arXiv Machine Learning
Jul 21
ExMAG: Learning of Maximally Ancestral Graphs
arXiv:2503. 08245v4 Announce Type: replace Abstract: In mixed graphs, there are both directed and bidirected edges.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 21
GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
arXiv:2607. 16283v1 Announce Type: cross Abstract: The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before.
arXiv AI
Jul 21
InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
arXiv:2510. 27497v2 Announce Type: replace-cross Abstract: Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored.
arXiv AI
Jul 21
SyriSign: A Parallel Corpus for Arabic Text to Syrian Arabic Sign Language Translation
arXiv:2603. 29219v2 Announce Type: replace-cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community.
arXiv AI
Jul 21
L2GTX: From Local to Global Time Series Explanations
arXiv:2603. 13065v2 Announce Type: replace-cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging.
arXiv AI
Jul 21
PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization
arXiv:2607. 16206v1 Announce Type: new Abstract: This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the "Invisible Shackles" of mode collapse in Large Language Model (LLM) fine-tuning.
arXiv AI
Jul 21
SCA: Segment-Wise CoT Compression with Answer Alignment
arXiv:2603. 07598v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning improves problem solving, but long think traces increase inference cost.
arXiv AI
Jul 21
Structure-Induced Information for Rerooting Levin Tree Search
arXiv:2605. 30664v2 Announce Type: replace Abstract: Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability.
arXiv AI
Jul 21
Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions
arXiv:2512. 24679v2 Announce Type: replace Abstract: Intelligent fault diagnosis has become an indispensable technique for ensuring machinery reliability.
arXiv AI
Jul 21
Thermodynamic Limits of Physical Intelligence
arXiv:2602. 05463v2 Announce Type: replace-cross Abstract: Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption.
arXiv AI
Jul 21
CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
arXiv Machine Learning
Jul 21
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
arXiv:2607. 17524v1 Announce Type: cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.
arXiv AI
Jul 21
Generative Ontology Induction: Domain-Agnostic Schema Discovery from Document Corpora Using Large Language Models
arXiv:2607. 16201v1 Announce Type: new Abstract: Ontology engineering remains a critical bottleneck in knowledge-intensive AI systems.
arXiv AI
Jul 21
Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA
arXiv:2607. 17834v1 Announce Type: cross Abstract: Endoscopic visual question answering (VQA) increasingly asks complex questions that combine several endoscopic answer components rather than isolated factual queries.
arXiv AI
Jul 21
CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning
arXiv:2607. 17568v1 Announce Type: cross Abstract: Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups.
arXiv AI
Jul 21
FST.ai 2.5: Explainable and Uncertainty-Aware AI for Olympic and Para-Taekwondo Decision Support, Athlete Digital Twins, and Federation-Scale Analytics
arXiv:2607. 16597v1 Announce Type: new Abstract: The rapid digitalisation of elite sport has created new opportunities for integrating artificial intelligence (AI), performance analytics, and decision-support systems into athlete development and competition management.
arXiv AI
Jul 21
OFD-Net: Teacher-Free Reliable Semi-supervised Medical Image Segmentation with Orthogonal Feature Disentanglement Net of Foreground-Background
arXiv:2607. 16705v1 Announce Type: cross Abstract: Semi-supervised learning (SSL) is an effective solution for medical image segmentation with limited annotations.
arXiv Machine Learning
Jul 21
Kernel Regression with Tensor Trains and Hadamard Overparameterization
arXiv:2607. 17390v1 Announce Type: cross Abstract: Kernel regression with tensor trains and Hadamard overparameterization (KReTTaH) is introduced as a training-data-free, interpretable, and nonparametric framework for multi-way data imputation.
arXiv AI
Jul 21
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
arXiv:2605. 18920v2 Announce Type: replace-cross Abstract: Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers.
arXiv AI
Jul 21
A small language model detects behavioural faithfulness gaps that frontier judges and human raters miss
arXiv:2607. 09306v2 Announce Type: replace-cross Abstract: Whether a language model behaves as it claims is a judgement on which independent human raters cannot agree (Fleiss kappa = 0.