Isolater - Feed

Ax Ziyang Yu, Wenbing Huang, Yang Liu 3/2/2026

Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge

Pretrained variational bridge for efficient molecular dynamics trajectory generation across diverse molecular systems.

Ax Iv\'an Arcuschin, David Chanin, Adri\`a Garriga-Alonso, Oana-Maria Camburu 3/2/2026

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

Automated detection pipeline for unverbalized biases in LLM chain-of-thought reasoning without predefined categories.

Ax Zhen Bi, Xueshu Chen, Luoyang Sun, Yuhang Yao, Qing Shen, Jungang Lou, Cheng Deng 3/2/2026

RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis

Performance characterization framework for small language models on edge devices using Roofline model analysis.

Ax Zhongzheng Qiao, Sheng Pan, Anni Wang, Viktoriya Zhukova, Yong Liu, Xudong Jiang, Qingsong Wen, Mingsheng Long, Ming Jin, Chenghao Liu 3/2/2026

It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

Benchmarking framework for time series foundation models addressing data quality, task alignment, and evaluation rigor.

Ax Daniel Romero-Alvarado, Fernando Mart\'inez-Plumed, Lorenzo Pacchiardi, Hugo Save, Siddhesh Milind Pawar, Behzad Mehrbakhsh, Pablo Antonio Moreno Casares, Ben Slater, Paolo Bova, Peter Romero, Zachary R. Tyler, Jonathan Prunty, Luning Sun, Jose Hernandez-Orallo 3/2/2026

Capabilities Ain't All You Need: Measuring Propensities in AI

Framework for measuring propensities (behavioral tendencies) in AI models beyond capability assessment using Item Response Theory.

Ax Sacchit Kale, Piyushi Manupriya, Pierre Marion, Francis Bach, Anant Raj 3/2/2026

Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression

Theoretical analysis of gradient descent convergence rates under large step sizes in separable logistic regression.

Ax Karthik Elamvazhuthi, Abhijith Jayakumar, Andrey Y. Lokhov 3/2/2026

Discrete Diffusion with Sample-Efficient Estimators for Conditionals

Discrete diffusion framework using sample-efficient conditional probability estimators for discrete state space generation.

Ax Junchen Liu, Sven Elflein, Or Litany, Zan Gojcic, Ruilong Li 3/2/2026

Test-Time Training with KV Binding Is Secretly Linear Attention

Analysis showing test-time training with KV binding functions as learned linear attention rather than memorization.

Ax Alina Devkota, Jacob Thrasher, Donald Adjeroh, Binod Bhattarai, Prashnna K. Gyawali 3/2/2026

FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning

Federated learning aggregation method (FedVG) using gradient guidance to address client drift and data heterogeneity.

Ax Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti 3/2/2026

Provably Safe Generative Sampling with Constricting Barrier Functions

Safety filtering framework for flow-based generative models with formal guarantees on constraint satisfaction.

Ax Chengrui Qu, Yizhou Zhang, Nicolas Lanzetti, Eric Mazumdar 3/2/2026

Training Generalizable Collaborative Agents via Strategic Risk Aversion

Strategic risk aversion approach for training collaborative AI agents that generalize better with new partners.

Ax Yicheng Bao, Xuhong Wang, Qiaosheng Zhang, Chaochao Lu, Xia Hu, Xin Tan 3/2/2026

To Deceive is to Teach? Forging Perceptual Robustness via Adversarial Reinforcement Learning

Adversarial reinforcement learning dataset (AOT-SFT) to improve robustness of multimodal LLMs on visually complex scenes.

Ax Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala, Idan Habler, Ammar Al-Kahfah, Ken Huang, Blake Gatto 3/2/2026

Manifold of Failure: Behavioral Attraction Basins in Language Models

Maps failure regions in LLMs using MAP-Elites quality diversity search to characterize unsafe behaviors and vulnerabilities.

Ax Timothy Oladunni, Blessing Ojeme, Kyndal Maclin, Clyde Baidoo 3/2/2026

When Should a Model Change Its Mind? An Energy-Based Theory and Regularizer for Concept Drift in Electrocardiogram (ECG) Signals

Energy-based theory for detecting concept drift in ECG signals, distinguishing physiologically plausible variation from true distribution shift.

Ax Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun 3/2/2026

Regularized Online RLHF with Generalized Bilinear Preferences

Regularized online RLHF for Nash Equilibrium identification with generalized bilinear preferences modeling intransitive preferences.

Ax Tianjun Yao, Yongqiang Chen, Yujia Zheng, Pan Li, Zhiqiang Shen, Kun Zhang 3/2/2026

ParamMem: Augmenting Language Agents with Parametric Reflective Memory

ParamMem augments language agents with parametric reflective memory to improve reasoning through diverse self-reflection.

Ax Ankur Sinha, Chaitanya Agarwal, Pekka Malo 3/2/2026

FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data

FinBloom presents a knowledge-grounding approach for LLMs to handle real-time financial queries with live data integration.

Ax Tim Schneider, Cristiana de Farias, Roberto Calandra, Liming Chen, Jan Peters 3/2/2026

Apple: Toward General Active Perception via Reinforcement Learning

Apple proposes general active perception via reinforcement learning to handle uncertainty in partially observable robotic environments.

Ax Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jun Rao, Min Zhang 3/2/2026

REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning

REA-RL uses online reinforcement learning with reflection to reduce overthinking and inference costs in large reasoning models.

Ax Sijie Li, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang 3/2/2026

CoMind: Towards Community-Driven Agents for Machine Learning Engineering

CoMind introduces MLE-Live, a framework for evaluating LLM agents that engage with research communities in ML engineering tasks.

Ax Nathan Mitchell, Lander Ver Hoef, Imme Ebert-Uphoff, Kristina Moen, Kyle Hilburn, Yoonjin Lee, Emily J. King 3/2/2026

Knowledge-Guided Machine Learning: Illustrating the use of Explainable Boosting Machines to Identify Overshooting Tops in Satellite Imagery

Uses Explainable Boosting Machines to identify overshooting tops in satellite imagery for weather forecasting, emphasizing interpretability in high-stakes ML.

Ax Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani 3/2/2026

pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models

pFedMMA proposes personalized federated fine-tuning with multi-modal adapters for vision-language models like CLIP on decentralized heterogeneous data.

Ax Paul Richmond, Prarit Agarwal, Borun Chowdhury, Vasilis Niarchos, Constantinos Papageorgakis 3/2/2026

FeynTune: Large Language Models for High-Energy Theory

20 fine-tuned Llama-3.1 8B variants specialized for High-Energy Physics, trained on arXiv abstracts with comparative domain analysis.

Ax Junming Yang, Ning Xu, Biao Liu, Shiqi Qiao, Xin Geng 3/2/2026

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Research method for LLM alignment using meta-weighted online sampling to address distribution mismatch between offline data and evolving model policy.

Ax Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu, Xiaobin Wang, Jintian Zhang, Zhao Bin, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen 3/2/2026

Scaling Generalist Data-Analytic Agents

DataMind framework trains scalable generalist data-analytic agents on diverse data formats for multi-step reasoning in scientific discovery.

Ax Laura Ying Schulz, Daniel Mitropolsky, Tomaso Poggio 3/2/2026

Unraveling Syntax: How Language Models Learn Context-Free Grammars

Study analyzing how language models learn context-free grammar structures and subgrammars during pretraining.

Ax Marcel Wien\"obst, Leonard Henckel, Sebastian Weichwald 3/2/2026

Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning

FLOP algorithm performs causal structure discovery for linear models using fast parent selection and discrete search optimization.

Ax Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee 3/2/2026

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Supervised Reinforcement Learning framework combines expert trajectories with step-wise reasoning to improve multi-step reasoning in open-source LLMs.

Ax Constanza Fierro, Fabien Roger 3/2/2026

Steering Language Models with Weight Arithmetic

Contrastive weight steering method edits LLM parameters via weight arithmetic for post-training behavior modification without expensive retraining.

Ax Aaron Miller, Sahil Kommalapati, Robert Moser, Petros Koumoutsakos 3/2/2026

Structure tensor Reynolds-averaged Navier-Stokes turbulence models with equivariant neural networks

Equivariant neural networks improve RANS turbulence model closures using structure tensors for better generalization in fluid dynamics.

Ax Rasmus F. Orsoe, Stephan Meighen-Berger, Jeffrey Lazar, Jorge Prado, Ivan Mozun-Mateo, Aske Rosted, Philip Weigel, Arturo Llorente Anaya 3/2/2026

NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes

NuBench open benchmark for deep learning-based event reconstruction in neutrino telescopes addressing inverse problems in particle physics.

Ax Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen 3/2/2026

Score-Regularized Joint Sampling with Importance Weights for Flow Matching

Non-IID sampling framework for flow matching models to reduce variance in expectation estimation with limited sampling budgets.

Ax Juvenal Bassa, Arghya Chattopadhyay, Sudhir Malik, Mario Escabi Rivera 3/2/2026

MEDIC: a network for monitoring data quality in collider experiments

MEDIC applies machine learning for automated data quality monitoring and anomaly detection in particle physics collider experiments.

Ax Tanmay Ambadkar, {\DJ}or{\dj}e \v{Z}ikeli\'c, Abhinav Verma 3/2/2026

Automating the Refinement of Reinforcement Learning Specifications

AutoSpec framework automatically refines logical specifications for reinforcement learning agents to improve policy learning from under-specified tasks.

Ax Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Nan-Yow Chen, Samuel Yen-Chi Chen, En-Jui Kuo, Hsi-Sheng Goan 3/2/2026

QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

QKAN-LSTM combines quantum-inspired methods with Kolmogorov-Arnold networks for improved sequential modeling with reduced parameter redundancy.

Ax Liping Tao, Xindi Tong, Chee Wei Tan 3/2/2026

Learning to Optimize by Differentiable Programming

Tutorial on using differentiable programming frameworks like PyTorch and JAX to learn and design optimization algorithms automatically.

Ax Thomas Ziller, Shashikant Ilager, Alessandro Tundo, Ezio Bartocci, Leonardo Mariani, Ivona Brandic 3/2/2026

GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference

GreenServ proposes dynamic routing framework for efficient multi-model LLM inference using context-aware model selection to reduce energy consumption.

Ax Quanquan Peng, Yunfeng Lin, Yufei Xue, Jiangmiao Pang, Weinan Zhang 3/2/2026

Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Research on training humanoid robots with reinforcement learning to handle diverse embodiments and complex behaviors through distillation methods.

Ax Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman, Mahfuz Ahmed Anik, Munem Shahriar, Mohsin Mahmud Topu, Sadia Tasnim Meem, Rahatun Nesa Priti, Sabrina Afroz Mitu, Md. Iqramul Hoque, Shahriyar Zaman Ridoy, Mohammed Eunus Ali, Majd Hawasly, Mohammad Raza, Md Rizwan Parvez 3/2/2026

SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

SpatiaLab benchmark evaluates vision-language models' spatial reasoning capabilities on real-world tasks with visual noise and diverse spatial relationships.

Ax Runze Tang, Penny Sweetser 3/2/2026

Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learning

SpatiaLab: benchmark evaluating vision-language model spatial reasoning on complex real-world visual scenarios.

Ax Ramansh Sharma, Matthew Lowery, Houman Owhadi, Varun Shankar 3/2/2026

Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows

Flow-based intermediate representation for few-shot robot imitation learning from human video demonstrations.

Ax Guoxuan Ma, Yuan Zhong, Moyan Li, Yuxiao Nie, Jian Kang 3/2/2026

Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance

Property-preserving kernel operator learning for incompressible Navier-Stokes flow simulation and surrogate modeling.

Ax Danil Akhtiamov, Reza Ghane, Omead Pooladzandi, Babak Hassibi 3/2/2026

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent

SceneTok: tokenizer encoding 3D scene views into compressed, permutation-invariant tokens for diffusion models.

Ax Xiang Li, Zikai Wei, Yiyan Qi, Wanyun Zhou, Xiang Liu, Penglei Sun, Jian Guo, Yongqi Zhang, Xiaowen Chu 3/2/2026

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

Theoretical analysis of stochastic mirror descent convergence with matrix parameters in overparameterized regime.

Ax Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong 3/2/2026