arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Jul 7
The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs
arXiv:2607. 02587v1 Announce Type: cross Abstract: Model cards quote trust-benchmark scores without recording when they were measured, and the same number is routinely carried across successive checkpoints of one release line as if the model behind it had not shifted.
arXiv Machine Learning
Jul 7
Routing Anonymity and Identifiability of Noisy Quantum Hardware
arXiv:2607. 05281v1 Announce Type: cross Abstract: Present-day quantum computing is cloud-based, where a user submits a circuit to a service provider's proprietary backend hardware.
arXiv Machine Learning
Jul 7
How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise
arXiv:2607. 03436v1 Announce Type: new Abstract: Routing among large language models (LLMs) promises better quality at lower cost, motivated by the reported gap between learned routers and a per-instance oracle.
arXiv Machine Learning
Jul 7
Geometry-Aware Bayesian Quantification via Compositional Data Analysis
arXiv:2607. 04977v1 Announce Type: new Abstract: Accurately estimating the unknown target label distribution is the critical first step for adapting to label shift.
arXiv Machine Learning
Jul 7
FedFFT: Taming Client Drift in Federated SAM via Spectral Perturbation Filtering
arXiv:2607. 04170v1 Announce Type: new Abstract: Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to client drift, poor generalization, and sharp minima compared to centralized training.
arXiv AI
Jul 7
JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode
arXiv:2607. 02825v1 Announce Type: cross Abstract: We release \textsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection.
arXiv AI
Jul 7
Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation
arXiv:2607. 03007v1 Announce Type: cross Abstract: Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding.
arXiv AI
Jul 7
A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving
arXiv:2509. 08269v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly integrated with evolutionary computation to support optimization tasks.
arXiv Machine Learning
Jul 7
Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics
arXiv:2603. 07108v2 Announce Type: replace-cross Abstract: Accurate and reliable forecasting of epidemic incidences is critical for public health preparedness, yet it remains a challenging task due to complex nonlinear temporal dependencies and heterogeneous spatial interactions.
arXiv Machine Learning
Jul 7
Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning
arXiv:2509. 22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data.
arXiv AI
Jul 7
Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
arXiv:2508. 04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images.
arXiv AI
Jul 7
SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints
arXiv:2607. 05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negotiate with services.
arXiv AI
Jul 7
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
arXiv:2607. 03013v1 Announce Type: cross Abstract: Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines, which degrades visual quality and affects downstream vision tasks.
arXiv AI
Jul 7
Enhanced Feature Extraction for IoT Network Intrusion Detection Using GNNs and KAN
arXiv:2607. 02981v1 Announce Type: cross Abstract: Recent advancements in the Internet of Things (IoT) emphasize the urgent need for advanced network security, as IoT networks feature dynamic topologies, imbalanced traffic, and complex attack patterns.
arXiv AI
Jul 7
Spectral Rewiring for Exploration, Purification, and Model Merging
arXiv:2607. 03065v1 Announce Type: cross Abstract: Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed reasoning performance, often reflected by premature saturation of test-time scaling, and interference when consolidating multiple capabilities through multi-domain training or model merging.
arXiv AI
Jul 7
Correlation-Weighted Multi-Reward Optimization for Compositional Generation
arXiv:2603. 18528v2 Announce Type: replace Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge.
arXiv AI
Jul 7
Towards Generalizable Deepfake Image Detection with Vision Transformers
arXiv:2604. 17376v2 Announce Type: replace-cross Abstract: In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods.
arXiv AI
Jul 7
Out-of-Distribution Generalization of Risk Aversion in Language Models
arXiv:2607. 02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned.
arXiv AI
Jul 7
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
arXiv:2508. 12116v2 Announce Type: replace-cross Abstract: As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge.