GitHub 新星
10 条
arXiv 论文
10 条
-
1
AI for Science with GPT-6 Astra: Thermal Design and Electrothermal Analysis of 2D CFET
Thermal optimization of 2D CFET inverters requires testing structural proposals against their electrical costs. We examine these research tasks using an AI agent workflow within a supplied electrotherMin-Hui Kim, Khushi Sharma, Sarah Zhang
-
2
Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement
Vision-language-action (VLA) systems already bring together two valuable resources for robot learning: rich visual representations and demonstrations of successful task execution. Intrinsic Robot RewaTobias Schaffer, Mohab Elkhayat, Daniela Nicklas
-
3
Finding Common Mistakes In Modelling With Mathematical Formalisms Using LLMs
Modelling with mathematical formalisms like logical formulas, mathematical equations, or regular expressions is an important yet challenging task for students of computer science and other STEM discipLilian Killich, Marko Schmellenkamp, Fabian Vehlken
-
4
Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We sDushyant Rajput
-
5
Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics
Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and tool-using agents stay unreliable: even frontierBaibek Davletiyarov, Junaid Ahmed Khan, Andrea Bartolini
-
6
High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics
The purpose of this paper is the identification of high-fidelity digital twin data models from numerical code outputs by non-intrusive techniques (i.e., not requiring Galerkin projection of the governDiana A. Bistrian
-
7
Semi-Supervised Learning-Based Genetic Biomarkers Dataset for Multiple-Stage Hepatocellular Carcinoma Prediction
Liver cancer is a complex disease responsible for a high number of deaths across the globe each year, making automated solutions for liver cancer classification urgent. The most common form of liver cAhmed Ammar Kubba, Manar Abu Talib, Jibran Sualeh Muhammad
-
8
Scaling-Score Conformal Prediction for Multi-Target Regression
Multi-target regression requires a model to simultaneously predict several related outputs. Conformal prediction provides distribution-free, finite-sample marginal coverage guarantees, but extending tSylvain Rousseau, Soundouss Messoudi
-
9
Optimization over covariance matrices with a parameterized metric
The choice of Riemannian metric can strongly influence the convergence of gradient-based optimization over covariance matrices. Euclidean, Bures-Wasserstein and affine-invariant metrics are common choYibang Li, Bamdev Mishra, Pratik Jawanpuria
-
10
Interactive Memory Learning for Long-Term Conversations
Recent advancements in large language models have significantly enhanced the capabilities of agents in modeling long-term conversations. Despite these successes, existing approaches typically adopt aCai Ke, Jiangyue Yan, Han Zhang
Hacker News
10 条
- 1 Show HN: An e-ink frame that hears birds and draws them as 1800s illustrations
- 2 Introducing System One Models and Jev
- 3 A single firm is behind OpenAI, Anthropic, and Meta hacking scandals
- 4 US confirms for first time it has deployed space weapons
- 5 Suspected sabotage causes major Netherlands rail disruption
- 6 An Update on Wayback Machine Access
- 7 Let's make quality the norm again
- 8 Gemini 3.8 Live and 3.8 Live Extended Thinking
- 9 Show HN: Capsule – Single-file web apps that save their data into SQLite
- 10 Most people prefer traditional architecture