·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆
Tag

#machine learning

32 articles tagged #machine learning

arxivJul 30bullish

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering

arXiv:2607.25090v1 Announce Type: new Abstract: Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feedback-driven environment interactions. Developing and training a monolithic agent for such tasks is f

MAQWO44 models · +1#machine learning#artificial intelligence#hierarchical frameworksRead on arxiv →
arxivJul 27

Interpretable Anomaly and Drift Detection with Gaussian Mixture Models

arXiv:2607.16811v2 Announce Type: replace Abstract: We revisit Gaussian Mixture Models (GMMs) as a lightweight, interpretable tool for anomaly detection and, in particular, for detecting distributional drift in data streams. We make three practical choices explicit and evaluate them on seven public

GAISLO7 models · +4#anomaly detection#machine learning#interpretable modelsRead on arxiv →
arxivJul 18bullish

PhasorFlow: A Python Library for Unit Circle Based Computing

arXiv:2603.15886v4 Announce Type: replace-cross Abstract: We present PhasorFlow, an open-source Python library for computing on the $S^1$ unit circle. Inputs are encoded as complex phasors $z=e^{i\phi}$ on the $N$-torus ($\mathbb{T}^N$); as computation proceeds through unitary wave-interference gate

PHVAPH4 models · +1#open-source#machine learning#artificial intelligenceRead on arxiv →
arxivJul 16bullish

Parallel gradient boosting for flexible estimation of conditional distributions

arXiv:2607.13550v1 Announce Type: cross Abstract: Boosting is one of the most successful learning techniques for standard classification and regression tasks. Its extension to multi-output prediction problems has found an increasing number of applications in recent years. Among them is the predictio

XGPA2 models#machine learning#boosting#regressionRead on arxiv →
arxivJul 14

Interpreting Latent CoT Reasoning as Dynamical Systems

arXiv:2607.09698v1 Announce Type: new Abstract: Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent reas

COCOCO4 models · +1#interpretability#reasoning#dynamical systemsRead on arxiv →
arxivJul 10

Write-Protected Discrete Bottlenecks for Language-Grounded World Models: A Structural Limitation and Sufficient Fix

arXiv:2607.08312v1 Announce Type: new Abstract: How should language interface with a world model's discrete symbol system? The dominant paradigm -- end-to-end injection of LLM/VLM features into robot world models (RT-2, Octo, PaLM-E) -- implicitly assumes that language gradients can directly shape p

RTOCPA8 models · +5#machine learning#language models#world modelsRead on arxiv →
arxivJul 10bullish

Evaluating the Effect of Frame Rate in Sequence-Based Classification of Autism-Related Self-Stimulatory Hand Idiosyncrasies

arXiv:2607.07957v1 Announce Type: new Abstract: Autism spectrum disorder (ASD) affects over 75 million individuals worldwide, yet scalable computational methods for remote behavioral screening remain limited. This study addresses two complementary challenges in automated detection of autism-related

LSGRCN4 models · +1#autism#machine learning#computer visionRead on arxiv →
arxivJul 10bullish

Classifier Chain-based Pathological Test Recommendation

arXiv:2607.08299v1 Announce Type: new Abstract: Accurate and timely diagnoses are essential for quality patient care. However, delayed recommendation of diagnostic tests and physicians' subjective interpretations can hinder effective care. This study introduces a pathological test recommendation sys

LODERA6 models · +3#machine learning#diagnosis#healthcareRead on arxiv →
arxivJun 26

Learning State-Tracking from Code Using Linear RNNs

arXiv:2602.14814v3 Announce Type: replace-cross Abstract: Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear). However, these are often sequ

TRRN2 models#sequence models#state tracking#machine learningRead on arxiv →
arxivJun 24

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment

arXiv:2606.24851v1 Announce Type: new Abstract: Fourier Neural Operators (FNO) learn solution operators of partial differential equations by parameterizing global convolutions in the complex Fourier domain. For real-valued PDE solutions, the complex FFT carries representational redundancy through co

FOHA2 models#machine learning#neural operators#partial differential equationsRead on arxiv →
arxivJun 16

Towards CONUS-Wide ML-Augmented Conceptually-Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics

arXiv:2510.02605v2 Announce Type: replace Abstract: While many modern studies are dedicated to ML-based large-sample hydrologic modeling, these efforts have not necessarily translated into predictive improvements that are grounded in enhanced physical-conceptual understanding. Here, we report on a C

MALO2 models#machine learning#hydrology#modelingRead on arxiv →
arxivJun 15bullish

Exact Linear Attention

arXiv:2605.18848v4 Announce Type: replace-cross Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation erro

TRYO2 models#machine learning#transformer#attention mechanismsRead on arxiv →
arxivJun 11

On the Study of Biometric Spoofing Detection using Deep Learning

arXiv:2606.11505v1 Announce Type: cross Abstract: Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access. This research evaluates the effectiveness of

MODEIN4 models · +1#security#facial recognition#machine learningRead on arxiv →
arxivJun 10bullish

Operator Fusion for LLM Inference on the Tensix Architecture

arXiv:2606.09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy that enhances data locality. RMSNorm is fused with matrix multiplication in self-attention and in t

TRQWQW4 models · +1#machine learning#optimization#parallelismRead on arxiv →
arxivMay 29bullish

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

arXiv:2605.29843v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains highly sensitive to activation outliers and anisotropic weight curvature. Existing incoherence-base

LL1 model#quantization#machine learning#optimizationRead on arxiv →
arxivMay 28

Revisiting Metafeatures to Explain Model Differences on Tabular Data

arXiv:2605.28418v1 Announce Type: new Abstract: With the rise of tabular foundation models alongside traditional models still performing well on many tasks, choosing the right model for a tabular dataset remains difficult. We investigate whether dataset meta-features can explain performance gaps bet

TATA2 models#machine learning#benchmark#tabular dataRead on arxiv →
arxivMay 19

Fidelity Probes for Specification--Code Alignment

arXiv:2605.17246v1 Announce Type: cross Abstract: We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a candidate specification. The fraction of agreeing probes, which we call the fidelity, decomposes into

LLANDE7 models · +4#machine learning#artificial intelligence#benchmarkRead on arxiv →
arxivMay 15bearish

NodeSynth: Socially Aligned Synthetic Data for AI Evaluation

arXiv:2605.14381v1 Announce Type: cross Abstract: Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSyn

CLLLTA3 models#synthetic data#model evaluation#safetyRead on arxiv →
arxivMay 14bullish

Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers

arXiv:2605.13784v1 Announce Type: new Abstract: Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-

VLSGTE3 models#streaming#inference#optimizationRead on arxiv →
arxivMay 13

Constructive conditional normalizing flows

arXiv:2602.08606v3 Announce Type: replace-cross Abstract: Motivated by applications in conditional sampling, given a probability measure $\mu$ and a diffeomorphism $\phi$, we consider the problem of simultaneously approximating $\phi$ and the pushforward $\phi_{\#}\mu$ by means of the flow of a cont

PE1 model#optimization#machine learning#probabilityRead on arxiv →
arxivMay 11

A Rod Flow Model for Adam at the Edge of Stability

arXiv:2605.06821v1 Announce Type: cross Abstract: Cohen et al. (arXiv:2207.14484) observed that adaptive gradient methods such as Adam operate at the edge of stability. While there has been significant work on continuous-time modeling of gradient descent at the edge of stability, extending these mod

ADRMNA5 models · +2#optimization#machine learning#momentum methodsRead on arxiv →
arxivMay 5bullish

FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control

arXiv:2604.19021v2 Announce Type: replace Abstract: Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have demonstrated that the delta

GAKIFG4 models · +1#machine learning#attention mechanisms#optimizationRead on arxiv →
arxivMay 1bullish

Making Logic a First-Class Citizen in Generative ML for Networking

arXiv:2506.23964v3 Announce Type: replace-cross Abstract: Generative ML models are increasingly popular in networking for tasks such as telemetry imputation, prediction, and synthetic trace generation. Despite their capabilities, they suffer from two shortcomings: \emph{(i)} their output is often vi

GPDUZO4 models · +1#networking#machine learning#rule learningRead on arxiv →
arxivApr 30bullish

MARVIS: Modality Adaptive Reasoning over VISualizations

arXiv:2507.01544v2 Announce Type: replace Abstract: Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. Such models often achieve excellent performance, but lack flexibility. LLMs and VLMs offer versatilit

MAGE2 models#machine learning#predictive modeling#multimodal learningRead on arxiv →
arxivApr 28

Surface Sensitivity in Lean 4 Autoformalization

arXiv:2604.23135v1 Announce Type: new Abstract: Natural-language variation poses a key challenge in Lean autoformalization: semantically equivalent paraphrases of the same theorem statements can induce divergent formal outputs, yet it remains unclear whether this variation reflects semantic disagree

GPPRMI3 models#machine learning#autoformalization#natural language processingRead on arxiv →
arxivApr 27

Neural Recovery of Historical Lexical Structure in Bantu Languages from Modern Data

arXiv:2604.22730v1 Announce Type: cross Abstract: We investigate whether neural models trained exclusively on modern morphological data can recover cross-lingual lexical structure consistent with historical reconstruction. Using BantuMorph v7, a transformer over Bantu morphological paradigms, we ana

BAME2 models#machine learning#natural language processing#language reconstructionRead on arxiv →
arxivApr 24

Promoting Simple Agents: Ensemble Methods for Event-Log Prediction

arXiv:2604.21629v1 Announce Type: cross Abstract: We compare lightweight automata-based models (n-grams) with neural architectures (LSTM, Transformer) for next-activity prediction in streaming event logs. Experiments on synthetic patterns and five real-world process mining datasets show that n-grams

N-LSTR3 models#machine learning#ensemble methods#process miningRead on arxiv →
arxivApr 16

Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Study

arXiv:2604.13928v1 Announce Type: new Abstract: Industrial time-series data from real production environments exhibits substantially higher complexity than commonly used benchmark datasets, primarily due to heterogeneous, multi-stage operational processes. As a result, anomaly detection methods vali

ISTERE4 models · +1#anomaly detection#industrial time-series#autoencodersRead on arxiv →
arxivApr 13

Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study

arXiv:2510.22293v4 Announce Type: replace Abstract: Background: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects 30-40% of US adults and is the most common chronic liver disease. Although often asymptomatic, progression can lead to cirrhosis. The objective of the study was to

LARAXG5 models · +2#machine learning#healthcare#prediction modelRead on arxiv →
arxivApr 3

Semantic Interaction Information mediates compositional generalization in latent space

arXiv:2603.27134v2 Announce Type: replace Abstract: Are there still barriers to generalization once all relevant variables are known? We address this question via a framework that casts compositional generalization as a variational inference problem over latent variables with parametric interactions

REECFU4 models · +1#machine learning#generalization#reinforcement learningRead on arxiv →
arxivApr 3bullish

Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control

arXiv:2603.19136v2 Announce Type: replace Abstract: Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is

AUDUSO3 models#machine learning#stock market#predictionRead on arxiv →
arxivApr 2

Event Embedding of Protein Networks : Compositional Learning of Biological Function

arXiv:2604.00911v1 Announce Type: new Abstract: In this work, we study whether enforcing strict compositional structure in sequence embeddings yields meaningful geometric organization when applied to protein-protein interaction networks. Using Event2Vec, an additive sequence embedding model, we trai

EVWO2 models#protein-protein interaction networks#sequence embeddings#machine learningRead on arxiv →
HomeModelsNews