Using learnings from small scale derisks to train larger model
LLMS
-
TL;DR prompt effectiveness on text length
By
–
So something like “Provide a TL;DR for the below text” How long a text have you tried this on?
-
Effective prompts for summarizing technical content with open models
By
–
Does anyone have good examples of prompts for summarising technical content? Looking at something that works w/ open models Trying something fun!
-
Perplexity for LLM Evaluation: Assessing Language Model Performance
By
–
Perplexity for LLM Evaluation https://
bit.ly/3CUFPQd
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
LLMs Spatial Reasoning Evaluation Study Findings
By
–
I really enjoyed working with @sainingxie and his students in this study called “Thinking in Space”, which is an evaluation on how LLMs (mostly failed to) do in spatial reasoning, something so essential to human intelligence. So much more to look ahead in 2025 to push the… https://t.co/CtZWQYIIoM
— Fei-Fei Li (@drfeifei) 22 décembre 2024I really enjoyed working with @sainingxie and his students in this study called “Thinking in Space”, which is an evaluation on how LLMs (mostly failed to) do in spatial reasoning, something so essential to human intelligence. So much more to look ahead in 2025 to push the
-
Fine-tuning LLMs for RAG: Advanced Techniques
By
–
Good morning! In this week's iteration, let’s dive into fine-tuning LLMs for RAG! https://
open.substack.com/pub/louisbouch
ard/p/fine-tuning-llms-for-rag?r=25qlky&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
… -
2024 AI Research Papers Compilation and Recovery Update
By
–
Thanks for all the warm wishes, everyone! I couldn’t write my yearly AI research review, but here’s my list of bookmarked papers you might find useful: https://
magazine.sebastianraschka.com/p/llm-research
-papers-the-2024-list
… And no worries, I’m slowly but steadily recovering & already starting to feel bit better every day -
Mathematical Reasoning in Multimodal LLMs: Comprehensive Survey
By
–
9). A Survey of Mathematical Reasoning in the Era of Multimodal LLMs – presents a comprehensive survey analyzing mathematical reasoning capabilities in multimodal large language models (MLLMs), covering benchmarks, methodologies, and challenges across 200+ studies since 2021.
-
Precise Length Control in LLMs: Countdown Positional Encoding
By
–
10). Precise Length Control in LLMs – adapts a pre-trained decoder-only LLM to produce responses of a desired length; integrates a secondary length-difference positional encoding into the input embeddings which enables counting down to a user-set response terminal length.
-
DeepSeek-VL2: Advanced Vision-Language Model with Dynamic Tiling
By
–
7). DeepSeek-VL2 – a new series of vision-language models featuring dynamic tiling for high-resolution images and efficient MoE architecture, achieving competitive performance across visual tasks.