[HN Gopher] Transformer^2: Self-Adaptive LLMs
       ___________________________________________________________________
        
       Transformer^2: Self-Adaptive LLMs
        
       Author : hardmaru
       Score  : 137 points
       Date   : 2025-01-15 00:37 UTC (22 hours ago)
        
 (HTM) web link (sakana.ai)
 (TXT) w3m dump (sakana.ai)
        
       | wildermuthn wrote:
       | Great research here. Contextual real-time weight modification is
       | definitely one of the breakthroughs required for AGI. Why create
       | a LoRA when you can generate one on the fly suited to the task at
       | hand?
        
         | verdverm wrote:
         | It does not seem like they are doing inference time weight
         | changes, to the tune of running backprop. It sounds more like
         | they are applying a pre-trained vector to the model, and select
         | that vector based on the input, in a two step process
        
           | wildermuthn wrote:
           | That's my general understanding as well, but it isn't a large
           | conceptual leap to go from real-time selection of pretrained
           | "z-vectors" to real-time generation of the same. The larger
           | conceptual breakthrough, with demonstration of its
           | effectiveness, is the big success here.
        
             | mtts wrote:
             | The interesting thing here is that the human brain also
             | seems to use pretrained ... things. For vision, use the
             | visual subsystem. For hearing, use the auditory subsystem.
             | For movement ... you get the point. Plus you can combine
             | these pretrained ... things, so for example for complex
             | movement, like balancing on a tightrope, multiple
             | subsystems are used (try standing on one leg with your eyes
             | closed).
             | 
             | Z-vectors are of course nothing like the subsystems in your
             | brain, but general the approach is certainly similar to how
             | the brain works.
        
               | dleeftink wrote:
               | > things
               | 
               | Senses?
        
               | mtts wrote:
               | For sight and hearing, yes, but is "language use" a
               | sense?
        
               | dleeftink wrote:
               | In the strict sense, no, but as a system of
               | communication, yes; organisms need some form of sensory
               | perception to communicate or 'sense' language.
        
             | verdverm wrote:
             | While not a large conceptual leap, the real-time generation
             | of "z-vectors" is not cheap in terms of compute or data
             | requirements, the latter of which I see as the main issue.
             | How are you going to generate the vector from a single
             | real-time input?
             | 
             | I still have yet to see anything that dissuades me from
             | agreeing with Yann LeCun when he says Transformers are
             | fundamentally limited. We won't get creativity, reasoning,
             | or even move past hallucinations without a major
             | breakthrough
        
               | mordymoop wrote:
               | How do the o3 results fit in context of this perspective?
        
               | verdverm wrote:
               | They do not change it, from what I have seen, o3 is more
               | hype and marketing than a meaningful step towards models
               | which can exhibit real creativity and reasoning as humans
               | perform it (rather than perceive it, which is the root of
               | the hype)
               | 
               | For example, a small child is completely capable of being
               | told "get in the car" and can understand, navigate, open
               | the door, and get in, with incredibly little energy usage
               | (maybe about the amount of a single potato chip/crisp)
               | 
               | Now consider what I have been working on recently (1)
               | evaluating secops tools from both a technical and
               | business perspective (2) prototyping and creating an RFC
               | for the next version of our DX at the org. They are very
               | far from this capability because it involves so many
               | competing incentives, trade offs, and not just the
               | context of the current state of code, but also the
               | history and vision. Crafting that vision is especially
               | beyond what a foundation in transformers can offer. They
               | are in essence an averaging and sequence prediction
               | algorithm
               | 
               | These tools are useful, even provide an ROI, but by no
               | means anywhere close to what I would call intelligent.
        
           | mtts wrote:
           | Sort of. According to the text they can use multiple
           | z-vectors (sets of weights that select for parts of the
           | system to be used to answer a specific question)
           | simultaneously, using a "simple optimization algorithm" to
           | determine the relative weight for each of these vectors.
        
         | bugglebeetle wrote:
         | See also the work being done by GoodFire AI:
         | 
         | https://www.goodfire.ai/
         | 
         | They now have an API that allows for dynamic exploration and
         | manipulation of the latent space for LLama 8-70B models (think
         | Golden Gate Claude). They also open sourced the sparse auto-
         | encoders that (in part) allow for this:
         | 
         | https://huggingface.co/Goodfire/Llama-3.3-70B-Instruct-SAE-l...
        
         | logicchains wrote:
         | >Contextual real-time weight modification is definitely one of
         | the breakthroughs required for AGI.
         | 
         | It's already been invented: https://arxiv.org/abs/2202.05780 .
         | That design is just very inefficient to scale up / use as a
         | transformer backbone.
        
         | mnky9800n wrote:
         | Why not, as each new task comes up, and then weights are
         | revalued, save those weights and keep them for reference as
         | priors for similar future tasks? As the model is exposed to new
         | data the average of the set of priors of things the model
         | thinks is similar might move closer to the posterior making the
         | model quicker and more able to arrive at good outcomes. I
         | suppose storage might be an issue.
        
           | magospietato wrote:
           | I'm wondering if you could fine tune the model on an
           | aggregate of a temporal slice of revalued weights? Something
           | analogous to REM sleep's involvement in embedding the days
           | events into long term memory.
        
             | Jerrrry wrote:
             | Sieve the temporary backprop interim weights as a function
             | of its loss of varentrophy relative to its place in the
             | revalued weights.
             | 
             | Remove the bottom weights dynamically based on the local
             | gradient in varentrophy so that internal dissonance
             | ("doubt") can be selected against.
             | 
             | "Preference Optimization" but with more opportunities for
             | meta-optimization.
        
           | QuadmasterXLII wrote:
           | thats just mixture of experts
        
             | mnky9800n wrote:
             | i thought mixture of experts didn't update itself with new
             | sets of weights and was just a collection of already
             | trained networks/weights? I could be wrong.
        
               | QuadmasterXLII wrote:
               | Well, that depends in whether you keep training it
        
               | mnky9800n wrote:
               | perhaps they should always be training and never static.
               | haha. i allegedly grow wiser in my age, why not neural
               | networks?
        
       | verdverm wrote:
       | This sounds like MoE and maybe a bit of chain-of-thought. Curious
       | what someone with more domain expertise thinks about this
       | 
       | If they can test against Llama 70B and Mistral 7B, they ought to
       | compare against Mistral 8x7b imho
        
         | imtringued wrote:
         | I'm not an expert, but MoE models perform better at continuous
         | learning, because they are less prone to catastrophic
         | forgetting.
        
       | Vampiero wrote:
       | It's all very interesting but those pictures look pretty bad.
       | Clear visible artifacts, awful shapes.
        
       | tzury wrote:
       | The ideas in the paper have been implemented and tested. The
       | authors conducted experiments on several tasks (math, coding,
       | reasoning, and visual question answering) and showed that their
       | approach works better than previous methods like LoRA.
       | 
       | Key ideas (in simple terms):
       | 
       | 1. What's the problem?                   - Fine-tuning LLMs for
       | every new task is slow, expensive, and often doesn't generalize
       | well.         - Models trained on one task may perform poorly on
       | others, especially unseen ones.         - Current methods (like
       | LoRA) can add new capabilities but aren't efficient enough.
       | 
       | 2. The solution:                   - Transformer2 uses a new
       | fine-tuning method called Singular Value Fine-tuning (SVF). This
       | focuses on adjusting only certain parts of the model's "weight
       | matrices" rather than changing everything.         - By tweaking
       | specific components (called "singular values"), it trains
       | smaller, efficient "expert" modules that specialize in particular
       | types of tasks.
       | 
       | 3. How it works:                   - Training phase: Train these
       | smaller expert modules offline using reinforcement learning (RL)
       | to specialize in tasks like coding, math, or reasoning.         -
       | Inference phase: When a new input is given, the system analyzes
       | the task (e.g., "Is this a math or coding problem?") in the first
       | pass. Based on this, it combines the right expert modules and
       | adapts the model's behavior in the second pass.
       | 
       | 4. Three adaptation strategies:                   - Prompt-based:
       | Use a cleverly designed text prompt to figure out the task type
       | and pick the right expert module.         - Classifier-based:
       | Train a separate model to classify tasks and match them to
       | experts.         - Few-shot adaptation: Look at a small number of
       | examples (few-shot learning) to dynamically combine expert
       | modules for the best results.
       | 
       | 5. Efficiency:                   - The system uses fewer
       | parameters than traditional fine-tuning methods like LoRA.
       | - Adaptation works even on small datasets without overfitting or
       | forgetting older tasks.
        
       | mdp2021 wrote:
       | It is discomforting to read, in the first paragraph, that
       | "dynamical adjustment of weights" is justified as "adaptation".
       | Clearly it is a sought milestone to have <<a future where AI
       | models are no longer static>>: but the chief reason remains,
       | "intelligent systems reprocesses their body of knowledge and
       | change it to improve it" - it is anterior to "adaptation to
       | environment", it is "maintenance of the body of knowledge (of the
       | world model)": it is the continuous practice of "thinking about
       | things", "pondering", "reflecting", "using judgement"...
       | 
       | There is not just a simple <<lifelong learning>>: the whole past
       | experience is still productive, requiring analysis, not "solved".
       | 
       | Anyway: the directions seem good.
       | 
       | Edit: equally interesting in another direction is the automated
       | analysis of the internal subagents, <<break[ing] down the vast,
       | complex knowledge stored in the LLM into smaller, meaningful, and
       | independent pieces (e.g., the different pathways or components
       | for math, language understanding, etc)>>. Should not there be a
       | general study of the dissection of systems with seemingly
       | emergent intelligence, doing on LLMs like we do on C. Elegans?
        
       | E_Bfx wrote:
       | > Transformer2 represents a significant milestone in the
       | evolution of AI systems.
       | 
       | Coming from a math background, it always amazes me to see how
       | people in AI/ML brag about their papers. If someone wrote:
       | 
       | > My paper represents a significant milestone in the evolution of
       | algebraic geometry/ergodic theory/combinatorics
       | 
       | it would be a laughing stock for the math community.
        
         | redox99 wrote:
         | In ML results are often a score (accuracy or whatever) which
         | makes it more gamefied
         | 
         | It's common to have competitions where the one with the highest
         | score in the benchmark "wins". Even if there is no formal
         | competition, it's very important being the SOTA model.
         | 
         | Results are more applicable to the real world, and more "cool"
         | subjectively (I don't think there's a 2 minutes paper
         | equivalent for math?), which increases ego.
         | 
         | And often authors are trying to convince others to use their
         | findings. So it's partly a marketing brochure.
        
           | E_Bfx wrote:
           | - There is also (but on a smaller scale) a gamification of
           | math with bounties
           | (https://mathoverflow.net/questions/66084/open-problems-
           | with-...) but when a result is proved you cannot prove it
           | "better than the first time". So it is more a "winner take it
           | all" situation. - I am not sure but the "2-minute papers"
           | equivalent would be poster sessions, a must-do for every
           | Ph.D. student - For the marketing side, there are some trends
           | in math, and subtly researchers try to brand their results so
           | they become active research fields. But since it cannot be
           | measured with GitHub stars or Hugging Face downloads, it is
           | more discreet
        
         | aithrowawaycomm wrote:
         | Especially when the results are so modest! "Significant"
         | doesn't seem like unfalsifiable hype here, it's just wrong.
        
         | verdverm wrote:
         | They aren't just researchers, there is a company that took on
         | $200M in a _Series A_...
         | 
         | https://sakana.ai/series-a/
        
           | mccoyb wrote:
           | Why is this relevant when presenting scientific research? Or
           | is the point of your comment to say, they are incentivized to
           | "brand" their research in a way which is attractive to a VC
           | audience?
        
             | verdverm wrote:
             | It's offered as one possible explanation for the tone or
             | style of the language that GP commented on. I don't think
             | their observation applies to ML research at large, this
             | group seems to be more eccentric in their writing (see
             | their history of submissions on HN and their blog more
             | generally)
        
             | KolmogorovComp wrote:
             | > Or is the point of your comment to say, they are
             | incentivized to "brand" their research in a way which is
             | attractive to a VC audience?
             | 
             | Yes
        
             | sroussey wrote:
             | > Why is this relevant when presenting scientific research?
             | 
             | I'm guessing that the difference lies in the potential
             | value extraction possibilities from the idea.
             | 
             | If comparing the transformers paper to an algorithm or
             | geometry, that is not used by anyone, I think the
             | differences are obvious from this perspective.
             | 
             | However, if that paper on geometry led to something like a
             | new way of doing strained silicon for integrated circuit
             | design that made manufacturing 10 times cheaper and the
             | circuit 10 times faster, then that would be more important
             | then that would the transformers one.
        
           | Der_Einzige wrote:
           | Anyone can be a researcher/scientist if they pass peer review
           | at a reputable journal or conference. That's just how it is.
        
             | verdverm wrote:
             | The bar seems to be much lower than getting a peer reviewed
             | paper published at a reputable outlet
             | 
             | This particular paper is not peer reviewed or published
             | beyond a preprint on arxiv
        
         | imtringued wrote:
         | Yeah the naming implies a significant breakthrough, but this is
         | just an incremental stepping stone that will be forgotten in
         | time.
        
       | justanotherjoe wrote:
       | Is this real? Or is this a hustler type paper/company.
        
         | SubiculumCode wrote:
         | The paper's infographics seems more PR than scientific
        
         | flakiness wrote:
         | fyi Sakana AI is founded by one of the transformer gang,
         | although that person is not in the author list.
         | https://venturebeat.com/ai/what-you-need-to-know-about-sakan...
        
       | verdverm wrote:
       | The code: https://github.com/SakanaAI/self-adaptive-llms
        
       | ghc wrote:
       | Can someone please enlighten me how this is any different from
       | Mixture of Experts? Because I don't see any difference at all.
        
         | liuliu wrote:
         | The router is manually designed (see their cem function). Also,
         | the experts are not separate weights, just different scales of
         | it's singular values.
        
           | ghc wrote:
           | Thank you, I was missing that second part.
        
       | liuliu wrote:
       | One weakness of this method is the storage of decomposed UV from
       | W. My linear algebra is rusty, but it seems required if you want
       | to scale in that U projected subspace, hence double your weight
       | memory footprint (that has been said, U / V should be easier to
       | quantize from information theory perspective). I also think MoE
       | is more principled if you want to have experts activations. But I
       | understand that Sakana's research focus mostly is about adapting
       | existing pretrained models, not to do it from scratch.
        
       | qrsjutsu wrote:
       | > https://sakana.ai/
       | 
       | I like that background animation. Seems like there's an
       | opportunity for tiny logic gates and some punny swarm behavior.
        
       | qoez wrote:
       | Worth noting is that the original inventor of the transformer is
       | part of this team
        
       ___________________________________________________________________
       (page generated 2025-01-15 23:02 UTC)