Viewing profile — hxypqr

Predicting the next character alone cannot achieve this kind of compression, because the probability distribution obtained from the training results is related to the corpus, and m…

The reasoning ability of Opus also has a clear ceiling

Key insight is the finiteness of reasoning parts in planar geometry that can be quickly solved by the SAT, which often does not exist in most first-order and second-order logics, s…

The problem is that using LLM as a role for drawing auxiliary lines is too inefficient. It is hard to imagine people deploying a large number of machines to solve a simple IMO prob…

The problem is that LLM as a role for drawing auxiliary lines is too inefficient. It is hard to imagine people deploying a large number of machines to solve a simple IMO problem. T…

Most of Dynamic programming is just a method of reducing computational complexity by changing the noun objects in first-order logic (or second-order logic, advanced version) to wal…

mixtral 7*8B does indeed have this characteristic. It tends to disregard the requirement for structured output and often outputs unnecessary things in a very casual manner. However…

Temperature and light may create illusions in LLM. A potential available solution to this is to establish a knowledge graph based on sensor signals, where LLM is used to understand…

This is a very insightful viewpoint. In this situation, I believe it is necessary to use NER to connect the LLM module and the ML module.

No matter what n is, the answer to this problem on an n*n chessboard is basically cn^2. Due to the finitness of this problem, the optimal solution will repeat in a certain pattern …

The number .001% should be changed to .1% or 1%.

Too optimistic, how did dinosaurs become extinct, and why won't similar things happen to humans? Even if AI is a problem inherent to humans, the core issue and the collision of ast…

Obviously, the cost of using LLM to solve this problem is relatively high. At most, it can only treat LLM as one of the signals instead of processing all the information. Combining…

The most important thing for a guitar teacher to do is to convince potential students to choose you as their teacher, and the most cost-effective way to achieve this goal is throug…

OPENAI is trying to release these views to confuse its opponents, I can clearly feel that the day when mathematics as a profession is disrupted is not far away from us, 5-10 years

This is not guesswork, if one evening you lie in the garden feeling bad because of a breakup or other reasons and watch the shadow of the lights, you can get similar results. Intro…

This is just fake news. In reality, there is no difference between what they actually do and training a three-layer CNN with one layer of FCN to predict what number should be fille…

The computational complexity of the diffusion model is very high, which means it may not be applicable in many practical scenarios. If our target image is two-dimensional but essen…

I haven't looked at the code, but I wanted to ask in advance if it is possible to incorporate lean4's formal mathematical capabilities into the current architecture to obtain more …

The ability of GPT-4 is not so much "figuring out" as it is "already knowing." Currently it seems.

Drones may be an example, they played a role in the Russia-Ukraine war