arXiv AI
Jul 21
Thermodynamic Limits of Physical Intelligence
arXiv:2602. 05463v2 Announce Type: replace-cross Abstract: Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption.
Watts-per-Intelligence Part II: Algorithmic Catalysis
arXiv:2604. 20897v2 Announce Type: replace-cross Abstract: We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints.
Related stories
arXiv AI
Jun 8
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
arXiv:2606. 05050v1 Announce Type: cross Abstract: Theoretical heterogeneous catalysis promises rapid catalyst discovery, yet computational and machine-learning predictions often deviate from experiment and stay confined to narrow material families, for want of a faithful, condition-aware catalytic simulator.
arXiv AI
Jul 21
SEER: Supervised Learning to Control Energetic Reasoning
arXiv:2607. 16523v1 Announce Type: new Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation.
arXiv AI
Jul 10
A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
arXiv:2510. 22052v2 Announce Type: replace Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictate the prosperity and might of the world's economies.
arXiv AI
Jun 17
Decidable By Construction: Design-Time Verification for Trustworthy AI
arXiv:2603. 25414v4 Announce Type: replace-cross Abstract: A prevailing assumption in machine learning is that model correctness must be enforced after the fact.
arXiv Machine Learning
Jun 25
Agentic evolution of physically constrained foundation models
arXiv:2606. 25532v1 Announce Type: cross Abstract: Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs.
arXiv Machine Learning
Jul 27
Complexity Bounds and Approaches to Learning Projected Gradient Descent Solver Iterates
arXiv:2607. 22467v1 Announce Type: new Abstract: Data scarcity poses a fundamental challenge in training generative models to produce initial guesses for parametric optimization problems that are otherwise numerically expensive to solve.
arXiv AI
Jul 21
Structure-Induced Information for Rerooting Levin Tree Search
arXiv:2605. 30664v2 Announce Type: replace Abstract: Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability.
arXiv AI
Jun 9
An Alternative Trajectory for Generative AI
arXiv:2603. 14147v2 Announce Type: replace Abstract: The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability.
arXiv AI
Jun 19
Thermodynamic Measure of Intelligence
arXiv:2606. 20231v1 Announce Type: new Abstract: Can intelligence be measured?
arXiv AI
Aug 5
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
arXiv:2608. 03461v1 Announce Type: new Abstract: Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals, and a synthesizer generates programs conditioned on them.
arXiv Machine Learning
Jun 17
Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining
arXiv:2606. 17445v1 Announce Type: new Abstract: Inverse design of heterogeneous catalysts remains challenging because catalyst surfaces exhibit substantial structural complexity with coupled surface-adsorbate interactions across a vast chemical space that is difficult to explore efficiently through conventional screening alone.