🤖 Large Language Models - nate_dkz

Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model

🧠LLM Code

github.com··DEV

Can activation verbalizers surface an internal chain of thought?

💬Prompt Engineering

lesswrong.com·

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

🧠LLM Academic

arxiv.org·

If Claude Fable stops helping you, you’ll never know

🤖AI

simonwillison.net··Hacker News

Alignment Defends LLMs from Property Inference Attacks

🧠LLMs Academic

arxiv.org·

Tight Sample Complexity of Transformers

💬Prompt Engineering Academic

arxiv.org·

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

🧠LLMs Academic

arxiv.org·

Boris Cherny, Claude Code creator at Anthropic, says his personal workflow has shifted from manual prompting to building autonomous loops

💬Prompt Engineering News

digg.com·

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

🧠LLM Academic

arxiv.org·

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

🧠LLM Academic

arxiv.org·

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

🧠LLMs Academic

arxiv.org·

Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA

♊Gemini Academic

arxiv.org·

A Regret Minimization Framework on Preference Learning in Large Language Models

🧠LLM Academic

arxiv.org·

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

💬Prompt Engineering Academic

arxiv.org·

TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

💬Prompt Engineering Academic

arxiv.org·

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

🧠LLMs Academic

arxiv.org·

Advancing the State-of-the-Art in Empirical Privacy Auditing

🔒Digital Privacy Academic

arxiv.org·

Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model

Contextual Identity Laundering: How Claude’s Image Refusal Can Be Routed Through Web Search

DeceptionX: Explainable Deception Detection with Multimodal Large Language Models

SLUUG Talk: Demystifying Large Language Models on Linux

Can activation verbalizers surface an internal chain of thought?

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

If Claude Fable stops helping you, you’ll never know

Alignment Defends LLMs from Property Inference Attacks

Tight Sample Complexity of Transformers

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

Boris Cherny, Claude Code creator at Anthropic, says his personal workflow has shifted from manual prompting to building autonomous loops

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA

A Regret Minimization Framework on Preference Learning in Large Language Models

Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation

TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

Advancing the State-of-the-Art in Empirical Privacy Auditing