arXiv AI
Jul 7
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
arXiv:2607. 04738v1 Announce Type: cross Abstract: Reconstructing population dynamics is a central problem in the physical and data sciences.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 7
HamQASBench: A Hamiltonian-Informed Diagnostic Benchmark for Evaluating Quantum Architecture Search
arXiv:2607. 04845v1 Announce Type: cross Abstract: Quantum Architecture Search (QAS) automates the design of parameterized quantum circuits for variational quantum algorithms, yet existing benchmarks organize instances by molecular identity or qubit count -- criteria agnostic to Hamiltonian structure -- and rely solely on energy accuracy, which cannot detect structural failures such as over-parameterization on near-product ground states.
arXiv AI
Jul 7
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
arXiv:2601. 22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data.
arXiv AI
Jul 7
RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba for Few-Shot Brain Tumor Segmentation
arXiv:2607. 05035v1 Announce Type: cross Abstract: Few-shot brain tumor segmentation remains challenging due to noisy support masks, inter-patient variations between support and query images, and the lack of pixel-wise confidence estimation.
arXiv Machine Learning
Jul 7
VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
arXiv:2410. 00296v2 Announce Type: replace Abstract: Vision-language Models (VLMs) are essential for contextual understanding of both visual and textual information.
arXiv AI
Jul 7
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
arXiv:2607. 05189v1 Announce Type: cross Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution.
arXiv AI
Jul 7
Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks
arXiv:2503. 10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions.
arXiv AI
Jul 7
Verifier-free Test-Time Sampling for Vision-Language-Action Models
arXiv:2510. 05681v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control.
arXiv AI
Jul 7
Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
arXiv:2604. 16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP).
arXiv AI
Jul 7
StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model
arXiv:2604. 19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications.
arXiv AI
Jul 7
CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
arXiv:2604. 21241v2 Announce Type: replace-cross Abstract: Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly through latent features.
arXiv AI
Jul 7
Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity
arXiv:2604. 24827v2 Announce Type: replace-cross Abstract: Closed-source frontier labs do not disclose parameter counts.
arXiv AI
Jul 7
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
arXiv:2605. 06142v2 Announce Type: replace-cross Abstract: When people recount personal memories, they often refer to people, places, and events indirectly, relying on con-textual cues rather than explicit names.
arXiv Machine Learning
Jul 7
Exploring Convolutional Neural Processes for Weather Downscaling
arXiv:2607. 04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularly in mountainous regions where temperature can vary by several degrees over short distances.
arXiv Machine Learning
Jul 7
SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
arXiv:2607. 04189v1 Announce Type: new Abstract: Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global convergence.
arXiv Machine Learning
Jul 7
MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula
arXiv:2607. 04774v1 Announce Type: new Abstract: Untargeted tandem mass spectrometry (MS/MS) detects thousands of small molecules per biological sample, yet most go unidentified because they are absent from spectral libraries.
arXiv Machine Learning
Jul 7
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
arXiv:2607. 05252v1 Announce Type: new Abstract: Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference.
arXiv Machine Learning
Jul 7
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
arXiv:2607. 05271v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) encounter ill-posed optimization, loss competition, and parameter compensation in partial differential equation (PDE) inverse problems.
arXiv Machine Learning
Jul 7
QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs
arXiv:2602. 20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation.
arXiv Machine Learning
Jul 7
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
arXiv:2605. 08678v3 Announce Type: replace Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes.