arXiv Machine Learning
Aug 4
CriPO: Enhancing Rubric-based RL via Self-Distillation
arXiv:2607. 18082v3 Announce Type: replace Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Aug 4
Learned, Relied Upon, or Necessary? Separating Checkpoint Dependence from Task-Level Value in Sheaf GNNs
arXiv:2607. 25387v2 Announce Type: replace Abstract: Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry.
arXiv Machine Learning
Aug 4
What EEG Foundation Models Encode: Dataset Identity and a Negative-Control Suite for Clinical Benchmarks
arXiv:2607. 24519v2 Announce Type: replace Abstract: Pretrained EEG foundation models are proposed for clinical decoding, but whether reported gains transfer across populations or survive negative controls is unclear.
arXiv Machine Learning
Aug 4
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
arXiv:2605. 18591v2 Announce Type: replace Abstract: Natural policy gradients improve optimization by accounting for the geometry of distribution space, but their practical use is limited by the cost of estimating and inverting the Fisher matrix.
arXiv Machine Learning
Aug 4
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
arXiv:2604. 03532v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult.
arXiv Machine Learning
Aug 4
Local-Time Riemannian Score Matching on the Quantum Pure-State Manifold
arXiv:2605. 03573v4 Announce Type: replace-cross Abstract: Score-based diffusion can be defined intrinsically on the manifold of quantum pure states, $\mathbb{CP}^{d-1}$ with the Fubini--Study metric, but no closed-form transition density is available, so the score must be supervised by a local-time teacher taken from the Euclidean limit of the diffusion in normal coordinates.
arXiv Machine Learning
Aug 4
Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
arXiv:2608. 00135v1 Announce Type: new Abstract: Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer vision benchmarks.
arXiv Machine Learning
Aug 4
Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
arXiv:2608. 00623v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains.
arXiv Machine Learning
Aug 4
Fast Discovery of Inclusion Dependencies with Desbordante
arXiv:2608. 02213v1 Announce Type: cross Abstract: Inclusion dependency is a relation between attributes of tables that indicates possible Primary Key-Foreign Key references.
arXiv Machine Learning
Aug 4
CoRe-GNN: Multilevel Message passing on Coarsened graphs
arXiv:2608. 02128v1 Announce Type: new Abstract: Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers.
arXiv Machine Learning
Aug 4
Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
arXiv Machine Learning
Aug 4
Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning
arXiv:2608. 00301v1 Announce Type: new Abstract: Error-penalized scoring rules ($+1$ for a correct answer, $-\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\ast=\lambda/(1+\lambda)$.
arXiv Machine Learning
Aug 4
RHEA: Reliability-Harmonized Reconstruction and Assignment for Robust Multimodal-Attributed Graph Clustering
arXiv:2608. 00621v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry heterogeneous attributes such as text and images over a relational structure, have become a fundamental substrate for label-free entity grouping tasks, including community discovery and product segmentation.
arXiv Machine Learning
Aug 4
HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning
arXiv:2608. 00491v1 Announce Type: new Abstract: Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data.
arXiv Machine Learning
Aug 4
Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models
arXiv:2608. 00019v1 Announce Type: new Abstract: Deploying large language models (LLMs) for operations research (OR) tasks remains challenging because correctness depends on a coherent modeling process, not merely a correct final answer.
arXiv Machine Learning
Aug 4
From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy
arXiv:2608. 00608v1 Announce Type: new Abstract: Visible and near-infrared (vis-NIR) and mid-infrared (MIR) spectroscopy enable rapid, cost-effective prediction of soil properties.
arXiv Machine Learning
Aug 4
Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling
arXiv:2608. 00732v1 Announce Type: new Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning.
arXiv Machine Learning
Aug 4
HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval
arXiv:2606. 21633v2 Announce Type: replace Abstract: The KV cache dominates GPU memory in long-context LLM serving, crowding out batch capacity and leaving GPU compute idle.
arXiv Machine Learning
Aug 4
Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA
arXiv:2607. 26052v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts $k$.
arXiv Machine Learning
Aug 4
LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins
arXiv:2608. 00406v1 Announce Type: cross Abstract: Accurate indoor localization is essential for emerging applications in robotic navigation and search and rescue.