Hugging Face's logo
Jaward Sesay's picture
1 37 33

Jaward Sesay

Jaward
namanvats's profile picture MMAcGeezy23's profile picture shoaibalvi's profile picture
·
https://github.com/Jaykef

AI & ML interests

I like to train large deep neural nets too 🧠🤖💥 | First Paper (AutoAgents: A Framework for Automatic Agent Generation) Accepted @ IJCAI 2024 | Role Model Karpathy

Recent Activity

posted an update about 13 hours ago
Finally my first solo preprint is here:) a love letter to the field. Nothing much lol, this is just me trying to finetune my understanding of research behind the recent breakthroughs in reasoning models. It’s a preprint targeting beginners in the field - will eventually make necessary changes later. In the meantime have fun with it:) Download: https://github.com/Jaykef/Jaykef/blob/main/papers/The-Dawn-of-Thinking-Machines.pdf
upvoted a paper about 15 hours ago
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
View all activity

Organizations

MLX Community's profile picture

Jaward's activity

posted an update about 13 hours ago
view post
Post
694
Finally my first solo preprint is here:) a love letter to the field. Nothing much lol, this is just me trying to finetune my understanding of research behind the recent breakthroughs in reasoning models. It’s a preprint targeting beginners in the field - will eventually make necessary changes later. In the meantime have fun with it:)
Download: https://github.com/Jaykef/Jaykef/blob/main/papers/The-Dawn-of-Thinking-Machines.pdf
posted an update 5 days ago
view post
Post
2210
New reasoning algo just dropped: Adaptive Parallel Reasoning
“we propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end. APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.”
Paper: https://arxiv.org/pdf/2504.15466
Code: https://github.com/Parallel-Reasoning/APR
replied to their post 7 days ago
posted an update 8 days ago
posted an update 14 days ago
view post
Post
1829
Funtime with SpatialLM- eventually it will serve well in embodied AI.
replied to their post 24 days ago
view reply

i noticed the models and code are not out yet, but they said they will release them shortly
posted an update 24 days ago
posted an update 26 days ago
view post
Post
1887
Implements from first-principle recently proposed dynamic tanh as alternative to layernorm. Specifically, we trained a nanoGPT (0.8 M params) on tiny shakespeare with conventional layernorm, RMSNorm and dynamic tanh, then compared performances. Observed performance seems to match or is stable for α = 0.5~ 1.5, might outperform if trained longer.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/Dynamic_Tanh.ipynb
Background music by 周子珺
reacted to clem's post with 🚀 27 days ago
view post
Post
4000
Before 2020, most of the AI field was open and collaborative. For me, that was the key factor that accelerated scientific progress and made the impossible possible—just look at the “T” in ChatGPT, which comes from the Transformer architecture openly shared by Google.

Then came the myth that AI was too dangerous to share, and companies started optimizing for short-term revenue. That led many major AI labs and researchers to stop sharing and collaborating.

With OAI and sama now saying they're willing to share open weights again, we have a real chance to return to a golden age of AI progress and democratization—powered by openness and collaboration, in the US and around the world.

This is incredibly exciting. Let’s go, open science and open-source AI!
·
posted an update about 1 month ago
posted an update about 1 month ago
view post
Post
1768
Finally, the ground truth / AlexNet’s original source code is available to all.
Context: AlexNet had a historic win in the 2012 ImageNet Large Scale Visual Recognition Challenge (ILSVRC), reducing error rate from 26% (previous best) to 15.3%. It’s a deep CNN with 8 layers (5 convolutional + 3 fully connected), pioneering the use of ReLU activations for faster training, dropout for regularization, and GPU acceleration for large-scale learning. This moment marked the beginning of the deep learning revolution, inspiring architectures like VGG, ResNet, and modern transformers.
Code: https://github.com/computerhistory/AlexNet-Source-Code
posted an update about 1 month ago
view post
Post
2122
Nvidia brings blue (from starwars droids) to life 🤯, supercute with flawless dexterity and droid voice. It's the result of their colab research with Google DeepMind and Disney, revealed as part of their new opensource physics engine for robotics simulation: NEWTON - which enables robots to learn how to complete complex tasks with greater precision.

ReadMore: https://developer.nvidia.com/blog/announcing-newton-an-open-source-physics-engine-for-robotics-simulation?ncid=so-twit-820797-vt48
posted an update about 2 months ago
view post
Post
1931
This is the most exciting of this week’s release for me: Gemini Robotics - A SOTA generalist Vision-Language-Action model that brings intelligence to the physical world. It comes with a verifiable real-world knowledge Embodied Reasoning QA benchmark. Cool part is that the model can be specialized with fast adaptation to new tasks and have such adaptations transferred to new robot embodiment like humanoids. Looking forward to the model and data on hf, it’s about time I go full physical:)
Technical Report: https://storage.googleapis.com/deepmind-media/gemini-robotics/gemini_robotics_report.pdf
posted an update about 2 months ago
view post
Post
2025
Super Interesting Paper!
Proposes a neural network NWM (Neural Wave Machine which are basically Oscillatory RNNs) that can learn to produce traveling waves in their hidden state in response to visual stimuli, thus enabling the transfer and integration of spatial information across neural connections. In other words they showed that neural networks have wave-like properties that blends and processes visual information over time, cool seeing a union of AI and physics in this way.
Paper: https://arxiv.org/pdf/2502.06034
Code: https://github.com/KempnerInstitute/traveling-waves-integrate
posted an update about 2 months ago
posted an update about 2 months ago
replied to their post 2 months ago
view reply

bro if you had read the repo you would see that this implementation is for educational purpose, it's not done because it's easy. Not to mention unsloth is using trl's GRPO trainer which is super slow on cpu and does not scale for models under 500M params, I tried it both on cpu and gpu. This custom implementation cuts most of the heavy lifting allowing you to train and scale faster even on cpu, plus a bunch of custom configs with a simplified GRPO trainer in under 500 lines of code. There's a lot one can learn from it.
posted an update 2 months ago
view post
Post
3911
Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
  • 2 replies
·
posted an update 3 months ago
view post
Post
3618
ByteDance drops OmniHuman🔥
This is peak SOTA performance - flawless natural gestures with perfect lip sync and facial expressions. This is the second time they've released SOTA level talking-heads only this time with hands and body motion.
Project: https://omnihuman-lab.github.io/
·
posted an update 3 months ago
view post
Post
1532
The beauty in GRPO is the fact that it doesn’t care if the rewards are rule-based or learned, the hack: let the data self-normalize— trajectories in a batch compete against their mean, no value model, no extra params, just clean, efficient RL that cuts memory usage by 50%, while maintaining SOTA performance. btw it was introduced 9months prior to R1: arxiv.org/pdf/2402.03300
  • 1 reply
·