Research on applying in-context learning and tensor methods to accelerate behavioral neuroscience discovery pipelines.

Ax Rahul Nanda, Chandra Maddila, Smriti Jha, Euna Mehnaz Khan, Matteo Paltenghi, Satish Chandra 2/20/2026

Wink: Recovering from Misbehaviors in Coding Agents

FATE: ensemble method for proactive anomaly detection in time-series with uncertainty quantification for early warning signals.

Ax Deepak Uniyal, Md Abul Bashar, Richi Nayak 2/20/2026

Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data

Wink: framework for recovering coding agents from misbehaviors including instruction deviation, infinite loops, and tool misuse.

Ax Hussein S. Al-Olimat, Ahmad Alshareef 2/20/2026

ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning

Study evaluating cross-lingual text classification approaches for multilingual social media analysis across nine million tweets.

Ax Tianyuan Cheng, Ruirui Mao, Judea Pearl, Ang Li 2/20/2026

General sample size analysis for probabilities of causation: a delta method approach

Research showing weight initialization signs persist in neural networks and create bottleneck for sub-bit model compression.

Ax Rong Fu, Muge Qi, Chunlei Meng, Shuo Yin, Kun Liu, Zhaolu Kang, Simon Fong 2/20/2026

AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

Statistical research on sample size analysis for probabilities of causation using delta method approach.

Ax Chuiyang Meng, Ming Tang, Vincent W. S. Wong 2/20/2026

FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment

AdvSynGNN: graph neural network architecture for robust node classification handling structural noise and non-homophilous topologies.

Ax Srijan Sood, Kassiani Papasotiriou, Marius Vaiciulis, Tucker Balch 2/20/2026

Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization

FLoRG: federated fine-tuning technique for LLMs using low-rank Gram matrices and Procrustes alignment across distributed clients.

Ax Xihao Piao, Zheng Chen, Lingwei Zhu, Yushun Dong, Yasuko Matsubara, Yasushi Sakurai 2/20/2026

TIFO: Time-Invariant Frequency Operator for Stationarity-Aware Representation Learning in Time Series

Research comparing deep reinforcement learning to mean-variance optimization for portfolio asset allocation and risk management.

Ax Chi-Shiang Gau, Konstantinos D. Polyzos, Athanasios Bacharis, Saketh Madhuvarasu, Tara Javidi 2/20/2026

3D Scene Rendering with Multimodal Gaussian Splatting

TIFO: machine learning method for nonstationary time series forecasting addressing distribution shift using frequency operators.

Ax Linwei Zhai, Han Ding, Mingzhi Lin, Cui Zhao, Fei Wang, Ge Wang, Wang Zhi, Wei Xi 2/20/2026

VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation

Novel vector quantization approach for VAEs that decouples representation learning from discretization to address training instability and codebook collapse.

Ax Tong Guan, Sheng Pan, Johan Barthelemy, Zhao Li, Yujun Cai, Cesare Alippi, Ming Jin, Shirui Pan 2/20/2026

TimeOmni-VL: Unified Models for Time Series Understanding and Generation

Unified multimodal model for time series that bridges numerical generation and semantic understanding tasks using vision-centric approach.

Ax Ayush Goel, Arjun Kohli, Sarvagya Somvanshi 2/20/2026

In-Context Learning in Linear vs. Quadratic Attention Models: An Empirical Study on Regression Tasks

Empirical study comparing how linear and quadratic attention mechanisms perform in-context learning on linear regression tasks, analyzing learning quality, convergence, and generalization.

Ax Heisei Yonezawa, Ansei Yonezawa, Itsuro Kajiwara 2/20/2026

Continual uncertainty learning

Continual uncertainty learning approach for robust control of mechanical systems using deep reinforcement learning.

Ax Shi Yin, Jinming Mu, Xudong Zhu, Lixin He 2/20/2026

Universal Fine-Grained Symmetry Inference and Enforcement for Rigorous Crystal Structure Prediction

Deep learning method for crystal structure prediction using universal fine-grained symmetry inference.

Ax Kishan Maharaj, Nandakishore Menon, Ashita Saxena, Srikanth Tamilselvam 2/20/2026

Robustness and Reasoning Fidelity of Large Language Models in Long-Context Code Question Answering

Systematic evaluation of LLM robustness in long-context code question answering across multiple programming languages.

Ax U\u{g}ur Gen\c{c}, Heng Gu, Chadha Degachi, Evangelos Niforatos, Senthil Chandrasegaran, Himanshu Verma 2/20/2026

The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

Study examining how conversational agents' linguistic personality expressions affect user perceptions and decisions.

Ax Yuduo Guo, Hao Zhang, Mingyu Li, Fujiang Yu, Yunjing Wu, Yuhan Hao, Song Huang, Yongming Liang, Xiaojing Lin, Xinyang Li, Jiamin Wu, Zheng Cai, Qionghai Dai 2/20/2026