GPUs, training clusters, MLOps, and deployment
UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...
![[2603.10047] Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.10047: Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination ...
Abstract page for arXiv paper 2512.18388: Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creatio...
This study evaluates the effectiveness of large language models (LLMs) in generating subject lines for mental health counseling emails, h...
The paper presents Inverse-distilled Diffusion Language Models (IDLM), a method that significantly accelerates inference in text generati...
This paper explores iterative feedback loops in image generative models, introducing the concept of neural resonance and its implications...
This paper introduces the Active Data Reconstruction Attack (ADRA), a novel approach to detect language model training data by leveraging...
This paper investigates the complexity of training deep neural networks under a realistic bit-level model, contrasting it with traditiona...
The paper introduces CausalFlip, a benchmark for evaluating large language models' (LLMs) causal reasoning capabilities, emphasizing the ...
This article presents findings on the latent introspection abilities of the Qwen 32B model, showing its capacity to detect prior concept ...
The paper presents LoMime, a novel framework for membership inference attacks that operates efficiently under label-only conditions, sign...
The paper introduces Semi-Local Differential Privacy (SLDP), a framework that enhances privacy-preserving analytics by decoupling privacy...
The paper introduces Ada-RS, an adaptive rejection sampling framework aimed at enhancing selective thinking in large language models (LLM...
This paper presents a novel approach to stabilize low-precision training in transformer models by deriving rank-aware spectral bounds on ...
The paper presents ComplLLM, a framework for fine-tuning large language models (LLMs) to enhance decision-making by utilizing complementa...
The paper explores the Bayesian Lottery Ticket Hypothesis, demonstrating that sparse subnetworks in Bayesian neural networks can achieve ...
This paper presents a novel framework, Latent Dirichlet-Tree Allocation (LDTA), which enhances the traditional Latent Dirichlet Allocatio...
This article explores the integration of artificial intelligence with modeling and simulation in digital twins, highlighting their roles ...
The paper introduces Prior Aware Memorization, a new metric for distinguishing genuine memorization from generalization in large language...
The paper presents Potara, a framework for federated personalization that merges general and personalized models, improving efficiency an...
The paper presents K-Search, a novel framework for optimizing GPU kernels using a co-evolving intrinsic world model, significantly improv...
The paper presents InfoNoise, a data-adaptive noise scheduling method for diffusion training, enhancing efficiency and performance by uti...
The paper presents ARTIST, a novel approach to time series reasoning that utilizes adaptive segment selection to improve accuracy in answ...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime