Continue to push the boundaries of LLM reasoning! Excited to announce SubgoalXL, a joint effort advancing the frontier of AI-powered theorem proving between @HKUniversity (
@xlzhao_hku
, @linzhengisme
, @ikekong
) and @SambaNovaAI
. On miniF2F, a challenging theorem proving
MACHINE LEARNING
-
SubgoalXL Advances LLM Reasoning for Theorem Proving
By
–
-
SubgoalXL Improves LLM Theorem Proving Efficiency
By
–
SubgoalXL tackles two major challenges in LLM theorem proving: Scarcity of specialized theorem-proving data Complexity in multi-step reasoning for formal proofs
Our solution: Optimizing data efficiency and structuring proofs into manageable subgoals. -
Quantization Technique Reduces LLM Size and Memory Requirements
By
–
While SOTA LLMs are too large to run on laptops, quantization is a technique that reduces LLMs’ computational and memory requirements. Quantization reduces a model’s size and speeds up processing by converting its parameters from 32-bit to lower-precision formats like 16-bit or
-
Cohere paper questions human feedback as gold standard for AI
By
–
Human Feedback for AI training might not be the golden goose we thought. I’ve just read a great paper where Cohere researchers raises significant questions about using Human feedback evaluate AI language models. Human feedback is often regarded as the gold standard for judging
-
Distillation Emerges as Superior Model Improvement Technique Over DPO
By
–
Because model merging and abliteration are destructive, DPO has been essential to healing networks. These days are now over: distillation is the new powerhouse that not only heals models but also improves them.
-
Handwritten Text Recognition Using OCR with TrOCR Model
By
–
In this article, we address the complex problem of recognizing handwritten text using OCR. We will train the TrOCR model for handwritten note recognition on the Goodnotes dataset.https://t.co/RRqkDm0FIt
— Satya Mallick (@LearnOpenCV) 3 septembre 2024
The dataset, which has been curated from several users, is versatile and… pic.twitter.com/yhQfrWkWydIn this article, we address the complex problem of recognizing handwritten text using OCR. We will train the TrOCR model for handwritten note recognition on the Goodnotes dataset. https://
learnopencv.com/handwritten-te
xt-recognition-using-ocr
…
The dataset, which has been curated from several users, is versatile and -
Fine-tuning and Model Merging Techniques Explained
By
–
Excellent breakdown of my fine-tuning and model merging talk by @TheTuringPost 🙂
-
Spherical Harmonics Resolution Approaches in AI Systems
By
–
Yes but it does not use spherical harmonics or other approaches (disco) to work at any resolution
-
LLMs Training on Book Summaries and Study Materials
By
–
LLMs would *already* have trained on stuff like this for major books, since they would have seen 2 page summaries, 'Cliff's Notes', chapter summaries, etc.
-
Commentary on LLM prompting and counting reliability
By
–
As many have pointed out, there are much better ways to prompt this. Also, it’s silly to use an LLM here, as there’s little hope of making them 100% reliable at counting. What’s notable IMO isn’t that it can’t count, but that it doesn’t see it can’t count (and e.g. try its REPL)