| ▲ | Energy-Based Reasoners: 385x more efficient inference(energy-based-reasoners.github.io) | |||||||||||||||||||||||||||||||||||||||||||
| 218 points by frenchmajesty 6 hours ago | 30 comments | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | Topfi 4 hours ago | parent | next [-] | |||||||||||||||||||||||||||||||||||||||||||
Recommend checking out Logical Intelligence, chaired by among others Yann LeCun, for more context on EBMs [0]. Has great potential in areas that LLMs traditionally do not perform that well in and, because they want to show the advantages of EBMs, also tends to be a great source of examples LLMs struggle with, like primary school level maths and counting (while ironically providing Millennium level Lean proofs). Does of course open the not unreasonable discussion of whether it matters if LLMs can accurately count when writing code to do the calculation is reliable and fast... [0] https://logicalintelligence.com/blog/energy-based-model-sudo... | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | program_whiz 3 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
A clarifying way to think about this for sudoku: For every clue, mark the probability of sampling its number in the row/col to zero. Also mark the probability of selecting a "clue cell" for modification to 0. Pick a random cell for modification, based on its "energy" (higher energy get modified first):
For the selected cell, choose a digit. Look at numbers in its row/column, every occurrence of a number in the row/col drop prob of sampling by 90%. Example:
Obviously this would get more complex with more numbers on the line (this is just checking 7 on otherwise empty line).This is essentially what these models are doing. It provides a kind of "wave function collapse" search with random exploration based on "energy", but energy is just defined as conflict / unsolved. For something like a maze, energy is disconnected path segments or walls, etc. | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | mocmoc 2 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
I've spent a year on this. EBMs while ... how to say it, they are impressive validators , it's insanely hard to train them. They are very niche specific. While LLMs , being not right all the time and clumsy and so on, they help the people to get the job done at the end. EBM sudoku is not that hard in a small scale, and Logical Intelligence sudoku solver doesn't scale , if I'm wrong , I want to see them offering as big of a sudoku as you want. also, after months and months training EBMs , you come to realize... it's really worth it? | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | xgk 4 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
The paper does not seem to define what Energy-Based means. The paper says: "EBMs learn a scalar function that assigns an energy to a candidate prediction given an input." What codomain do those learned scalar function have? I guess real numbers? But is "Energy" just a synonym for the reals? | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | igleria 5 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
As far as I could understand, this works very well for a very specific logic puzzle problem set. Interested on future papers tho :) | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | crab2 10 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
"Autoregressive Language Models are Secretly Energy-Based Models" | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | program_whiz 4 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
Big caveat if anyone thinks this could replace or strongly augment "reasoning" models (LLMs, RNNs) -- its more like an energy-based search for a discrete problem (graph coloring, solving mazes, sudoku). It works by training a weight matrix (N-to-N) on different solutions. For example, in sudoku you're training a weight matrix for every space to every other space (81 c 2), with 9x9 numbers (~240K weights). So then the "energy" for every number in a space is W_ij(a, b) where ij is a pair of spaces, and (a, b) is a pair numbers you want to swap (e.g. 4->2 in the space). Pick the lowest energy move each time (argmin of this whole space), and iterate. This has a few limitations. First, its discrete and has a limited space definition, getting this to work for arbitrary reasoning seems hard (what size/shape graph would you use for arbitrary reasoning). Second, the ruleset is defined apriori (e.g. you need to know you have a 9x9 grid and 9 numbers, the rules of the game are implicit in the checker). Third, the actual search algorithm is somewhat bespoke to task (less of a factor, maybe use generic graph coloring as the basis of any problem), but for something like agentic reasoning its not clear how this would be adapted. For example with mazes, we need to know what constitutes a valid path and a solved maze, but for language/code rules like that are hard to formulate. Fourth, this doesn't admit of an easy way to use "fuzzy reasoning" that would be required for integration with any kind of human language or image-based system, where continuous vectors are useful (the graph edges and colors are on/off or discrete). There are ways to adapt, but this approach fits pretty solidly in the "deterministic, fixed problem size" realm. In addition, for training you need correct solutions and counter-examples (strongly labeled). For something like "fuzzy logic" training or "natural language" coming up with clear examples and counter-examples would be challenging to fit into this model. LLMs are only possible by leveraging vast quantities of unlabeled data. Not saying impossible, but challenging. For example, if training on human code, what constitutes a counter-example? You basically already have to have a method of getting correct and sufficiently incorrect code just to train this type of system, and its unclear how to represent those changes. For all of these problems, given the constraints and amount of bespoke logic required, solving with dynamic programming is far faster (including arbitrary graph coloring problems). I only say this to mean that if we could solve all the problems I mentioned above and get arbitrary reasoning into the form of graph coloring, it would still probably be more efficient just to solve that with good old dynamic programming / recursion than with a model like this that needs O(N^2) params versus the graph and needs millions of training examples for different domains. They brag about solving sudoku, but a CPU-based approach to solving it the good old fashioned way on is probably 10-100x faster. If we were using an H200 like they did, we could easily solve the whole sudoku dataset in less than a second. But it _is_ a very interesting approach, partly because the energy strategy encodes good / likely guesses, so that is kind of interesting vs dynamic programming which is kind of a brute-force approach, so maybe for very large spaces it would be more efficient (but then you have the issue of the parameter space blowing up). | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | thesnarkitecht 2 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
Anyone want to explain how these models work? And can you actually run them on any hardware? | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | scurnus 4 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
This is basic and similar to recurrent reasoning papers, it works only on sudoku and basic games, with constrained rules, unique or low number of solutions. It would be interesting to see how these reasoners do in games like Chess or Go. Efficient inference is useful when it comes with something useful. | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | saithound 6 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
385x? Them's rookie numbers. Classical energies learn to reason 1000x faster than looped models. [1] Of course, all for a very generous definition of reasoning, that has almost nothing in common with the thing most people associate with the term nowadays. [2] [1] https://arxiv.org/abs/2611.17309 [2] https://developers.openai.com/api/docs/guides/reasoning?api-... | ||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | cobychapple 2 hours ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||
title says 385x and the page says 345x, I guess the compression is lossy? | ||||||||||||||||||||||||||||||||||||||||||||
| ▲ | netbioserror 3 hours ago | parent | prev [-] | |||||||||||||||||||||||||||||||||||||||||||
The more abstractly reasoning can be modeled, the better. It means knowledge can be externalized to discrete knowledge bases and queried when needed, and models can be run locally with lower and lower energy hardware. The question is, how integral to reasoning is compressing vast quantities of knowledge to the latent space? | ||||||||||||||||||||||||||||||||||||||||||||