arXiv:2606.11258v1 Announce Type: new Abstract: Gradient-based inversion of reaction-diffusion systems is typically approached via surrogate models or physics-informed neural networks (PINNs), while the most direct route, backpropagation through the PDE’s structure itself, has largely been avoided. We pursue this direct…
arXiv:2606.08956v2 Announce Type: replace Abstract: Scientists have historically relied on mathematical models based on differential equations to relate system inputs — forces, fluxes, or heat sources — to outputs, such as displacement, velocity, concentration, and temperature. These models rely on…
arXiv:2606.11262v1 Announce Type: new Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates,…
arXiv:2512.11081v2 Announce Type: replace-cross Abstract: Feature and Interaction Importance (FII) methods are essential in supervised learning for assessing the relevance of input variables and their interactions in complex prediction models. In many domains, such as personalized medicine, local interpretations for…
arXiv:2606.11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode…
arXiv:2606.06527v3 Announce Type: replace-cross Abstract: Energy-efficient neural-network inference at the edge requires reducing arithmetic cost, memory traffic, computation energy, and storage overhead while maintaining acceptable accuracy. This paper presents an ablation-focused study of NVFP4 quantization for edge-efficient neural networks, with…
arXiv:2606.11267v1 Announce Type: new Abstract: Data leakage — contamination of a model with information unavailable at baseline — is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise. None operates on…
The “Sonar-MASt3R” combines sonar and visual data to create real-time 3D maps, even in cloudy water.
A new study shows people expect reciprocal generosity only in interactions with friends or others of equal social status.
arXiv:2601.00791v2 Announce Type: replace Abstract: Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and output-based heuristics are brittle. We show that valid mathematical reasoning induces a measurable, training-free spectral signature…
