arXiv:2602.02250v2 Announce Type: replace-cross Abstract: Kullback-Leibler (KL) divergence regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise regimes. Using a unified information-geometric framework, we introduce KL analogs by replacing the…
arXiv:2606.00144v1 Announce Type: new Abstract: Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple tokens that a verifier validates in parallel. In resource-constrained deployments, the drafter uses a sparse KV cache to limit peak GPU memory…
arXiv:2606.00136v1 Announce Type: new Abstract: The proliferation of adversarial synthetic content, accelerated by Generative AI (GenAI) is rendering traditional reactive detection methods ineffective. This survey synthesizes emerging research to demonstrate a paradigm shift toward the proactive detection of emerging inauthentic…
arXiv:2602.04861v2 Announce Type: replace Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard energy and force regression evaluations can miss.…
arXiv:2606.00169v1 Announce Type: new Abstract: Increased competition and the growing similarity of products and services offered by retailers have lowered the barriers for customers to switch to competitors. Accurate churn prediction can be a valuable tool for driving effective personalized…
arXiv:2605.16446v2 Announce Type: replace Abstract: Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees. We identify a structural conflict in tabular fair SSL through a diagnostic stress test: under confidence-gated…
arXiv:2412.19419v2 Announce Type: replace Abstract: Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive…
arXiv:2606.00147v1 Announce Type: new Abstract: Domain-specific supervised fine-tuning (SFT) often improves in-domain performance at the cost of degrading a model’s general capabilities. We view this degradation through two practical gaps in domain SFT: a supervision-compatibility gap, where domain targets differ…
arXiv:2606.00140v1 Announce Type: new Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure has emerged as a…
arXiv:2606.00151v1 Announce Type: new Abstract: In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this…
