isolater
feed knowledge
Search:
Sources
ArXiv CS.AI
ArXiv CS.LG
Bluesky
Dev.to
GitHub Trending
Google DeepMind Blog
Hacker News
HuggingFace Papers
LinkedIn
Lobsters
OpenAI Blog
Twitter/X
YouTube
Topics
llms 98
research 97
code 68
agents 53
training 46
products 41
tutorials 40
open-source 28
inference 25
computer-vision 20
rag 19
infrastructure 16
safety 8
Entities
Claude 38
OpenAI 31
Anthropic 24
Google 19
Gemini 16
MCP 15
Claude Code 13
GitHub 13
AI systems 12
Codex 11
GPT-5 10
Docker 9
NVIDIA 9
DeepSeek 9
Llama 9
EU 8
Hugging Face 7
Transformers 7
Perplexity 5
Microsoft 5
Ax Igor Halperin 6/30/2026

I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory

I-BBS extends BBS theory for coordinate-free inference of latent manifolds from distance matrices using random matrix theory, without accessing ambient space.

Ax Igor Halperin 6/30/2026

Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions

Observable Matrix Dynamics framework uses random matrix theory to diagnose neural network internal representations and training dynamics via distance matrices.

Ax Duc Anh Nguyen 6/30/2026

IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients

IG-Lens provides exact additive probability attribution across transformer layers using integrated gradients, improving upon logit lens methods for interpreting decoder-only models.

Ax Liu Zewen 6/30/2026

A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM Agents

Diagnostic framework (EPC) for detecting preference collapse in self-adapting LLM agents with multimodal evaluators.

Ax Zewen Liu 6/30/2026

The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles

Analysis of how SMOTE and resampling degrade probability calibration in imbalanced classification tree ensembles.

Ax Youngseok Hwang, Sungho Bae, Dohun Lee, Jaeeun Seo, Jeehong Kim, Wonhee Lee, Hyunwoo Park 6/30/2026

Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies

Maritime anomaly detection using equation-grounded synthetic anomalies for AIS vessel tracking data.

Ax Guang-Xing Li 6/30/2026

ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields

ScaleAware-JEPA: self-supervised framework for multiscale physical field representation learning for scientific discovery.

Ax Liam A. Kruse, Houjun Liu, Alexandros E. Tzikas, Mansur M. Arief, Mykel J. Kochenderfer 6/30/2026

Simplifying Flow Matching Transformations with Low-Rank Mixture Models

Low-rank mixture models for flow matching to simplify normalizing flow transformations and improve generative modeling.

Ax Riku Nakao, Akihito Hiromori, Hamada Rizk, Hirozumi Yamaguchi 6/30/2026

Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning

Vehicle routing optimization for nursing care taxi dispatch combining integer linear programming with machine learning.

Ax Doo Hwan Hwang, Kee-Eung Kim 6/30/2026

PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF

PS-PPO: critic-free RLHF method for LLMs using prefix-sampling to optimize long reasoning traces efficiently.

Ax Haoxin Sun, Yiqing Lin, Yajun Huang, Chenhui Dong, Mingjun Li, Zhongzhi Zhang 6/30/2026

GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks

GLIP: joint pretraining framework combining graph neural networks with LLMs for graph-level tasks.

Ax Zheng Fang, Chen Yang, Yusen Tan, Yunpeng Zhao, Fanjie Xu, Hongxin Xiang, Hanyu Sun, Hanyu Gao, Xiaojian Wang, Wenjie Du, Yuqiang Li, Jun Xia 6/30/2026

Towards Generalizable and Evidential Nuclear Magnetic Resonance-Based Molecular Structure Elucidation via Large Language Model Agent

LLM agent for NMR molecular structure elucidation providing interpretable results beyond black-box methods.

Ax Kuan Wang, Chao Zhang 6/30/2026

MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory

MemLeak: method for diagnosing information leaks in multimodal agent memory systems via implicit visual cues.

Ax Kunwoong Kim, Dongha Kim 6/30/2026

What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics

Theoretical analysis of inlier-memorization effect in early training dynamics for unsupervised outlier detection.

Ax Prabhat Nagarajan, Brett Daley, Martha White, Marlos C. Machado 6/30/2026

Accelerating Q-learning through Efficient Value-Sharing across Actions

Efficient value-sharing method for Q-learning that accelerates learning by sharing information across actions.

Ax Qijun Li, Zheng Fu, Qi Song, Yifei He, Weitao Zhou, Kun Jiang, Diange Yang 6/30/2026

Dual-Flow Reinforcement Learning with State-Aware Exploration

Dual-flow reinforcement learning approach for multimodal action exploration in continuous-control tasks.

Ax Yiting Hu, Lingjie Duan, Qian Zhang 6/30/2026

The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning

First certified unlearning theory for continual learning addressing privacy protection with sequential model updates.

Ax Yiting Hu, Lingjie Duan 6/30/2026

Theory of Continual Learning Against Data Poisoning Attacks

Theoretical framework for understanding data poisoning attacks and defenses in continual learning systems.

Ax Nithisha Raghavaraju, Barbara Giunti, Bastian Rieck 6/30/2026

Comparing Chatbot Performance Enhanced with Persistent Homology

Chatbot enhancement using persistent homology for mental health support with privacy-preserving training methods.

Ax Adithya Mohan, Daniel Kriegl, Torsten Sch\"on 6/30/2026

RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning

RoAd-RL: open-source benchmarking framework for robust adversarial reinforcement learning with standardized evaluation protocols.

Ax Chungpa Lee, Jihoon Kwon, Kyle Min, Jy-yong Sohn 6/30/2026

Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders

Sparse autoencoders applied to vision-language joint embeddings to decompose entangled features into interpretable monosemantic components.

Ax Han Zhou, Teodora Popordanoska, Matthew Blaschko 6/30/2026

Bandwidth Selection in Kernel Density Estimation for Model Calibration

Kernel density estimation method for selecting optimal bandwidth in model calibration for uncertainty quantification in deep learning.

Ax Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen 6/30/2026

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

Framework combining deep neural networks with linear model interpretability via local fidelity regularization for more reliable explanations.

Ax Seonghwan Park, Hyunji Jung, Dongyeop Lee, Namhoon Lee 6/30/2026

Exploiting Local Flatness for Efficient Out-of-Distribution Detection

Post-hoc OOD detection method using loss-landscape curvature for uncertainty estimation in pre-trained networks without retraining.

Ax Peyman Hosseini, Ondrej Bohdal, Ahmed Alajrami, Andrea Maracani, Ignacio Castro, Matthew Purver, Mete Ozay, Savas Ozkan, Taha Ceritli 6/30/2026

DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation

DuoMem dual-space distillation framework enabling capable memory-augmented LLM agents on resource-constrained devices.

Ax Aydin Javadov, Shyngys Aitkazinov, Tobias Hoesli, Florian von Wangenheim, Bjoern Schuller, Joseph Ollier 6/30/2026

NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries

Study mapping boundaries of reasoning capability elicitation in LLMs across diverse cognitive tasks.

Ax Ali Ramlaoui, Daniel T. Speckhard, Sagar Pal, Fragkiskos D. Malliaros, Alexandre Duval, Victor Schmidt 6/30/2026

Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets

Atompack: append-oriented storage format for large immutable atomistic ML training datasets.

Ax Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, Wieland Brendel, Martin Jaggi 6/30/2026

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Learned stochastic stopping mechanism for improving length generalization in looped Transformers.

Ax Huy Truong, Alexander Lazovik, Victoria Degeler 6/30/2026

T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

Test-time adaptation for GNNs under distribution shifts via gradient rotation without labeled data.

Ax Huaijie Wang, Shusheng Xu, Yi Wu, Kaifeng Lyu 6/30/2026

Building Multi-Task Agentic LLMs via Two-Phase Distillation

Two-phase distillation approach for building multi-task agentic LLMs from separate RL experts.

Ax Shuchang Ye, Jinqiang Yu, Zhujun Xiao, Yajing Kong, Yist Y. Lin, Yang Ma, Jiaxi Liu, Xiaolei Xu, Zheng Yu 6/30/2026

From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation

Diagnostic methodology for industry-scale audio-visual LLM evaluation in video moderation systems.

Ax L. U. Abdullaev, F. Herrera, U. A. Rozikov, M. V. Velasco 6/30/2026

Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures

Data-driven probabilistic framework using Gibbs measures on hierarchical structures for energy-based learning.

Ax Byeong Hoon Yoon 6/30/2026

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

Neural Subspace Reallocation reframes continual learning as retrieval-based memory management over LoRA subspaces.

Ax Ayan Pendharkar 6/30/2026

Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study

Study showing JEPA-style predictive objectives discard exogenous control-relevant features in learned representations.

Ax Jun Wang, Quoc Phong Nguyen, Julien Monteil, Vu Nguyen 6/30/2026

Online Data Selection for Instruction Tuning via Gaussian Processes

GAIA framework for global online data selection in LLM instruction tuning via Gaussian processes.

Ax Illia Makarov, Mykola Glybovets 6/30/2026

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

Query-aware spreading activation method for multi-hop retrieval over knowledge graphs in Graph RAG systems.

Ax Sura Alhanouti, G\"uzin Bayraksan, Parinaz Naghizadeh 6/30/2026

Robust Strategic Classification under Decision-Dependent Cost Uncertainty

ML research on robust strategic classification when agents manipulate inputs under cost uncertainty.

Ax Dario Fenoglio, Daniil Kirilenko, Martin Gjoreski, Marc Langheinrich 6/30/2026

Federated Learning with Energy-Based Structured Probabilistic Inference

Federated learning framework using CRFs to optimize client aggregation weights with heterogeneous data.

Ax Matthias Blaschke, Daniel Kienzle, Zsuzsanna Koczor-Benda, Julian Lorenz, Rainer Lienhart, Fabian Pauly 6/30/2026

Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark

NMO benchmark for generative molecular design beyond drug discovery, addressing domain transferability in ML.

Ax Marcelina Marjankowska, Valerio Modugno, Paolo Barucca 6/30/2026

Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization

Analysis of neural network training dynamics by studying how Hessian eigenvectors evolve and affect learning trajectories.

Ax Maximilian Bloor, Liyuan Xu, Hrvoje Stojic, Victor Picheny 6/30/2026

B3O: Scalable Boltzmann Batch Bayesian Optimization

Scalable batch Bayesian optimization framework using Boltzmann distribution sampling for parallel simulation workflows.

Ax Feifan Wang 6/30/2026

Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

Unsupervised community detection algorithm using discrete Forman-Ricci curvature for heterophilic graphs via sheaf diffusion.

Ax Boshko Koloski, Xiangjian Jiang, Senja Pollak, Bla\v{z} \v{S}krlj, Mateja Jamnik, Nikola Simidjievski 6/30/2026

KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models

Knowledge-informed fine-tuning of tabular foundation models using knowledge graphs for improved performance in niche domains with scarce data.

Ax Aaryam Sharma 6/30/2026

When Is a Draft Accepted? A Theory of Acceptance in Speculative Decoding

Theoretical analysis of token acceptance conditions in speculative decoding with greedy decoding and tree-based candidates for practical LLM acceleration.

Ax Bertram Taetz, Hugo Albuquerque Cosme da Silva, Gabriele Bleser-Taetz 6/30/2026

Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation

Methods using LoRA variants for continual learning in motion-language agents handling both motion-to-text and text-to-motion without catastrophic forgetting.

Ax Yousuf Moiz Ali, Jaroslaw E. Prilepsky, Jo\~ao Pedro, Sasipim Srivallapanondh, Antonio Napoli, Sergei K. Turitsyn, Pedro Freire 6/30/2026

Hybrid Active-Online Learning Framework for Label-Efficient Concept Drift Adaptation in Optical Network Failure Detection

Hybrid active-online learning framework for optical network failure detection adapting to concept drift with margin-based selective labeling.

Ax Marek Polewczyk, Maximilian Schambach, Marco Spinaci, Sam Thelin, Johannes H\"ohne 6/30/2026

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

Encoder-decoder architecture for in-context learning on tabular data producing target-agnostic row embeddings reusable across diverse downstream tasks.

Ax Haisen Luo, Yiwei Liu, Haoning Wang, Dan Liu, Junxi Yin, Haotian Wang, Lei Zhang, Xiaoyu Tian, Shuaiting Chen, Yuansheng Song, Baoyan Guo, Xiongfei Yan, Bolan Yang, Chengwei Liu, Ming Cui, Jiong Chen 6/30/2026

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

Self-distillation method for LLM reasoning that routes training by problem difficulty and maintains success buffer for stable improvement without external supervision.

Ax Kuangpu Guo, Qingyan Zheng, Jian Liang, Yongcan Yu, Zilei Wang, Ran He, Tieniu Tan 6/30/2026

On the Vulnerability of Parameter-Level Defenses to Model Merging

Analysis showing parameter-level defenses against model merging are vulnerable due to small task vector magnitudes enabling reconstruction attacks.

Ax Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu 6/30/2026

FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

Method for aligning generative flow models via online RL that addresses trajectory likelihood tractability and training-inference inconsistencies.

← Newer 4301–4350 of 40516 Older →