Isolater - Feed

Ax Th\'eo A. Neukomm, Zlatko Jon\v{c}ev, Philippe Schwaller 4/20/2026

Teaching Language Models Mechanistic Explainability Through MechSMILES

Framework teaching LLMs to predict chemical reaction mechanisms using arrow-pushing formalism notation for computer-assisted synthesis planning.

Ax Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu 4/20/2026

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration

CadLLM training-free acceleration method for diffusion-based LLM inference using confidence-aware adaptive control of generation parameters.

Ax Sonal Prabhune, Balaji Padmanabhan, Kaushik Dutta 4/20/2026

Information-Consistent Language Model Recommendations through Group Relative Policy Optimization

Group Relative Policy Optimization method for improving consistency and reliability of LLM recommendations across semantically equivalent prompts.

Ax Bhrij Patel, Davide Belli, Amir Jalalirad, Maximilian Arnold, Aleksandr Ermolov, Bence Major 4/20/2026

Dynamic Tool Dependency Retrieval for Lightweight Function Calling

Dynamic tool dependency retrieval method for LLM-based function calling agents, improving tool selection and reducing context length for on-device agents.

Ax Zijian Zhao, Yitong Shang, Sen Li 4/20/2026

AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt

Federated learning approach for traffic prediction using adaptive prompts, enabling privacy-preserving collaborative training across distributed data.

Ax Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen, Weidong Zhang, Yujin Yuan, Tong Xiao, Jingbo Zhu, Wenbo Su, Bo Zheng 4/20/2026

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling

CoMeT architecture enabling LLMs to process arbitrarily long sequences with constant memory and linear time complexity via efficient plug-in module.

Ax Peter Lalor, Ayush Panigrahy, Alex Hagen 4/20/2026

Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy

Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy using simulation-to-reality transfer learning.

Ax Indranil Halder, Annesya Banerjee, Cengiz Pehlevan 4/20/2026

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Empirical analysis of adversarial attacks on safety-aligned LLMs showing polynomial-to-exponential growth in attack success rates with prompt injection.

Ax Yuval Ran-Milo 4/20/2026

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks

Proves attention sinks are functionally necessary in softmax transformers for certain tasks, formalizing their role beyond optimization artifacts.

Ax Mahmoud Elhadidy, Roshan M. D'Souza, Amirhossein Arzani 4/20/2026

SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators

Continual learning framework for Fourier Neural Operators enabling model adaptation to new data distributions without retraining on prior data.

Ax Alex Al\`i Maleknia, Yuzuru Sato 4/20/2026

Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario

Dynamical analysis of MLP training through saddle structures, explaining vanishing gradients and overfitting phenomena.

Ax William Merrill, Yanhong Li, Tyler Romero, Anej Svete, Caia Costello, Pradeep Dasigi, Dirk Groeneveld, David Heineman, Bailey Kuehl, Nathan Lambert, Chuan Li, Kyle Lo, Saumya Malik, DJ Matusz, Benjamin Minixhofer, Jacob Morrison, Luca Soldaini, Finbarr Timbers, Pete Walsh, Noah A. Smith, Hannaneh Hajishirzi, Ashish Sabharwal 4/20/2026

Olmo Hybrid: From Theory to Practice and Back

Hybrid language models mixing RNNs and attention mechanisms, comparing performance advantages over pure transformers with theoretical and practical evidence.

Ax Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, J\"urgen Schmidhuber 4/20/2026

Neural Computers

Proposes Neural Computers that unify computation, memory, and I/O in learned runtime states, exploring general-purpose neural machine architectures.

Ax Haonan Zhu, Adrienne Deganutti, Elad Hirsch, Purvanshi Mehta 4/20/2026

Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis

Leave-one-out analysis for evaluating SVG generation beyond visual similarity, assessing structural editability and reusability.

Ax Patrick Lutz, Themistoklis Haris, Arjun Chandra, Aditya Gangrade, Venkatesh Saligrama 4/20/2026

Layerwise Dynamics for In-Context Classification in Transformers

Interpretable analysis of transformer in-context classification using permutation equivariance constraints to reveal layer-wise dynamics.

Ax You Qin, Linqing Wang, Hao Fei, Roger Zimmermann, Liefeng Bo, Qinglin Lu, Chunyu Wang 4/20/2026

SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

SOAR bridges SFT and RL stages in diffusion model training with self-correction mechanism for out-of-distribution denoising.

Ax Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel, Hassan Sawaf 4/20/2026

Selectivity and Shape in the Design of Forward-Forward Goodness Functions

Explores goodness function design space for Forward-Forward algorithm, finding shape-sensitive functions outperform sum-of-squares.

Ax Chuangtao Chen, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo, Bing Li, Ulf Schlichtmann 4/20/2026

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

Context-independent KV caching for LLMs eliminating recomputation overhead when reusing cached documents in new contexts.

Ax Sourav Ganguly, Kartik Pandit, Arnob Ghosh 4/20/2026

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

Policy learning algorithm with regret and violation guarantees for agents operating under adversarial exogenous factors.

Ax Yuncong Liu, Yuan Wan, Zhou Jiang, Yao Lu 4/20/2026

When Missing Becomes Structure: Intent-Preserving Policy Completion from Financial KOL Discourse

Completes financial KOL trading strategies from discourse by inferring unspecified execution decisions using structured analysis.

Ax Amy Rouillard, Sitwala Mundia, Linda Camara, Michael Cameron Gramanie, Ziyaad Dangor, Ismail Kalla, Shabir A. Madhi, Kajal Morar, Marlvin T. Ncube, Haroon Saloojee, Bruce A. Bassett 4/20/2026

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?

Evaluates LLM jury of frontier models scoring medical diagnoses against expert clinician panels on real-world hospital cases.

Ax Yury Gorishniy, Ivan Rubachev, Dmitrii Feoktistov, Artem Babenko 4/20/2026

Benchmarking Optimizers for MLPs in Tabular Deep Learning

Systematic benchmark of 15 optimizers on 17 tabular datasets for training MLP-based models, examining alternatives to AdamW.

Ax Goitom Ybrah Hailu, Hadush Hailu, Shishay Welay 4/20/2026

Deep Learning Based Amharic Chatbot for FAQs in Universities

Chatbot using NLP and deep learning to answer FAQs in Amharic language for university students.

Ax Garima Chhikara, Anurag Sharma, V. Gurucharan, Kripabandhu Ghosh, Abhijnan Chakraborty 4/20/2026

LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports

LLM-guided extractive summarization for processing code-mixed sexual harassment incident reports on citizen platforms.

Ax Koki Chinzei, Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima 4/20/2026

Resource-efficient equivariant quantum convolutional neural networks

Resource-efficient equivariant quantum convolutional neural networks for near-term quantum devices with limited computational resources.

Ax Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken 4/20/2026

Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All

ML-based preference elicitation algorithms for iterative combinatorial auctions addressing exponential bundle space problem.

Ax Mengxin Wang (Naveen Jindal School of Management, The University of Texas at Dallas), Dennis J. Zhang (Olin School of Business, Washington University in St. Louis), Heng Zhang (W. P. Carey School of Business, Arizona State University) 4/20/2026

Large Language Models for Market Research: A Data-augmentation Approach

Uses LLMs to generate synthetic data for market research and conjoint analysis, addressing scalability limitations of traditional surveys.

Ax Qin Fang, Lei Shi, Min Xu, Ding-Xuan Zhou 4/20/2026

Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approach

Constructive approach for building 2D CNNs to approximate Korobov functions with rigorous theoretical analysis.

Ax Dimitris Tsirmpas, Ion Androutsopoulos, John Pavlopoulos 4/20/2026

Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation

Synthetic Discussion Generation framework uses LLMs to create simulated multi-participant discussions for cost-effective social science experiments.

Ax Rachmad Vidya Wicaksana Putra, Avaneesh Devkota, Muhammad Shafique 4/20/2026

Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents

Scalable multi-task learning for autonomous agents using Spiking Neural Networks with adaptive task-switching to reduce resource consumption.

Ax Wenhao Qian, Zhenzhen Hu, Zijie Song, Jia Li 4/20/2026

Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification

LayerNorm tuning with concept drift guidance for multimodal metaphor identification in internet memes using efficient fine-tuning.

Ax Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang, Yanfang Ye, Soroush Vosoughi 4/20/2026

What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context

Investigates how LLMs effectively model sequential recommendations by analyzing preference intensity and temporal context factors.

Ax Dorival Le\~ao, Reiko Aoki, Alberto Ohashi, Teh Led Red 4/20/2026

Sequential Regression Learning with Randomized Algorithms

Randomized SINDy presents a sequential machine learning algorithm for time-dependent dynamic data with PAC learning guarantees.

Ax Ran Tong, Lanruo Wang, Tong Wang, Wei Yan 4/20/2026

Modeling Parkinson's Disease Progression Using Longitudinal Voice Biomarkers: A Comparative Study of Statistical and Neural Mixed-Effects Models

Compares statistical and neural mixed-effects models for predicting Parkinson's Disease progression using voice biomarkers.

Ax Md Afif Al Mamun, Gias Uddin, Lan Xia, Longyu Zhang 4/20/2026

TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings

TriagerX applies dual transformers to bug triaging, improving token relevance attention for software engineering tasks.

Ax Yuxuan Zhu, David H. Yang, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Pin-Yu Chen 4/20/2026

OjaKV: Context-Aware Online Low-Rank KV Cache Compression

OjaKV compresses KV cache in long-context LLMs using context-aware online low-rank projection, reducing memory bottlenecks during inference.

Ax Akira Takahashi, Shusuke Takahashi, Yuki Mitsufuji 4/20/2026

MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

MMAudioSep applies video-to-audio generative models for sound separation queried by video or text input.

Ax Zihan Zhao, Kaushik Pendiyala, Masood Mortazavi, Ning Yan 4/20/2026

PULSE: Privileged Knowledge Transfer from Rich to Deployable Sensors for Embodied Multi-Sensory Learning

PULSE transfers knowledge from rich sensor modalities to deployable sensors for embodied AI systems with sensor asymmetry constraints.

Ax Ritik Raj, Souvik Kundu, Ishita Vohra, Hong Wang, Tushar Krishna 4/20/2026

Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective

Analyzes CPU-centric execution characteristics of agentic AI systems, examining performance bottlenecks in tool-calling autonomous LLM agents.

Ax Victoria Ebert, Rishabh Singh, Tuochao Chen, Noah A. Smith, Shyamnath Gollakota 4/20/2026

Reading Between the Lines: The One-Sided Conversation Problem

Addresses one-sided conversation problem where only one speaker is recorded, reconstructing missing dialogue and generating summaries using conversational AI.

Ax Dionysios Adamopoulos, Anastasia Poulopoulou, Georgios Goumas, Christina Giannoula 4/20/2026

Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks

Optimizes sparse convolution operations in 3D point cloud networks by exploiting voxel coordinate properties.

Ax Samuel Burles, Enrico Camporeale 4/20/2026

The Machine Learning Approach to Moment Closure Relations for Plasma: A Review

Reviews machine learning approaches for plasma closure relations in fluid dynamics simulations.

Ax Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang 4/20/2026

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

Disco-RAG enhances RAG systems by incorporating discourse structure awareness, enabling LLMs to better synthesize knowledge from multiple retrieved passages.

Ax Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou 4/20/2026

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

EnvScaler automatically generates scalable tool-interactive environments for LLM agents using programmatic synthesis, enabling training without hallucinations or manual sandbox building.

Ax Alexandra Dragomir, Florin Brad, Radu Tudor Ionescu 4/20/2026

CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning

CLewR integrates curriculum learning into preference optimization for machine translation, improving LLM multilingual MT performance by optimizing training data ordering.

Ax Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, Bingxu Mu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Xiansong Huang, Fan Xu, Feidiao Yang, Yao Lu, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian 4/20/2026