Clémentine, @huggingface
's evaluation expert, made an excellent guide about LLM evaluation. It covers automatic benchmarks, human eval, and LLM-as-a-judge, including tips and tricks to create your own evals.
RESEARCH
-
LLM Evaluation Guide: Benchmarks, Human Eval, and Judge Methods
By
–
-
Discover Aria’s paper and try Rhymes AI’s BeaGo
By
–
Read their paper for Aria
https://
huggingface.co/papers/2410.05
993
… Try BeaGo
https://
rhymes.ai/blog-details/m
eet-rhymes-ai-powerful-ai-built-for-all
… -
Rhymes AI’s Aria MoE beats GPT-4o and Gemini-1.5-Flash
By
–
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash New player entered the game! @rhymes_ai_ has just been announced, and unveiled Aria – a multimodal powerhouse that's punching above its weight. Key insights: Mixture-of-Experts
-
AI wins Nobel in physics and chemistry, proof of benefit to humanity
By
–
The fact that AI wins the Nobel Prize in physics and chemistry is the best proof that AI is a positive asset for science, and more broadly an incredible opportunity for humanity.
-
AI-Generated Content Lacks Logic and Authentic Reasoning
By
–
There’s no logic in that list, just moralizing, and it’s clearly spit out by an AI bot.
-
Novel Framework Redefines Global Pruning Into Coordinated Subproblems
By
–
a novel framework that redefines the global pruning process into manageable, coordinated subproblems, allowing for resource-efficient optimization with global optimality
-
SparseLLM: Global Pruning Method for Pre-trained Language Models
By
–
SparseLLM: Towards Global Pruning of Pre-trained Language Models https://
arxiv.org/abs/2402.17946 https://
github.com/BaiTheBest/Spa
rseLLM
…
#neurips2024 -
IterComp: Iterative Composition-Aware Feedback Learning for Image Generation
By
–
IterComp Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
-
Real-Time Text Toonify Head Avatar from Single Video
By
–
TextToon
— AK (@_akhaliq) 10 octobre 2024
Real-Time Text Toonify Head Avatar from Single Video pic.twitter.com/0sXccm8IkTTextToon Real-Time Text Toonify Head Avatar from Single
-
Capturing and Physically Synthesizing Piano Hand Motions
By
–
FürElise
— AK (@_akhaliq) 10 octobre 2024
Capturing and Physically Synthesizing Hand Motions of Piano Performance pic.twitter.com/m0rvHUkdfPFürElise Capturing and Physically Synthesizing Hand Motions of Piano Performance