TinyLLM

@tiny_language

TinyLLM: Bringing language models to constrained edge devices for supporting embedded sensing applications

tinyllm.org

Joined December 2024

8Posts 0Followers 16Following

TinyLLM reposted

Vega Shah

@dr_alphalyrae

Dec 24

Automating the Search for Artificial Life with Foundation Models arxiv.org/abs/2412.17799

TinyLLM reposted

Atul Butte

@atulbutte

Dec 23

Whoa! In @NEJM_AI: A Multimodal Biomedical Foundation Model Trained from 15 Million Image–Text Pairs… fully open-access foundation model! ai.nejm.org/doi/full/10.10…

TinyLLM reposted

maharshi

@maharshii

Dec 24

150GB of math dataset, holy shit

TinyLLM reposted

Jonas Pfeiffer

@PfeiffJo

Dec 24

🧠💡 Our LLMs just had a ‘memory augmentation’—now they can deliberate like seasoned thinkers! arxiv.org/abs/2412.17747

TinyLLM reposted

Sloth: scaling law for LLM skills predicts benchmark scores (even from a single model per family). It is based on factor analysis and has family-specific parameters, making it interpretable and accurate! Paper: arxiv.org/abs/2412.06540 GitHub: github.com/felipemaiapolo… 🧵1/8

felipemaiapolo's tweet image. Sloth: scaling law for LLM skills predicts benchmark scores (even from a single model per family). It is based on factor analysis and has family-specific parameters, making it interpretable and accurate!

Paper: arxiv.org/abs/2412.06540
GitHub: github.com/felipemaiapolo…

🧵1/8

TinyLLM reposted

Surya Ganguli

@SuryaGanguli

Dec 23

Our new paper "Fooling LLM graders into giving better grades through neural activity guided adversarial prompting" expertly lead by @atsushi_y1230 arxiv.org/abs/2412.15275 With the potential rise of automated grading, we examine the fragility of these grading systems to attacks…

Atsushi Yamamura (山村篤志)

@atsushi_y1230

Dec 23

Excited to share our latest work, "Fooling LLM graders into giving better grades through neural activity-guided adversarial prompting" (w/ @SuryaGanguli)! We investigate distorting AI decision-making to build fair and robust AI judges/graders.arxiv.org/abs/2412.15275 #AISafety 1/n

TinyLLM reposted

Yuchen Jin

@Yuchenj_UW

Dec 23

I'm more and more confident that tokenization will be gone. Humans don't think in "tokens". Tokens are hardcoded abstractions in LLMs that lead to weird behavior: LLMs can solve PhD-level math questions but cannot answer "Is 9.9 > 9.11?" Meta is shifting LLMs to LCMs (Large…