Isolater - Feed

Ax Donghao Li, Chengshuai Shi, Weijuan Ou, Cong Shen, Jing Yang 5/15/2026

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits

Framework for multi-objective prompt optimization using pure-exploration bandits to select effective LLM prompts across multiple performance metrics.

Ax Langzhou He, Junyou Zhu, Yue Zhou, Zhengyao Gu, Junhua Liu, Wei-Chieh Huang, Henry Peng Zou, David Wipf, Philip S. Yu, Qitian Wu 5/15/2026

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy

Method for improving agentic reinforcement learning by optimizing token-level credit assignment in LLM trajectories using energy-based approaches.

Ax Ho Hung Lim, Yi Yang 5/15/2026

A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval

Empirical study on aggregation strategies for visual document retrieval in RAG systems, evaluating information loss in financial document processing.

Ax Oubo Ma, Ruixiao Lin, Yang Dai, Jiahao Chen, Chunyi Zhou, Linkang Du, Shouling Ji 5/15/2026

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

Research on backdoor attack vulnerabilities in deep reinforcement learning agents with plasticity interventions, examining security threats in DRL systems.

Ax Andreas Schlaginhaufen, Maryam Kamgarpour 5/15/2026

Fast Rates for Inverse Reinforcement Learning

Theoretical analysis establishing fast convergence rates for entropy-regularized inverse reinforcement learning with linear reward classes.

Ax Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky 5/15/2026

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries

Analysis showing defenses against malicious fine-tuning of foundation models fail under adaptive adversaries that account for defense mechanisms.

Ax Yaroslav Sokolov, Yury Khudyakov, Lenar Sharipov, Andrei Gasparian, Parth Tiwary, Artem Trofimov 5/15/2026

In-IDE Toolkit for Developers of AI-Based Features

JetBrains IDE plugin toolkit for developers building AI features with LLMs and agentic workflows, enabling tracing, debugging, and evaluation in development loop.

Ax Tian Qin, Junzhe Chen, Yuqing Shi, Tianshu Zhang, Qiang Ju, Lijie Wen 5/15/2026

Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution

SIRA: Training-free method to reduce hallucinations in vision-language models through internal contrastive decoding without external tools.

Ax Sohaib Afifi 5/15/2026

An Amortized Efficiency Threshold for Comparing Neural and Heuristic Solvers in Combinatorial Optimization

Energy efficiency analysis comparing neural combinatorial optimization solvers to CPU metaheuristics, accounting for amortized training costs.

Ax Tianwei Chen, Takuya Furusawa, Yuki Hirakawa, Ryotaro Shimizu, Mo Fan, Takashi Wada 5/15/2026

MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models

Multi-label visual emotion analysis benchmark for evaluating multimodal large language models on image emotion prediction tasks.

Ax Matteo Cobelli, Stefano Sanvito 5/15/2026

Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applications

AI agent framework (Automat) for automated design of material descriptors through iterative proposal, implementation, and evaluation for materials science.

Ax Vicent Briva-Iglesias, Mar\'ia Ferre-Fern\'andez 5/15/2026

AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents

Comparing neural machine translation and glossary-augmented LLM approaches for translating specialized rock art terminology in cultural heritage documents.

Ax Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech, Angeliki-Ilektra Karaiskou, Guido Gagliardi, Thomas Strypsteen, Mohammad Hossein Badiei, Anku Rani, Maarten Vanmarcke, Miguel Bhagubai, Chanakya Ekbote, Jaedong Hwang, Christos Chatzichristos, Paul Pu Liang, Maarten De Vos 5/15/2026

NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

Benchmarking foundation models on EEG and brain-computer interface tasks with standardized datasets and metrics for clinical relevance evaluation.

Ax Posheng Chen, Powen Cheng, Gueter Josmy Faure, Hung-Ting Su, Winston H. Hsu 5/15/2026

SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization

arXiv paper on SceneFunRI: vision-language model benchmark for reasoning about occluded objects using spatial reasoning and context inference.

Ax Shijie Lian, Bin Yu, Xiaopeng Lin, Zhaolong Shen, Laurence Tianruo Yang, Yurun Jin, Haishan Liu, Changti Wu, Hang Yuan, Cong Huang, Kai Chen 5/15/2026

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

arXiv paper on IntentVLA: vision-language model for robot manipulation handling multimodal demonstrations and intent disambiguation.

Ax Krish Sharma, Omar Naim, Soumadeep Saha, Nicholas Asher 5/15/2026

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

arXiv paper investigating task-aware layer pruning for LLMs; shows pruning improves out-of-distribution performance while maintaining in-distribution accuracy.

Ax Jos\'e Manuel de la Chica Rodr\'iguez, Carlos Mart\'i-Gonz\'alez 5/15/2026

Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems

arXiv paper on governance failures in LLM-based financial systems; proposes metrics for auditable decision-making compliance beyond task accuracy.

Ax Weimin Xiong, Shuhao Gu, Bowen Ye, Zihao Yue, Lei Li, Feifan Song, Sujian Li, Hao Tian 5/15/2026

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

arXiv paper on Video2GUI: automated framework synthesizing large-scale GUI interaction data for pretraining generalized GUI agents using video.

Ax Sangwoo Kim 5/15/2026

Non-linear Interventions on Large Language Models

arXiv paper extending intervention methods for LLMs beyond linear approaches to capture non-linear feature representations in model internals.

Ax Yi Wang, Hongye Qiu, Yue Xu, Sibei Yang, Zhan Qin, Minlie Huang, Wenjie Wang 5/15/2026

EVA: Editing for Versatile Alignment against Jailbreaks

arXiv paper on EVA: defense against LLM jailbreaks through editing techniques to improve model safety alignment without computational overhead.

Ax Qirui Liu, Hao Chen, Weijie Shi, Jiajie Xu, Jia Zhu 5/15/2026

Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions

Knowledge distillation approach for identifying student misconceptions in educational settings with noisy labels.

Ax Hongyu Lin, Antonio Briola, Yuanrong Wang, Tomaso Aste 5/15/2026

Compositional Sparsity as an Inductive Bias for Neural Architecture Design

Theoretical analysis of compositional sparsity as inductive bias enabling deep networks to overcome curse of dimensionality.

Ax Titouan Parcollet, Shucong Zhang, Xianrui Zheng, Rogier C. van Dalen 5/15/2026

Streaming Speech-to-Text Translation with a SpeechLLM

SpeechLLM system for streaming speech-to-text translation in real-time without waiting for complete utterances.

Ax Suorong Yang, Hanqi Zhu, Hai Gan, Fangjian Su, Guang Li, Furao Shen, Soujanya Poria 5/15/2026

Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training

Data selection scheduling method that dynamically adjusts training data volume throughout model training.

Ax William Lugoloobi, Samuelle Marro, Jabez Magomere, Joss Wright, Chris Russell 5/15/2026

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

Security analysis showing LLM browser agents can be fingerprinted through UI interaction traces and timing patterns.

Ax Songyang Gao, Yinghui Xia, Siyi Liu, Hui Xiong 5/15/2026

Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation

LLM-based research idea generation using citation evolution graphs as structural supervision signal.

Ax Licong Xu, Thomas Borrett 5/15/2026

Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology

Autonomous AI agents for scientific discovery in cosmology using LLM-guided code evolution and multi-agent research labs.

Ax Paolo Mandica, Micha{\l} Brzozowski, Zuzanna Dubanowska, Neo Christopher Chung 5/15/2026

GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning

Parameter-efficient fine-tuning method improving upon LoRA through isometric global parameter partitioning.

Ax Thomas Witt 5/15/2026

XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference

Dynamic weight quantization method for efficient LLM inference with adaptive codebook sizing and quality targets.

Ax Zhigao Huang, Zhengqing Hu, Dong Chen, Shaohan Zhang, Zhao Jin, Bo Zhang, Han Wu, Mingliang Xu 5/15/2026

IFPV: An Integrated Multi-Agent Framework for Generative Operational Planning and High-Fidelity Plan Verification

Multi-agent framework integrating operational plan generation and verification for complex battlefield planning.

Ax Zheng Yan, Jingxiang Weng, Charles Chen, Dengyun Peng, Ethan Qin, Jiannan Guan, Jinhao Liu, Qiming Yu, Yixin Yuan, Fanqing Meng, Carl Che, Mengkang Hu 5/15/2026

Do Coding Agents Understand Least-Privilege Authorization?

Evaluation of whether coding agents understand least-privilege authorization principles for safe deployment.

Ax Lingzhe Zhang, Tong Jia, Kangjin Wang, Chiming Duan, Minghua He, Rongqian Wang, Xi Peng, Meiling Wang, Gong Zhang, Renhai Chen, Ying Li 5/15/2026

Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought

Multi-agent AI system with recursion-of-thought for root cause localization in microservice systems.

Ax Hanbo Cheng, Limin Lin, Ruo Zhang, Yicheng Pan, Jun Du 5/15/2026

Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning

Multi-step reasoning approach for text-to-image generation with closed-loop verification to handle complex semantics.

Ax Jakub Grzywaczewski, Dawid P{\l}udowski, Przemys{\l}aw Biecek 5/15/2026

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers

Analysis of noise in CLIP vision-language model embeddings using spectral decomposition of covariance matrices.

Ax Senne Deproost, Denis Steckelmacher, Ann Now\'e 5/15/2026

Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models

Distillation method for converting deep RL policies to interpretable surrogate models using Voronoi quantization.

Ax Wei Ding, Yilin Li, Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Yu Wang 5/15/2026

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs

MHSA: lightweight framework for mitigating hallucinations in vision-language models via steered attention mechanisms.

Ax Haoze Wu, Rocky Klopfenstein, Keith Farkas, Nina Narodytska 5/15/2026

Viverra: Text-to-Code with Guarantees

Viverra: text-to-code system generating verifiable, correct code with guarantees, reducing developer review burden.

Ax Xiaofei Hui, Haoxuan Qu, Hossein Rahmani, Shuohong Wang, Jeff W. Lichtman, Jun Liu 5/15/2026

MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions

MicroscopyMatching: framework for automated microscopy image analysis across diverse biological and imaging conditions.

Ax Sanjeev Manivannan, Shuban V 5/15/2026

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition

Second-order actor-critic methods for discounted MDPs using policy Hessian decomposition for accelerated convergence.

Ax Rebecca Handler, Suhana Bedi, Nigam Shah 5/15/2026

Quantifying and Mitigating Premature Closure in Frontier LLMs

Study quantifying premature closure in frontier LLMs—inappropriate commitment under uncertainty—with mitigation strategies.

Ax Kai Yan, Alexander G. Schwing, Yu-Xiong Wang 5/15/2026

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance

Method for improving sample efficiency in RLVR by using randomly selected few-shot guidance for LLM chain-of-thought tasks.

Ax Zihan Deng, Xiaozhen Zhong, Chuanzhi Xu 5/15/2026

COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

COTCAgent: LLM-based clinical decision support using probabilistic chain-of-thought reasoning on longitudinal EHR data.

Ax Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang 5/15/2026

Generalized Priority-Aware Shapley Value

Generalized Priority-Aware Shapley Value: extension of Shapley value for valuation on arbitrary weighted priority graphs.

Ax Georgios Liargkovas, Mihir Nitin Joshi, Hubertus Franke, Kostis Kaffes 5/15/2026

SemaTune: Semantic-Aware Online OS Tuning with Large Language Models

SemaTune: LLM-based system for online OS tuning that models cross-knob policy structure for long-running service optimization.

Ax Tri Cao, Yulin Chen, Hieu Cao, Yibo Li, Khoi Le, Thong Nguyen, Yuexin Li, Yufei He, Yue Liu, Shuicheng Yan, Bryan Hooi 5/15/2026

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

WARD: defense framework against prompt injection attacks on web agents, improving robustness across unseen domains and attack patterns.

Ax Vinicius Covas, Jorge Alberto Hidalgo Toledo 5/15/2026

AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models

Study of linguistic adaptation in multi-agent LLM systems under social observation, examining LLM behavior as communicative actors.

Ax KiHyun Nam, Jungwoo Heo, Siu Bae, Ha-Jin Yu, Joon Son Chung 5/15/2026