Isolater - Feed

Ax Jonathan Wenger, Beau Coker, Juraj Marusic, John P. Cunningham 3/17/2026

Variational Deep Learning via Implicit Regularization

Analysis of implicit regularization in overparametrized deep neural networks and improved out-of-distribution generalization via variational methods.

Ax Yajie Zhou, Jiajun Ruan, Eric S. Wang, Sadjad Fouladi, Francis Y. Yan, Kevin Hsieh, Zaoxing Liu 3/17/2026

NetArena: Dynamic Benchmarks for AI Agents in Network Automation

Dynamic benchmark framework (NetArena) for evaluating AI agents in network automation with production-level complexity and reduced contamination risk.

Ax Geonwoo Cho, Jaemoon Lee, Jaegyun Im, Subi Lee, Jihwan Lee, Sundong Kim 3/17/2026

AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification

Adaptive multi-objective reinforcement learning method for balancing exploration and skill diversity in skill-based RL pretraining.

Ax Jingyu Xiao, Ming Wang, Man Ho Lam, Yuxuan Wan, Junliang Liu, Yintong Huo, Michael R. Lyu 3/17/2026

DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation

Benchmark for evaluating multimodal LLM-based front-end code generation with modern development frameworks and evaluation metrics.

Ax Shubham Parashar, Shurui Gui, Xiner Li, Hongyi Ling, Sushil Vemuri, Blake Olson, Eric Li, Yu Zhang, James Caverlee, Dileep Kalathil, Shuiwang Ji 3/17/2026

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning

Curriculum learning approach scheduling tasks from easy to hard to improve LLM reasoning via reinforcement learning, inspired by DeepSeek-R1.

Ax Ha-Thanh Nguyen, Hideyuki Tachibana, Chaoran Liu, Qianying Liu, Su Myat Noe, Koichi Takeda, Sadao Kurohashi 3/17/2026

BIS Reasoning 1.0: The First Large-Scale Japanese Benchmark for Belief-Inconsistent Syllogistic Reasoning

BIS Reasoning 1.0: Japanese benchmark with 1K+ syllogistic problems evaluating belief bias and inconsistent reasoning in LLMs.

Ax Arpita Chowdhury, Zheda Mai, Zihe Wang, Sooyoung Jeon, Lemeng Wang, Jiacheng Hou, Wei-Lun Chao 3/17/2026

AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

AVA-Bench: systematic evaluation benchmark for vision foundation models addressing blind spots in VQA evaluation protocols.

Ax Geonwoo Cho, Jaegyun Im, Jihwan Lee, Hojun Yi, Sejin Kim, Sundong Kim 3/17/2026

TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design

TRACED: unsupervised environment design using regret approximation for co-learning to improve deep RL agent generalization.

Ax Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa 3/17/2026

Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought

Rationale-Enhanced Decoding improves chain-of-thought prompting in vision-language models by optimizing intermediate reasoning generation.

Ax Hangjie Yuan, Weihua Chen, Jun Cen, Hu Yu, Jingyun Liang, Shuning Chang, Zhihui Lin, Tao Feng, Pengwei Liu, Jiazheng Xing, Hao Luo, Jiasheng Tang, Fan Wang, Yi Yang 3/17/2026

Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective

Lumos-1: LLM-based autoregressive video generation using discrete diffusion with efficient architecture avoiding external encoders.

Ax Julien Pourcel, C\'edric Colas, Pierre-Yves Oudeyer 3/17/2026

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

SOAR: self-improving method integrating language models into evolutionary program synthesis for challenging tasks like ARC-AGI.

Ax Qinglong Yang, Haoming Li, Haotian Zhao, Xiaokai Yan, Jingtao Ding, Fengli Xu, Yong Li 3/17/2026

FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents

FingerTip 20K: benchmark for proactive mobile LLM agents with 20K tasks, evaluating multimodal agents using contextual data without explicit instructions.

Ax Xuan Wu, Di Wang, Chunguo Wu, Kaifang Qi, Chunyan Miao, Yubin Xiao, Jian Zhang, You Zhou 3/17/2026

Efficient Neural Combinatorial Optimization Solver for the Min-max Heterogeneous Capacitated Vehicle Routing Problem

Neural Combinatorial Optimization solver for min-max heterogeneous vehicle routing with multiple vehicles using novel decoding approach.

Ax Xinda Wang, Zhengxu Hou, Yangshijie Zhang, Bingren Yan, Jialin Liu, Chenzhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao 3/17/2026

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation

EvolvR: self-evolving method for story evaluation using LLM-as-judge with pairwise reasoning to improve generation guidance.

Ax Yang Liu, Lu Zhou, Xiawei Du, Ruikun He, Xuguang Zhang, Rongbo Shen, Yixue Li 3/17/2026

Benchmarking LLM-based agents for single-cell omics analysis

Novel benchmarking system evaluating LLM-based agent capabilities for single-cell omics data analysis, assessing planning and code generation.

Ax Haokun Lin, Haobo Xu, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun 3/17/2026

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

Systematic study of post-training quantization methods for diffusion LLMs to enable edge device deployment, comparing compression techniques.

Ax Dongjun Lee, Changho Hwang, Kimin Lee 3/17/2026

Learning to Generate Unit Test via Adversarial Reinforcement Learning

UTRL: reinforcement learning framework training LLMs to generate high-quality unit tests automatically, addressing test generation challenges.

Ax Katalina Hernandez Delgado 3/17/2026

The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment

Research evaluating Law-Following AI framework for embedding legal compliance in advanced AI agents, analyzing legal personhood constructs and technical feasibility.

Ax Zhuoxiao Chen, Hongyang Yu, Ying Xu, Yadan Luo, Long Duong, Yuan-Fang Li 3/17/2026

OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation

Reinforcement learning approach for radiology report generation using FactScore-based rewards with reduced data requirements.

Ax Hanqing Liu, Shouwei Ruan, Jiahuan Long, Junqi Wu, Jiacheng Hou, Huili Tang, Tingsong Jiang, Weien Zhou, Wen Yao 3/17/2026

Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations

Framework evaluating robustness of Vision-Language-Action models under real-world physical variations for robotic tasks.

Ax Mohammed Sabry, Anya Belz 3/17/2026

Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning

Matched-compute study evaluating synthetic data interventions for in-context learning in language models. Tests mechanism-targeted pretraining effects.

Ax Yuan-An Xiao, Pengfei Gao, Chao Peng, Yingfei Xiong 3/17/2026

Reducing Cost of LLM Agents with Trajectory Reduction

Method for reducing LLM agent inference costs through trajectory reduction. Addresses token cost efficiency in multi-turn agent systems for software engineering.

Ax Shuyang Jiang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang 3/17/2026

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling

Technique reducing LLM reasoning model overthinking through decoupled rewards and curriculum scheduling. Addresses excessive token generation without performance gain.

Ax Ziyan Wang, Zheng Wang, Jie Fu, Xingwei Qu, Qi Cheng, Shengpu Tang, Minjia Zhang, Xiaoming Huo 3/17/2026

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

Reinforcement learning framework (SFPO) for improving LLM reasoning by decomposing policy optimization into slow and fast components to reduce training instability.

Ax Christoph Riedl 3/17/2026

Emergent Coordination in Multi-Agent Language Models

Information-theoretic framework measuring higher-order structure and emergence in multi-agent LLM systems. Tests for dynamical emergence in agent coordination.

Ax Gagan Bhatia, Somayajulu G Sripada, Kevin Allan, Jacobo Azcona 3/17/2026

Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models

Model-native technique to explain LLM hallucinations using layer-wise semantic maps. Traces concept flow through residual streams via unembedding.

Ax Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis 3/17/2026

A Functional Perspective on Knowledge Distillation in Neural Networks

Theoretical analysis of knowledge distillation in neural networks from a functional perspective. Decouples compression from architecture reduction.

Ax Mingyan Yang, Guanjie Wang, Manqi Luo, Yifei Liu, Chen Chen, Han Zhao, Yu Feng, Quan Chen, Minyi Guo 3/17/2026

Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering

Justitia scheduling algorithm for fair and efficient execution of task-parallel LLM agents on shared GPUs. Resource scheduling optimization for agent systems.

Ax Xueyi Chen, Keda Tao, Kele Shao, Huan Wang 3/17/2026

StreamingTOM: Streaming Token Compression for Efficient Video Understanding

StreamingTOM training-free token compression for streaming video understanding. Efficiency optimization for video vision-language models.

Ax Jinchang Luo, Mingquan Cheng, Fan Wan, Ni Li, Xiaoling Xia, Shuangshuang Tian, Tingcheng Bian, Haiwei Wang, Haohuan Fu, Yan Tao 3/17/2026

GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

GlobalRAG reinforcement learning approach for multi-hop question answering with improved global reasoning. RAG system enhancement via RL for better query planning.

Ax Vishakha Lall, Yisi Liu 3/17/2026

Eyes on Target: Gaze-Aware Object Detection in Egocentric Video

Gaze-guided object detection framework for egocentric videos using vision transformers. Computer vision with attention mechanisms.

Ax Manav Kulshrestha, S. Talha Bukhari, Damon Conover, Aniket Bera 3/17/2026

VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models

Zero-shot robotic grasp detection using vision-language models without training data or retraining. Robotics application leveraging VLMs.

Ax Ankan Mullick, Sukannya Purkayastha, Saransh Sharma, Pawan Goyal, Niloy Ganguly 3/17/2026

IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction

Semi-supervised intent detection framework with active learning correction for voice dialog agents. LLM application for dialog system improvement.

Ax Athul M. Mathew, Haithem Hermassi, Thariq Khalid, Arshad Ali Khan 3/17/2026

GazeVLM: A Vision-Language Model for Multi-Task Gaze Understanding

Vision-language model for unified gaze understanding combining detection, target, and object recognition. Multimodal model for attention estimation.

Ax Khashayar Alavi, Zhastay Yeltay, Lucie Flek, Akbar Karimi 3/17/2026

Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization

Privacy-preserving explainable AI for IoT applications using SHAP entropy regularization. Focuses on interpretability and privacy in edge devices.

Ax Bowen Sun, Yujun Cai, Ming-Hsuan Yang, Hang Wu, Yiwei Wang 3/17/2026

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs

Training-free stabilizer (PAS) fixing temporal inconsistency in video LLMs caused by rotary position embedding ripples. Technical improvement for video understanding.

Ax Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU 3/17/2026

Decoupled Action Expert: Confining Task Knowledge to the Conditioning Pathway

Decoupled action expert for vision-language-action models using diffusion/flow-matching for manipulation policies. Computer vision and robotics research.

Ax Yuxuan Gu, Weimin Bai, Yifei Wang, Weijian Luo, He Sun 3/17/2026

Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

Fast inference acceleration for masked auto-regressive diffusion models enabling practical reinforcement learning. Optimization technique for generative models in RL contexts.

Ax Scott Merrill, Shashank Srivastava 3/17/2026

Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation

Pipeline for speaker-attributed civic simulation using LLMs from ASR transcripts. LLM application for multi-agent deliberation modeling.

Ax Arianna Stropeni, Valentina Zaccaria, Francesco Borsatti, Davide Dalle Pezze, Manuel Barusco, Gian Antonio Susto 3/17/2026

Explainable Visual Anomaly Detection via Concept Bottleneck Models

Concept bottleneck models for explainable visual anomaly detection with semantic interpretability. Computer vision research with interpretability focus.

Ax Chieh-Yun Chen, Zhonghao Wang, Qi Chen, Zhifan Ye, Min Shi, Yue Zhao, Yinan Zhao, Hui Qu, Wei-An Lin, Yiru Shen, Ajinkya Kale, Irfan Essa, Humphrey Shi 3/17/2026

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models

MapReduce LoRA and RaTE methods for multi-preference optimization in generative models using RLHF. Advances alignment of LLMs through parameter-efficient fine-tuning techniques.

Ax Osvaldo Simeone, Yaniv Romano 3/17/2026

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective

Review of uncertainty quantification and data efficiency methods for AI systems in robotics, telecommunications, and healthcare. Theoretical ML research with practical applications.

Ax Michael Schlee, Christoph Weisser, Timo Kivim\"aki, Melchizedek Mashiku, Benjamin Saefken 3/17/2026

LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification

Combines large language models with transformer encoders for financial news classification with limited labeled training data.

Ax Bart{\l}omiej Starosta, S{\l}awomir T. Wierzcho\'n, Piotr Borkowski, Dariusz Czerski, Marcin Sydow, Eryk Laskowski, Mieczys{\l}aw A. K{\l}opotek 3/17/2026

Rough Sets for Explainability of Spectral Graph Clustering

Rough set theory applied to explain results of spectral graph clustering algorithms for text document analysis.

Ax Sangeeth B, Serena Nicolazzo, Deepa K., Vinod P 3/17/2026

Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking

Method for watermarking deep neural networks to protect intellectual property and verify model ownership using chaos-based approaches.

Ax Gyeongrok Oh, Youngdong Jang, Jonghyun Choi, Suk-Ju Kang, Guang Lin, Sangpil Kim 3/17/2026

Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation

Geo-4D: training-free geometric approach for 4D LiDAR panoptic segmentation without deep networks or dedicated modules.

Ax Yongxin Wang, Zhicheng Yang, Meng Cao, Mingfei Han, Haokun Lin, Yingying Zhu, Xiaojun Chang, Xiaodan Liang 3/17/2026

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

CARE: failure-centric post-training framework using contrastive learning for verifiable multimodal reasoning in reinforcement learning.

Ax Hongming Fu, Wenjia Wang, Xiaozhen Qiao, Rolandos Alexandros Potamias, Taku Komura, Shuo Yang, Zheng Liu, Bo Zhao 3/17/2026

EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos

EgoGrasp: method for reconstructing world-space hand-object interactions from egocentric videos supporting open-vocabulary objects.

Ax Shaocheng Shen, Jianfeng Liang, Chunlei Cai, Cong Geng, Huiyu Duan, Xiaoyun Zhang, Qiang Hu, Guangtao Zhai 3/17/2026

Agentic Retoucher for Text-To-Image Generation

Agentic Retoucher: hierarchical agent for fixing distortions in text-to-image generation with spatial grounding.