arXiv:2607. 24074v1 Announce Type: new Abstract: We present MiSS, a black-box, query-based framework for explaining 3D point cloud classifiers through perturbation-relative sufficiency reasoning.
arXiv:2606. 29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups.
arXiv:2510. 17543v3 Announce Type: replace Abstract: Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging.
arXiv:2606. 09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing.
Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups. We introduce Self-Organized Conformal Prediction (SOCP), a calibration scheme that discovers input-space groups with a Self-Organizing Map (SOM) and, at test time, draws a local calibration buffer from the query's best-matching unit (BMU) cell or a fixed grid neighborhood.
arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.
arXiv:2505. 08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety.
arXiv:2603. 14198v3 Announce Type: replace-cross Abstract: Deploying trustworthy AI systems requires principled uncertainty quantification.
arXiv:2606. 26454v1 Announce Type: new Abstract: Sphere neural networks have achieved symbolic level syllogistic reasoning without training data, raising the question of where the limit of the scaling law for logical reasoning lies, i.
arXiv:2607. 06407v1 Announce Type: new Abstract: The XAI community has studied a wide range of queries and scores for explaining predictions of ML models.
arXiv:2608. 08826v1 Announce Type: new Abstract: Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may have to answer queries whose coordinate and inspection time are chosen only after the data are seen.
arXiv:2606. 16140v1 Announce Type: new Abstract: This technical report introduces VibeThinker-3B, a compact dense model with 3B parameters developed to investigate how far verifiable reasoning can be pushed within a strictly small-model regime.
arXiv:2604. 24827v2 Announce Type: replace-cross Abstract: Closed-source frontier labs do not disclose parameter counts.