Isolater - Feed

Ax Sihong Wu, Yiling Ma, Yilun Zhao, Tiansheng Hu, Owen Jiang, Manasi Patwardhan, Arman Cohan 3/11/2026

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation

LLM-based method for generating actionable peer review feedback using rebuttal data as supervision.

Ax Chengjun Yu, Xuhan Zhu, Chaoqun Du, Pengfei Yu, Wei Zhai, Yang Cao, Zheng-Jun Zha 3/11/2026

EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning

Benchmark for evaluating multimodal LLMs on egocentric scene prediction with long-horizon action reasoning.

Ax Soroush Seifi, Simon Gardier, Vaggelis Dorovatas, Daniel Olmeda Reino, Rahaf Aljundi 3/11/2026

Ego: Embedding-Guided Personalization of Vision-Language Models

Personalization framework for vision-language models enabling customized AI assistants without additional training.

Ax Jialei Tan, Zheng Lin, Xiangming Cai, Ruoxi Zhu, Zihan Fang, Pingping Chen, Wei Ni 3/11/2026

Exploiting Label-Aware Channel Scoring for Adaptive Channel Pruning in Split Learning

Adaptive channel pruning for split learning to reduce communication overhead in federated training.

Ax Abhishikth Mallampalli, Sridhara Dasu 3/11/2026

MITRA: An AI Assistant for Knowledge Retrieval in Physics Collaborations

RAG-based AI assistant prototype for knowledge retrieval across large scientific collaboration documentation.

Ax Vitaly Bulgakov 3/11/2026

Correction of Transformer-Based Models with Smoothing Pseudo-Projector

Lightweight pseudo-projector module to improve transformer robustness by correcting hidden representations.

Ax Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee, Mengye Ren, Sung Ju Hwang 3/11/2026

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents

QA task over multi-agent egocentric video data for human-AI collaboration scenarios.

Ax Laya Iyer, Angelina Wang, Sanmi Koyejo 3/11/2026

SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases

Benchmark suite for evaluating large audio language models on audio understanding tasks beyond speech recognition.

Ax Mohamad Alkadamani, Halim Yanikomeroglu, Amir Ghasemi 3/11/2026

A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks

Hierarchical graph attention network for spectrum demand prediction using geospatial data.

Ax Yiyang Lu, Yu He, Jianlong Chen, Hongyuan Zha 3/11/2026

MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning

Memory-aware replay strategy for continual LLM fine-tuning to prevent catastrophic forgetting during sequential training.

Ax Colin Brown, Mohamad Alkadamani, Halim Yanikomeroglu 3/11/2026

AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation

Data-driven ML approach for forecasting spectrum demand in wireless networks.

Ax Alberto Fern\'andez-Hern\'andez, Cristian P\'erez-Corral, Jose I. Mestre, Manuel F. Dolz, Jose Duato, Enrique S. Quintana-Ort\'i 3/11/2026

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

Analysis of learning rate sensitivity in PPO actor-critic RL using hidden neuron behavior and overfitting metrics.

Ax Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve 3/11/2026

Towards a Neural Debugger for Python

Neural debugger training LLMs on Python execution traces to enable line-by-line execution prediction for developer assistance.

Ax Xinyu Gao, Gang Chen, Javier Alonso-Mora 3/11/2026

BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion

BEACON predicts navigation affordances from language instructions and visual observations, handling occluded regions via vision-language models.

Ax Lucas Prieto, Edward Stevinson, Melih Barsbey, Tolga Birdal, Pedro A. M. Mediano 3/11/2026

From Data Statistics to Feature Geometry: How Correlations Shape Superposition

Mechanistic interpretability study of how feature correlations shape superposition in neural networks beyond sparse, uncorrelated settings.

Ax Ziwei Zhou, Rui Wang, Zuxuan Wu, Yu-Gang Jiang 3/11/2026

Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities

Daily-Omni benchmark for audio-visual reasoning with temporal alignment in multimodal LLMs using 684 real-world videos.

Ax Xueyao Wan, Hang Yu 3/11/2026

MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs

MMGraphRAG extends GraphRAG to multimodal knowledge graphs preserving visual structure, reducing LLM hallucinations in vision-language tasks.

Ax Hanzhong Zhang, Muhua Huang, Jindong Wang 3/11/2026

Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents

CMASE framework combining generative agent-based modeling with virtual ethnography for interactive social simulation research.

Ax Honghao Fu, Junlong Ren, Qi Chai, Deheng Ye, Yujun Cai, Hao Wang 3/11/2026

VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft

VistaWise framework integrating cross-modal domain knowledge graphs with fine-tuned smaller models for cost-effective embodied agents in Minecraft.

Ax Zhanke Zhou, Chentao Cao, Xiao Feng, Xuan Li, Zongze Li, Xiangyu Lu, Jiangchao Yao, Weikai Huang, Tian Cheng, Jianghangfan Zhang, Tangyu Jiang, Linrui Xu, Yiming Zheng, Brando Miranda, Tongliang Liu, Sanmi Koyejo, Masashi Sugiyama, Bo Han 3/11/2026

AlphaApollo: A System for Deep Agentic Reasoning

AlphaApollo system for agentic reasoning combining multi-turn interactions, structured tool calls, and trustworthy verification for long-horizon problem solving.

Ax Guang Yang, Tianpei Yang, Jingwen Qiao, Yanqing Wu, Jing Huo, Xingguo Chen, Yang Gao 3/11/2026

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

Multi-agent RL approach handling lossy communication constraints for cooperative policy learning in complex, dynamic real-world environments.

Ax Polaris Jhandi, Owais Kazi, Shreyas Subramanian, Neel Sendas 3/11/2026

Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning

Small Language Models fine-tuned for agentic tool calling outperform large models while reducing computational costs for enterprise deployment.

Ax Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong 3/11/2026

Reinforcement Learning for Self-Improving Agent with Skill Library

LLM-based agents with skill libraries that enable continuous learning and adaptation through skill validation and application in new environments.

Ax Jiaxuan Gao, Jiaao Chen, Chuyi He, Shusheng Xu, Di Jin, Yi Wu 3/11/2026

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents

Method for post-training multi-turn interactive tool-using agents via self-evolving synthetic data and verifiable-reward RL, enabling complex multi-step task execution.

Ax Elias Hossain, Shubhashis Roy Dipta, Subash Neupane, Rajib Rana, Ravid Shwartz-Ziv, Ivan Garibay, Niloofar Yousefi 3/11/2026

UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers

UAT-LITE addresses miscalibration in neural NLP models by adding inference-time uncertainty awareness to transformer attention without changing training or storage costs.

Ax Aditya Gulati, Nuria Oliver 3/11/2026

Why do we Trust Chatbots? From Normative Principles to Behavioral Drivers

Examines behavioral mechanisms underlying user trust in chatbots versus normative trust frameworks.

Ax Jaehoon Lee, Suhwan Park, Tae Yoon Lim, Seunghan Lee, Jun Seo, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, SoonYoung Lee, Yongjae Lee, Wonbin Ahn 3/11/2026

FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing

FinTexTS dataset pairs financial time-series with textual data using semantic-based multi-level pairing for joint analysis.

Ax Yong Liu, Xingjian Su, Shiyu Wang, Haoran Zhang, Haixuan Liu, Yuxuan Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long 3/11/2026

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Timer-S1 is a 8.3B parameter mixture-of-experts time series foundation model with serial scaling across architecture, data, and training.

Ax Zhiming Xue, Yujue Wang, Menghao Huo 3/11/2026

LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks

Framework combining temporal graph attention networks with LLM explanations for supply chain risk prediction and interpretation.

Ax Amutheezan Sivagnanam, Ayan Mukhopadhyay, Samitha Samaranayake, Abhishek Dubey, Aron Laszka 3/11/2026

Dynamic Vehicle Routing Problem with Prompt Confirmation of Advance Requests

Dynamic vehicle routing optimization for on-demand transit with advance request confirmation and real-time constraints.

Ax Jahir Sadik Monon, Deeparghya Dutta Barua, Md. Mosaddek Khan 3/11/2026

Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards

GNN-driven intrinsic rewards improve cooperation in decentralized multi-agent reinforcement learning with heterogeneous agents.

Ax Jian Xu, Delu Zeng, John Paisley 3/11/2026

Sparse Variational Student-t Processes for Heavy-tailed Modeling

Sparse Variational Student-t Processes enable scalable Gaussian process alternatives for heavy-tailed data modeling.

Ax Chengxi Ye, Grace Chu, Yanfeng Liu, Yichi Zhang, Lukasz Lew, Li Zhang, Mark Sandler, Andrew Howard 3/11/2026

Robust Training of Neural Networks at Arbitrary Precision and Sparsity

Robust neural network training method addressing gradient path issues in quantization and sparsification for ultra-low precision regimes.

Ax Shaobo Wang, Youxin Jiang, Tianle Niu, Yantai Yang, Ruiji Zhang, Shuhao Hu, Shuaiyu Zhang, Chenghao Sun, Weiya Li, Conghui He, Xuming Hu, Linfeng Zhang 3/11/2026

DRUPI: Dataset Reduction Using Privileged Information

DRUPI reduces datasets using privileged information beyond input-label pairs, improving dataset condensation efficiency.

Ax Xinxin You, Xien Liu, Xue Yang, Ziyi Wang, Ji Wu 3/11/2026

MKE-Coder: Multi-Axial Knowledge with Evidence Verification in ICD Coding for Chinese EMRs

MKE-Coder applies multi-axial knowledge and evidence verification for automatic ICD coding in Chinese electronic medical records.

Ax Ling Xiao, Toshihiko Yamasaki 3/11/2026

LLM-Advisor: An LLM Benchmark for Cost-efficient Path Planning across Multiple Terrains

LLM-Advisor benchmarks LLMs for cost-efficient multi-terrain path planning in robot navigation tasks.

Ax Arsham Gholamzadeh Khoee, Shuai Wang, Robert Feldt, Dhasarathy Parthasarathy, Yinan Yu 3/11/2026

GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics

GateLens is an LLM agent for automotive software analytics that enhances reasoning on structured tabular data with safety-critical decision support.

Ax Gerardo Flores, Abigail Schiff, Alyssa H. Smith, Julia A Fukuyama, Ashia C. Wilson 3/11/2026

A Consequentialist Critique of Binary Classification Evaluation: Theory, Practice, and Tools

Consequentialist critique of binary classification evaluation metrics, advocating for proper scoring rules over threshold-dependent metrics.

Ax Arash Ahmadi, Sarah Sharif, Yaser M. Banad 3/11/2026

MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers

MCP Bridge provides a lightweight RESTful proxy for Model Context Protocol servers, enabling LLM tool integration on resource-constrained devices.

Ax Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin 3/11/2026

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO

Stepwise Guided Policy Optimization improves GRPO for LLM reasoning by addressing the all-negative-sample group failure in reinforcement learning.

Ax Xiaojie Gu, Ziying Huang, Jia-Chen Gu, Kai Zhang 3/11/2026

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models

UltraEdit enables efficient lifelong knowledge editing in LLMs without training, preserving existing capabilities while updating with new information.

Ax Huanyu Liu, Ge Li, Jia Li, Hao Zhu, Kechi Zhang, Yihong Dong 3/11/2026

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning

SATURN uses SAT-based reinforcement learning to improve LLM reasoning capabilities without heavy human annotation or expensive data synthesis.

Ax Shunyu Wu, Dan Li, Wenjie Feng, Haozheng Ye, Jian Lou, See-Kiong Ng 3/11/2026

Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment

Meta-learning approach to rate time series data quality using LLM judgments, extending to diverse domains beyond single-domain methods.

Ax Mengda Ji, Genjiu Xu, Keke Jia, Zekun Duan, Yong Qiu, Jianjun Ge, Mingqiang Li 3/11/2026

Cooperative Game-Theoretic Credit Assignment for Multi-Agent Policy Gradients via the Core

CORA method uses cooperative game theory to solve credit assignment in multi-agent reinforcement learning through coalitional advantage allocation.

Ax Jinkwan Jang, Hyungjin Park, Jinmyeong Choi, Taesup Kim 3/11/2026

Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness

Unified framework for multivariate time series forecasting handling inter-channel dependencies, sampling asynchrony, and missing values.

Ax Negar Foroutan, Jakhongir Saydaliev, Ye Eun Kim, Antoine Bosselut 3/11/2026