· ai
How AI Documentation Tools Cut Onboarding Time by 80%
Developer onboarding is one of the most expensive bottlenecks in engineering organizations. The average company spends $954 per new hire on onboarding, with eng...
-
- · ai
[Paper] Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis
Gradually growing the depth of Transformers during training can not only reduce training cost but also lead to improved reasoning performance, as shown by MIDAS...
- · ai
[Paper] Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts
Understanding human personality is crucial for web applications such as personalized recommendation and mental health assessment. Existing studies on personalit...
- · ai
[Paper] Multicalibration for LLM-based Code Generation
As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represe...
- · ai
[Paper] Democratizing ML for Enterprise Security: A Self-Sustained Attack Detection Framework
Despite advancements in machine learning for security, rule-based detection remains prevalent in Security Operations Centers due to the resource intensiveness a...
- · ai
[Paper] Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?
Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN ...
- · ai
[Paper] MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidance
Document shadow removal is essential for enhancing the clarity of digitized documents. Preserving high-frequency details (e.g., text edges and lines) is critica...
- · ai
[Paper] A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where st...
- · ai
Launch HN: Mentat (YC F24) – Controlling LLMs with Runtime Intervention
Hi HN, I’m Cyril from CTGT. Today we’re launching Mentat https://docs.ctgt.ai/api-reference/endpoint/chat-completions, an API that gives developers deterministi...
- · ai
Launch HN: Mentat (YC S16) – Controlling LLMs with Runtime Intervention
Hi HN, I’m Cyril from CTGT. Today we’re launching Mentat https://api.ctgt.ai/v1/chat/completions, an API that gives developers deterministic control over LLM be...
- · ai
[Paper] Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
We propose a post-training method for lower-resource languages that preserves fluency of language models even when aligned by disfluent reward models. Preferenc...
- · ai
Google’s first AI glasses expected next year
Google is working on various types of AI-powered glasses — one model is designed for screen-free assistance, using built-in speakers, microphones, and cameras t...