Isolater - Feed

Ax Alibek T. Kaliyev, Artem Maryanskyy 4/2/2026

EvolveTool-Bench: Evaluating the Quality of LLM-Generated Tool Libraries as Software Artifacts

EvolveTool-Bench: diagnostic benchmark for evaluating quality of LLM-generated tool libraries as software artifacts in engineering workflows.

Ax Weyl Lu, Chenjie Hao, Yubei Chen 4/2/2026

Deep Networks Favor Simple Data

Research on out-of-distribution anomaly where deep models assign higher density to simple OOD data than in-distribution test data.

Ax Yuchen Yang, Shuangyang Zhong, Haijun Yu, Langcuomu Suo, Hongbin Han, Florian Putz, Yixing Huang 4/2/2026

Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions

Domain adaptation framework for brain metastases segmentation across multiple medical institutions with different imaging protocols.

Ax Seohyoung Park, Jaeyeol Lim, Seoyoung Ju, Kyeonghun Kim, Nam-Joon Kim, Hyuk-Jae Lee 4/2/2026

COTTA: Context-Aware Transfer Adaptation for Trajectory Prediction in Autonomous Driving

Transfer learning approach for trajectory prediction in autonomous driving handling domain shift across different regional driving patterns.

Ax Weizhuo Wang, Yanjie Ze, C. Karen Liu, Monroe Kennedy III 4/2/2026

Learning Humanoid Navigation from Human Data

System enabling humanoid robot navigation in unseen environments using diffusion models trained on 5 hours of human walking video without robot data.

Ax Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou 4/2/2026

G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs

Privacy attack method using gradient-induced feature drift to infer membership in LLM training data without relying on output probabilities.

Ax Iyad Ait Hou, Rebecca Hwa 4/2/2026

Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics

Analysis of neuron polysemy in neural networks, decomposing superposition metrics to separate lexical overlap from concept compression.

Ax Jiwoo Ha, Jongwoo Baek, Jinhyun So 4/2/2026

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models

Method to mitigate object hallucination in Vision-Language Models through visual grounding using logit boosting without retraining.

Ax Veda Duddu, Jash Rajesh Parekh, Andy Mao, Hanyi Min, Ziang Xiao, Vedant Das Swain, Koustuv Saha 4/2/2026

Not My Truce: Personality Differences in AI-Mediated Workplace Negotiation

Study examining how personality traits moderate effectiveness of AI-driven conversational coaching in workplace negotiation scenarios.

Ax Zhensu Sun, Zhihao Lin, Zhi Chen, Chengran Yang, Mingyi Zhou, Li Li, David Lo 4/2/2026

Executing as You Generate: Hiding Execution Latency in LLM Code Generation

Technique to reduce LLM code generation latency by executing code incrementally as tokens are generated, eliminating idle waiting periods.

Ax Yabin Zhang, Chong Wang, Yunhe Gao, Jiaming Liu, Maya Varma, Justin Xu, Sophie Ostmeier, Jin Long, Sergios Gatidis, Seena Dehkharghani, Arne Michalson, Eun Kyoung Hong, Christian Bluethgen, Haiwei Henry Guo, Alexander Victor Ortiz, Stephan Altmayer, Sandhya Bodapati, Joseph David Janizek, Ken Chang, Jean-Benoit Delbrouck, Akshay S. Chaudhari, Curtis P. Langlotz 4/2/2026

A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation

Vision-Language foundation model for chest X-ray interpretation providing explicit reasoning about visual evidence and diagnostic predictions.

Ax Yunwen Lei, Yufeng Xie 4/2/2026

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

Theoretical analysis of generalization bounds for overparameterized neural networks using distance from initialization as an explanatory factor.

Ax Junxian Wu, Chenghan Fu, Zhanheng Nie, Daoze Zhang, Bowen Wan, Wanxian Guan, Chuan Yu, Jian Xu, Bo Zheng 4/2/2026

MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding

Multimodal LLM approach for e-commerce product understanding that captures fine-grained attributes through reasoning-aware representation learning.

Ax Kyeonghun Kim, Hyeonseok Jung, Youngung Han, Junsu Lim, YeonJu Jean, Seongbin Park, Eunseob Choi, Hyunsu Go, SeoYoung Ju, Seohyoung Park, Gyeongmin Kim, MinJu Kwon, KyungSeok Yuh, Soo Yong Kim, Ken Ying-Kai Liao, Nam-Joon Kim, Hyuk-Jae Lee 4/2/2026

MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning

Self-supervised learning framework using masked autoencoders for 3D medical imaging, addressing domain shift from natural image pretraining.

Ax Axiu Mao, Meilu Zhu, Lei Shen, Xiaoshuai Wang, Tomas Norton, Kai Liu 4/2/2026

Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition

Deep learning approach for animal activity recognition from wearable sensors, optimizing sampling rates and addressing class-specific classification accuracy.

Ax Haibo Wang, Zihao Lin, Zhiyang Xu, Lifu Huang 4/2/2026

Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding

Agentic framework combining Vision-Language Models with iterative reasoning for zero-shot 3D visual grounding from natural language descriptions.

Ax Zhiting Fan, Ruizhe Chen, Tianxiang Hu, Ru Peng, Zenan Huang, Haokai Xu, Yixin Chen, Jian Wu, Junbo Zhao, Zuozhu Liu 4/2/2026

Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation

Method for optimizing rubrics used in synthetic data generation for LLM fine-tuning, leveraging influence-guided selection in knowledge-intensive domains.

Ax Kyeonghun Kim, Jaehyung Park, Youngung Han, Anna Jung, Seongbin Park, Sumin Lee, Jiwon Yang, Jiyoon Han, Subeen Lee, Junsu Lim, Hyunsu Go, Eunseob Choi, Hyeonseok Jung, Soo Yong Kim, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Hyuk-Jae Lee, Ken Ying-Kai Liao, Nam-Joon Kim 4/2/2026

MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy

Mamba-based neural network for dental diagnosis from X-rays, unifying tooth detection, caries segmentation, anomaly detection, and developmental staging.

Ax Hongyang Yang, Yanxin Zhang, Yang She, Yue Xiao, Hao Wu, Yiyang Zhang, Jiapeng Hou, Rongshan Zhang 4/2/2026

HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation

Multi-agent LLM system for housing consultation decisions, combining reasoning, constraint handling, and factuality guarantees beyond simple ranking.

Ax Mingming Ha, Guanchen Wang, Linxun Chen, Xuan Rao, Yuexin Shi, Tianbao Ma, Zhaojie Liu, Yunqian Fan, Zilong Lu, Yanan Niu, Han Li, Kun Gai 4/2/2026

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

Unified neural architecture framework studying scaling laws across attention-based, TokenMixer, and factorization-machine recommendation systems.

Ax Pawe{\l} Liskowski, Kyle Schmaus 4/2/2026

Streaming Model Cascades for Semantic SQL

Method using model cascades to optimize LLM inference costs in semantic SQL queries by routing rows through fast/expensive models based on confidence.

Ax Lewis Tham, Nicholas Mac Gregor Garcia, Jungpil Hahn 4/2/2026

Internal APIs Are All You Need: Shadow APIs, Shared Discovery, and the Case Against Browser-First Agent Architectures

Research on autonomous web agents navigating browser-based websites by leveraging internal APIs instead of DOM inspection, addressing architectural mismatches in agent design.

Ax Yu Xia, Canwen Xu, Zhewei Yao, Julian McAuley, Yuxiong He 4/2/2026

Learning to Hint for Reinforcement Learning

Reinforcement learning technique adding hints to overcome advantage collapse in group relative policy optimization.

Ax Ruozhao Yang, Mingfei Cheng, Gelei Deng, Junjie Wang, Tianwei Zhang, Xiaofei Xie 4/2/2026

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

Black-box security tool for detecting exploitable third-party vulnerabilities in web applications.

Ax Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao, Sachin Kumar, Emmy Liu, Steven Y. Feng 4/2/2026

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining

Study of tradeoffs between parametric knowledge in LLM pretraining and non-parametric knowledge from retrieval.

Ax Sihan Zhou, Tiantian He, Yifan Lu, Yaqing Hou, Yew-Soon Ong 4/2/2026

GRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization

Multi-agent optimization framework addressing non-stationarity through active shared perception of agent policies.

Ax Ricardo Hidalgo-Arag\'on, Jes\'us M. Gonz\'alez-Barahona, Gregorio Robles 4/2/2026

A CEFR-Inspired Classification Framework with Fuzzy C-Means To Automate Assessment of Programming Skills in Scratch

Educational framework for assessing Scratch programming skills using fuzzy clustering aligned with CEFR levels.

Ax Bj\"orn Roman Kohlberger (EctoSpace, Dublin, Ireland) 4/2/2026

Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction

Memory-efficient LLM training via truncated SVD factorization of weight matrices on consumer hardware.

Ax Sayed Hashim, Frank Soboczenski, Paul Cairns 4/2/2026

BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction

Transformer-based framework for predicting immunotherapy response using biomarkers in small medical datasets.

Ax Dong-Jae Lee, Sunghyun Baek, Junmo Kim 4/2/2026

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

Token pruning framework for vision-language models using attention dual form perspective without retraining.

Ax Swapnil Parekh 4/2/2026

Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning

Security analysis of backdoor attacks on language models using continuous latent reasoning without token output.

Ax Dharma Teja Vooturi, Dhiraj Kalamkar, Dipankar Das, Bharat Kaul 4/2/2026

Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer

LLM pretraining at exascale using Aurora supercomputer with Mula-1B model and Optimus training library.

Ax Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Hanbing Li, Long Chen, Zhi-Xin Yang, Jiwen Lu 4/2/2026

DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale

End-to-end autonomous driving model using 3D geometry instead of language descriptions for planning.

Ax Hemanth Kotaprolu, Kishan Maharaj, Raey Zhao, Abhijit Mishra, Pushpak Bhattacharyya 4/2/2026

Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding

Bayesian inference framework for multi-dimensional emotion understanding accounting for dependencies among emotions.

Ax Zhanzhi Lou, Hui Chen, Yibo Li, Qian Wang, Bryan Hooi 4/2/2026

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

Language agents with learnable adaptation policies that optimize test-time learning instead of using fixed hand-crafted policies.

Ax Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain, K. M. Azharul Hasan 4/2/2026

KUET at StanceNakba Shared Task: StanceMoE: Mixture-of-Experts Architecture for Stance Detection

Mixture-of-Experts architecture for actor-level stance detection in geopolitical text classification.

Ax Nan Wang, Zhiwei Jin, Chen Chen, Haonan Lu 4/2/2026

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

PixelPrune: adaptive visual token reduction for vision-language models using predictive coding for document and GUI tasks.

Ax Razvan Mihai Popescu, David Gros, Andrei Botocan, Rahul Pandita, Prem Devanbu, Maliheh Izadi 4/2/2026

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Dataset and analysis of autonomous coding agents' contributions in real-world projects, examining code quality and team dynamics over time.

Ax Dylan B. Lewis, Jens Gregor, Hector Santos-Villalobos 4/2/2026

Representation Selection via Cross-Model Agreement using Canonical Correlation Analysis

Training-free canonical correlation analysis method for improving efficiency of pretrained image encoder representations.

Ax Arina Kharlamova, Bowei He, Chen Ma, Xue Liu 4/2/2026

Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting

DANCEMATCH framework for motion-based dance retrieval using quantized structure-preserving representations.

Ax Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen, Yan-Ru Chen, Yi-Ling Chang, Fang Yu 4/2/2026

WARP: Guaranteed Inner-Layer Repair of NLP Transformers

WARP: method for repairing adversarial vulnerabilities in transformer NLP models with provable inner-layer repair guarantees.

Ax Ruijie Hao, Longfei Zhang, Yang Dai, Yang Ma, Xingxing Liang, Guangquan Cheng 4/2/2026

Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization

Reinforcement learning with flow-based policies and distributional RL for trajectory optimization in multi-solution problems.

Ax Xiangqi Wang, Yue Huang, Haomin Zhuang, Kehan Guo, Xiangliang Zhang 4/2/2026

Dual Optimal: Make Your LLM Peer-like with Dignity

Dignified Peer framework addressing evasive and sycophantic behavior in aligned LLMs through anti-sycophancy and empathy.

Ax Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang, Yiduo Guo, Ziniu Li, Chenxin Li, Jingyuan Hu, Shunian Chen, Tongxu Luo, Jiaxi Bi, Zeyu Qin, Shaobo Wang, Xin Lai, Pengyuan Lyu, Junyi Li, Can Xu, Chengquan Zhang, Han Hu, Ming Yan, Benyou Wang 4/2/2026