Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of rollouts to every task and trajectory state, even though some rollouts provide much more useful…
We investigate the transferability of Earth weather foundation models to planetary atmospheres by adapting the GraphCast graph neural weather forecasting model to Mars. While GraphCast achieves state-of-the-art performance for terrestrial forecasting, its applicability to…
Google is making some significant AI leadership changes, including a major shift for Google DeepMind leader Demis Hassabis. Hassabis will become the chair of Google DeepMind and the chief scientist at Alphabet, CEO Sundar Pichai announced on Wednesday. Hassabis will continue to…
Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as critical. Determinism, reproducibility, and auditability are engineering requirements rather than optional extras. STLF is no…
We show that tiny transformers can profitably employ a simple form of Chain of Thought, which we call protoreasoning, allowing us to study step-by-step reasoning on ~1M-parameter models and opening up opportunities for much more detailed experimentation and analysis than is…
We propose a deep learning framework for image restoration from images degraded by both multiplicative Gamma noise and blur. Unlike conventional deep equilibrium (DEQ) models that rely on implicit neural regularization, the proposed method learns an explicit and interpretable…
ParVL framework scales multimodal LLMs via parallel computation reuse between ViT and LLM, enabling task-specific optimization without fixed component allocation.
Physics-Flavored Neural Network automates kinetic phenotyping of engineered skeletal muscle tissues, replacing simplistic peak-force metrics.
KV cache transfer enables prefill reuse across different-sized LLM family models via closed-form linear mapping.
ContinualSkillBench evaluates whether LLM agents can continually acquire and reuse skills across 500 interconnected task domains.
Source-Conditioned Description-Length Gain detects LLM-generated plagiarism via probabilistic compression, distinguishing source reuse from similarity.
Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data... Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent…
Computing actual causes for neural network predictions using Halpern-Pearl causal models and Boolean SCMs to improve explainability under structured input dependencies.
Early-epoch telemetry from training runs predicts final test accuracy and training failure without cross-run reference.
AutoSND uses tree search to discover heuristic policies for network dismantling by converting LLM execution feedback into structural guidance.
MuEvo uses LLMs to evolve multi-component heuristic ensembles for combinatorial optimization, addressing inter-component dependencies.
Hardware-aware multi-objective optimization for designing energy-efficient DNNs on microcontrollers with intermittent power availability.
Gas Town was intended to be reusable, but I only ever wound up using it to build itself. Gas Town fell apart at the seams with Opus 4.7. Up through 4.6 it was working brilliantly. With 4.7 we saw the introduction of the "just two more things" tic, which prevented Opus from ever…
Framework for teaching AI in power systems emphasizing engineering-grounded workflows over black-box LLM usage; addresses gap in reusable educational material.
Pseudorandom streams in diffusion models act as learnable inputs; predictable orbits from finite-precision hardware affect training and generation quality.
First systematic benchmark of Sheaf Neural Networks on inductive tasks, extending prior transductive-only evaluations across three diffusion mechanisms.
The EU made some AI labels that companies can use instead of designing their own. | Image: The European Commission / The Verge The European Union has ushered in some additional rules that aim to make it easier for people to identify chatbots and AI deepfakes online. The new…
Storage is an active part of every agentic AI workflow. As agents retrieve enterprise knowledge, access persistent memory, reuse key-value (KV) cache data,... Storage is an active part of every agentic AI workflow. As agents retrieve enterprise knowledge, access persistent…
KING: Graph neural network for cross-embodiment kinematic models in legged and wheeled robots via proprioceptive geometry learning.
FDR-controlled feature selection framework for grouped features in sequential and neural models using block-level mirror statistics.
Neuro-symbolic governance framework for verifiable AI agents in decentralized digital twin ecosystems with semantic profile layers.
Freeze-then-select method decouples PDE discovery from neural optimization via structured field adapters and Stability-Validated Weak Selection for sparse observations.
Neurosymbolic pipeline combines foundation models with Bayesian Networks for automated Alzheimer's diagnosis from speech.
Transfer learning with GNNs predicts formation energy and HOMO-LUMO gaps in high-entropy perovskite oxides.
High-entropy parameter solutions mitigate catastrophic forgetting in neural networks via Boltzmann entropy robustness.