DEV Community

Data Science

Data Science allows us to extract meaning from and interpret data.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Models That Prove Their Own Correctness

Models That Prove Their Own Correctness

Comments
5 min read
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Comments
4 min read
Surveilling the Masses with Wi-Fi-Based Positioning Systems

Surveilling the Masses with Wi-Fi-Based Positioning Systems

Comments
5 min read
Lessons from the Trenches on Reproducible Evaluation of Language Models

Lessons from the Trenches on Reproducible Evaluation of Language Models

Comments
5 min read
Not All Language Model Features Are Linear

Not All Language Model Features Are Linear

Comments
4 min read
Many-Shot In-Context Learning

Many-Shot In-Context Learning

Comments
4 min read
Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks

Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks

1
Comments
3 min read
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

Comments
4 min read
Extracting Prompts by Inverting LLM Outputs

Extracting Prompts by Inverting LLM Outputs

Comments
4 min read
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA

Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA

Comments
4 min read
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

Comments
4 min read
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Comments
4 min read
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Comments
4 min read
Attention as an RNN

Attention as an RNN

Comments
4 min read
The CAP Principle for LLM Serving

The CAP Principle for LLM Serving

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.