技术雷达 · 2026-09-02

G GitHub 新星 10 条

A arXiv 论文 10 条

1 Constant Individual Regret in General Games cs.LGcs.GT
Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for individual regret retain a polylogarithmic dependence on the horizon. We remove this dependence for
Mingyang Liu, Gabriele Farina, Asuman Ozdaglar
2 SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies cs.ROcs.AI
Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that behavior into a reacti
Weiqi Wang, Zhi Li, Yudong Lei
3 Sharp Approximation Rates for Neural Networks with Affine Latent Parameterizations cs.LGstat.ML
Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture $Φ$ with $P_Φ$ parameter slots, we write $\boldsy
Shijun Zhang
4 Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification cs.SEcs.AIcs.CR
The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data-handling terms, sup
Yisen Xi
5 OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques cs.AI
Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recently, Large Language
Hamed Babaei Giglou, Sören Auer, Peio Popov
6 Implementing neural network mixed-effects models in Template Model Builder (TMB) stat.MLcs.LG
Neural network mixed-effects models (NMMs) have gained traction by combining the strong representation and predictive power of artificial neural networks with the capacity of mixed-effects modeling to
Nan Zheng, Hoi Yiu Cheung, Vibhu Sharma
7 On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions cs.LGcs.CCmath.PR
The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the form of conditional pro
Guy Emerson
8 When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning cs.AI
The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning dense and Mixture-of
Hamed Babaei Giglou, Sören Auer, Jennifer D'Souza
9 "Train classical, deploy quantum" requires rethinking generalization quant-phcs.LG
Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered one of the most prom
Snehal Raj, Natansh Mathur, Alejandro Perdomo-Ortiz
10 Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions cs.LG
Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is made cheaper. We stress
Ahmed El Kady, Aravind Narayanan, Rehana Noorani

H Hacker News 10 条