ποΈ Slide
Virtual Agentic Lab!
10-slide paper summary of Swanson et al. (doi:10.1038/s41586-025-09442-9)
π·οΈ LLMs
Tag: LLMs
12 items tagged with "LLMs"
ποΈ Slide
LLM Research Directions
SCIPE Workshop on LLMs - Day 3
ποΈ Slide
Tool Use (Function Calling) & RAG
SCIPE Workshop on LLMs - Day 2
ποΈ Slide
State of Large Language Models
SCIPE Workshop on LLMs
ποΈ Slide
Test-Time Scaling Under Budget
M.Sc. Thesis in Computer Science
π Post
Entropy of bfloat16: 8 Bits Are Doing 2.6 Bits of Work
ποΈ Slide
Psychometric Modeling of LLM Evaluation Datasets
A principled Bayesian framework that replaces Pass@k with posterior estimates, credible intervals, and stable rankings for LLM evaluation
π Post
Simulating LLM Evaluation Datasets Using Psychometric Models
π Post
Simulating LLM Answers to Evaluation Datasets
π Paper
Donβt Pass@π: A Bayesian Framework for Large Language Model Evaluation
Mohsen Hariri, Amirhossein Samandar, Michael Hinczewski, Vipin Chaudhary
A Bayesian framework for evaluating large language models that replaces unstable Pass@k metrics with robust posterior estimates and credible intervals. This method improves sample efficiency, supports graded outcomes, and enables statistically sound model comparisons.
π Paper
Quantize What Counts: More For Keys, Less For Values βοΈπππ’
Mohsen Hariri, Alan Luo, Weicong Chen, Shaochen Zhong, Tianyi Zhang, Qifan Wang, Xia Hu, Xiaotian Han, Vipin Chaudhary
Key-favored KV-cache quantization for LLMs: theory shows keys have larger norms and should get more bits; empirics show 4b-K/2b-V preserves up to 98.3% accuracy while cutting memory.
π Paper
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float
Tianyi Zhang, Mohsen Hariri, Shaochen Zhong, Vipin Chaudhary, Yang Sui, Xia Hu, Anshumali Shrivastali
DFloat11 compresses LLMs to 70% of their original size while maintaining bit-for-bit identical outputs. A lossless compression framework with efficient GPU inference that enables running Llama 3.1 405B on a single node.