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.
The paper argues that partition-level scores used in decomposed algorithm selection overestimate what a deployable selector can achieve. It introduces the deployment‑fidelity gap, G(R), which measures the difference between partition‑level and end‑to‑end utility, and derives conditions under which a partition choice is truly deployment‑optimal. Experiments on five public benchmarks show that every decomposed pipeline has a positive gap, with some cases where the partition advantage disappears or reverses when evaluated end‑to‑end, highlighting the need to report both partition and end‑to‑end scores.
arXiv:2609.17413v1 Announce Type: new Abstract: This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring compl...
The paper examines three recent studies that highlight distinct reliability issues in large language models (LLMs). Each study points to a missing capability—whether a tool‑reliability representation, safe generation behavior, or a consistent‑reasoning function—yet all converge on the need for calibrated abstention. The authors argue that current benchmarks fail to reward abstention, preventing the development of this function, and propose four evaluation changes to address the gap.