Hugging Face's logo

AI Zero to Hero

classroom
https://xr.azurewebsites.net/
Aaron_Wacker
AaronCWacker
Activity Feed Request to join this org

AI & ML interests

AGI and ML Pipelines, Ambient IoT AI, Behavior Cognitive and Memory AI, Clinical Medical and Nursing AI, Genomics AI, GAN Gaming GAIL AR VR XR and Simulation AI, Graph Ontology KR KE AI, Languages and NLP AI, Quantum Compute GPU TPU NPU AI, Vision Image Document AI

AIZeroToHero's activity

hesamationΒ 
posted an update 2 days ago
view post
Post
2673
this book actually exists for free, β€œthe little book of deep learning”. best to refresh your mind about DL basics:
> foundations of machine learning
> how models train
> common layers (dropout, pooling…)
> basic intro to LLMs
actually optimized for mobile.

Book: https://fleuret.org/public/lbdl.pdf
hesamationΒ 
posted an update 23 days ago
view post
Post
2953
The best researchers from DeepSeek, OpenAI, Microsoft, and ByteDance explored RL and Reasoning in LLMs,

Here's some of their key findings:

1/ RL can further improve distilled models. These models are essentially SFT fine-tuned with the data generated by larger models, and the SFT+RL combo does not disappoint.

This is verified in the DeepSeek-R1 paper.

2/ both GRPO and PPO algorithms suffer from length bias; they encourage longer responses. This can be tackled by introducing explicit rewards based on the length of the answer.

3/Most reasoning research is focused on code and math. But training models on logic puzzles improves them for mathematical tasks too.

This shows the RL reasoning is generalized beyond the specific domain knowledge.

Previous research also shows RL can be a great generalizer.

4/The reasoning might not be only induced by RL; it might already be hidden in the base models due to the pre-training and CoT data they were trained on.

So while RL does wake up the reasoning beast, maybe it's not the only solution (e.g. other methods such as distillation)

5/ back to the length bias; reasoning models tend to generate longer responses for wrong answers. RL might be the culprit.

RL favours longer answers when the reward is negative, to dilute the penalty per individual token and lower the loss.

This might explain the "aha" moments!

6/ OpenAI's competitive programming paper showed an interesting finding:

o3 can learn its own test-time strategies (like writing an inefficient but correct solution to verify the answer of an optimized solution)

RL helps LLMs develop their own reasoning & verification methods.
The recent article by @rasbt helped me a lot in getting a broad view of the recent research on reasoning models.

He also lists more influential papers on this topic, It's a must-read if you're interested.

check it out πŸ‘‡
https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training
hesamationΒ 
posted an update 26 days ago
view post
Post
2158
OpenAI just released a 34-page practical guide to building agents,

Here's 10 things it teaches us:

1➜ agents are different from workflows: they are complete autonomous systems that perform tasks on your behalf. many applications use LLMs for workflows, but this is not an agent.

2➜ use them for tricky stuff: complex decision making, dynamic rules, unstructured data

3➜ core recipe: each agent has three main components: Model (the brain), Tools, Instructions on how to behave

4➜ choose the right brain: set up evals to get a baseline performance, use a smart model to see what's possible, gradually downgrade the model for cost and speed

5➜ tools are key: choose well-defined and tested tools. an agent needs tools to retrieve data and context, and take actions.

6➜ instruction matters A LOT: be super clear telling the agent its goals, steps, and rules. Vague instructions = unpredictable agent. Be explicit.

7➜ start simple, then scale: often a single agent with several tools is ok. don't jump to complex multi-agent systems immediately.

8➜ if you use multi-agents: you can have a "manager" agent directing traffic to specialist agents, or have agents hand off tasks to each other.

9➜ gaurdrails are a MUST: check user input for weird stuff, make sure the agent isn't about to do something risky, filter out private info, block harmful content. Don't let it run wild.

10➜ build and plan for humans: start small, test, improve. always have a plan for when the agent gets stuck or is about to do something high-risk.

Download: https://t.co/fJaCkgf7ph
Β·
hesamationΒ 
posted an update 28 days ago
hesamationΒ 
posted an update about 1 month ago
view post
Post
8934
Google published a 69-page whitepaper on Prompt Engineering and its best practices, a must-read if you are using LLMs in production:
> zero-shot, one-shot, few-shot
> system prompting
> chain-of-thought (CoT)
> ReAct

LINK: https://www.kaggle.com/whitepaper-prompt-engineering
> code prompting
> best practices
hesamationΒ 
posted an update about 1 month ago
view post
Post
2897
The best researchers from Yale, Stanford, Google DeepMind, and Microsoft laid out all we know about Agents in a 264-page paper [book],

Here are some of their key findings:

They build a mapping of different agent components, such as perception, memory, and world modelling, to different regions of the human brain and compare them:

- brain is much more energy-efficient
- no genuine experience in agents
- brain learns continuously, agent is static

An agent is broken down to:
- Perception: the agent's input mechanism. can be improved with multi-modality, feedback mechanisms (e.g., human corrections), etc.
- Cognition: learning, reasoning, planning, memory. LLMs are key in this part.
- Action: agent's output and tool use.

Agentic memory is represented as:
- Sensory memory or short-term holding of inputs which is not emphasized much in agents.
- Short-term memory which is the LLM context window
- Long-term memory which is the external storage such as RAG or knowledge graphs.

The memory in agents can be improved and researched in terms of:
- increasing the amount of stored information
- how to retrieve the most relevant info
- combining context-window memory with external memory
- deciding what to forget or update in memory

The agent must simulate or predict the future states of the environment for planning and decision-making.

ai world models are much simpler than the humans' with their causal reasoning (cause-and-effect) or physical intuition.

LLM world models are mostly implicit and embedded.

EMOTIONS are a deep aspect of humans, helping them with social interactions, decision-making, or learning.

Agents must understand emotions to better interact with us.

But rather than encoding the feeling of emotions, they have a surface-level modelling of emotions.

Perception is the process by which an agent receives and interprets raw data from its surroundings.

READ PAPER: Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems (2504.01990)
hesamationΒ 
posted an update about 1 month ago
view post
Post
2720
What, How, Where, and How Well? This paper reviews test-time scaling methods and all you need to know about them:
> parallel, sequential, hybrid, internal scaling
> how to scale (SFT, RL, search, verification)
> metrics and evals of test-time scaling

πŸ”—paper: What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models (2503.24235)

If you want to learn what inference-time compute scaling is @rasbt has a great blog post on that:
https://magazine.sebastianraschka.com/p/state-of-llm-reasoning-and-inference-scaling
hesamationΒ 
posted an update about 1 month ago
awacke1Β 
posted an update about 1 month ago
view post
Post
1655
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.

https://huggingface.co/spaces/awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? β˜•
2. Camera Snap πŸ“·: Capture life’s chaosβ€”your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR πŸ”: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt β€œneon superhero me”
5. PDF πŸ“„: Double-page OCR Single-page sniping

Build Titans 🌱: Train tiny AI models. πŸ’ͺCharactersπŸ§‘β€πŸŽ¨: Craft quirky heroes.
πŸŽ₯
not-lainΒ 
posted an update 2 months ago
awacke1Β 
posted an update 2 months ago
awacke1Β 
posted an update 3 months ago
view post
Post
2484
πŸš€ Blast into the future with ZaxxonGalaxian – a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies. awacke1/ZaxxoGalaxian
not-lainΒ 
posted an update 3 months ago
not-lainΒ 
posted an update 4 months ago
view post
Post
1708
we now have more than 2000 public AI models using ModelHubMixinπŸ€—
not-lainΒ 
posted an update 4 months ago
view post
Post
4070
Published a new blogpost πŸ“–
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
πŸ”— https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
awacke1Β 
posted an update 4 months ago
view post
Post
3206
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.

1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]


To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.

1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
Sri-Vigneshwar-DJΒ 
posted an update 4 months ago
view post
Post
758
Checkout phi-4 from Microsoft, dropped a day ago... If you ❀️ the Phi series, then here is the GGUF - Sri-Vigneshwar-DJ/phi-4-GGUF. phi-4 is a 14B highly efficient open LLM that beats much larger models at math and reasoning - check out evaluations on the Open LLM.

Technical paper - https://arxiv.org/pdf/2412.08905 ; The Data Synthesis approach is interesting
Sri-Vigneshwar-DJΒ 
posted an update 4 months ago
view post
Post
2088
Just sharing a thought: I started using DeepSeek V3 a lot, and an idea struck me about agents "orchestrating during inference" on a test-time compute model like DeepSeek V3 or the O1 series.

Agents (Instruction + Function Calls + Memory) execute during inference, and based on the output decision, a decision is made to scale the time to reason or perform other tasks.
Sri-Vigneshwar-DJΒ 
posted an update 4 months ago
view post
Post
2352
Combining smolagents with Anthropic’s best practices simplifies building powerful AI agents:

1. Code-Based Agents: Write actions as Python code, reducing steps by 30%.
2. Prompt Chaining: Break tasks into sequential subtasks with validation gates.
3. Routing: Classify inputs and direct them to specialized handlers.
4. Fallback: Handle tasks even if classification fails.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/building-effective-agents-with-anthropics-best-pra
awacke1Β 
posted an update 4 months ago