In Honour of This Year's NeurIPs Test of Time Paper Awardees
•
2
Jaward Sesay
Jaward
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
liked
a model
about 5 hours ago
deepseek-ai/DeepSeek-V3-Base
replied to
their
post
5 days ago
Implements from first-principle a discrete flow matching model for code generation- trained a small sized 2D dfm model on two variations of code for binary search. The result was amazing, code in comment:
Code: https://github.com/Jaykef/ai-algorithms/blob/main/dfm.ipynb
Articles
Organizations
Jaward's activity
replied to
their
post
5 days ago
btw the background songs in the videos are actually what I listen to during implementation
posted
an
update
5 days ago
Post
1703
Implements from first-principle a discrete flow matching model for code generation- trained a small sized 2D dfm model on two variations of code for binary search. The result was amazing, code in comment:
Code: https://github.com/Jaykef/ai-algorithms/blob/main/dfm.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/dfm.ipynb
-
- 1 reply
posted
an
update
16 days ago
Post
577
In Honour of This Year's NeurIPs Test of Time Paper Awardees
This year's NIPs Test of Time Paper Awards went to two groundbreaking papers:
1. Generative Adversarial Nets (Goodfellow et al)
2. Sequence to Sequence Learning with Neural Networks (Ilya et al)
Let's explore how these papers helped pioneered breakthroughs in today's AI:
Full Article: https://huggingface.co/blog/Jaward/nip
This year's NIPs Test of Time Paper Awards went to two groundbreaking papers:
1. Generative Adversarial Nets (Goodfellow et al)
2. Sequence to Sequence Learning with Neural Networks (Ilya et al)
Let's explore how these papers helped pioneered breakthroughs in today's AI:
Full Article: https://huggingface.co/blog/Jaward/nip
posted
an
update
17 days ago
Post
624
Lightweight implementation of the seminal paper “Sequence to Sequence Learning with Neural Networks”
Built, trained and eval a 2 layer deep seq2seq LSTM-based model (~10M params) on German-English corpus of Multi30K dataset. In honor of
ilya sutskever et al for winning this year’s NeurIPSConf Test of Time paper award 🫡
Code: https://github.com/Jaykef/ai-algorithms/blob/main/seq2seq.ipynb
Built, trained and eval a 2 layer deep seq2seq LSTM-based model (~10M params) on German-English corpus of Multi30K dataset. In honor of
ilya sutskever et al for winning this year’s NeurIPSConf Test of Time paper award 🫡
Code: https://github.com/Jaykef/ai-algorithms/blob/main/seq2seq.ipynb
posted
an
update
24 days ago
Post
471
Rethinking Backpropagation: Thoughts on What's Wrong with Backpropagation
As a young researcher, I've often pondered the limitations of backpropagation, especially when mapped with how learning occurs in the human brain. While backpropagation has been the workhorse of deep learning, it isn't without flaws. In this post, I aim to share some thoughts on these shortcomings from first principles.
Full article
https://huggingface.co/blog/Jaward/rethinking-backpropagation
As a young researcher, I've often pondered the limitations of backpropagation, especially when mapped with how learning occurs in the human brain. While backpropagation has been the workhorse of deep learning, it isn't without flaws. In this post, I aim to share some thoughts on these shortcomings from first principles.
Full article
https://huggingface.co/blog/Jaward/rethinking-backpropagation
posted
an
update
26 days ago
Post
2409
Implements compute-efficient DeepPCR algorithm which parallelizes sequential operations thus speeding up inference and training of neural networks. DeepPCR can significantly reduce the time complexity in operations such as denoising in latent diffusion space from O(L) to O(log2 L).
Code: https://github.com/Jaykef/ai-algorithms/blob/main/deep_pcr.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/deep_pcr.ipynb
posted
an
update
about 1 month ago
Post
1224
This is supercool!!
Explores o1-like multimodal reasoning.
Multi-agents with DPO is a nice touch 👍
Paper: https://arxiv.org/pdf/2411.14432
Code: https://github.com/dongyh20/Insight-V
Explores o1-like multimodal reasoning.
Multi-agents with DPO is a nice touch 👍
Paper: https://arxiv.org/pdf/2411.14432
Code: https://github.com/dongyh20/Insight-V
posted
an
update
about 1 month ago
Post
1618
Ok RNNs can rap too:)
Here we implement the seminal RNN paper “Generating Text with Recurrent Neural Networks"- we train a character-level multiplicative recurrent neural network model (~250k params) for 1000 epochs with Adam opt on 2pac's "Hit 'em Up", sample was fun lol.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/generating_texts_with_rnns.ipynb
Here we implement the seminal RNN paper “Generating Text with Recurrent Neural Networks"- we train a character-level multiplicative recurrent neural network model (~250k params) for 1000 epochs with Adam opt on 2pac's "Hit 'em Up", sample was fun lol.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/generating_texts_with_rnns.ipynb
posted
an
update
about 1 month ago
Post
1732
Interesting Work on Reasoning 🤔
- explores a new take on few-shot reasoning while challenging assumptions that program synthesis is necessary for abstract reasoning.
- shows test-time training + smart inference tricks can match human-average performance, though at high computational cost. Key insight: proper compute allocation matters more than method (whether symbolic or neural).
Paper: https://ekinakyurek.github.io/papers/ttt.pdf
- explores a new take on few-shot reasoning while challenging assumptions that program synthesis is necessary for abstract reasoning.
- shows test-time training + smart inference tricks can match human-average performance, though at high computational cost. Key insight: proper compute allocation matters more than method (whether symbolic or neural).
Paper: https://ekinakyurek.github.io/papers/ttt.pdf
posted
an
update
about 2 months ago
Post
2102
It's work like this that in some way signal the eventual “dominance” of AI over all the sciences.
“We train our model on the six-dimensional N-body phase space, predicting particle velocities as the time derivative of the model’s displacement outputs”
The emulator is capable of predicting
the nonlinear displacement and velocity fields for 128^3 particles in half a second on a single GPU🤯
“We train our model on the six-dimensional N-body phase space, predicting particle velocities as the time derivative of the model’s displacement outputs”
The emulator is capable of predicting
the nonlinear displacement and velocity fields for 128^3 particles in half a second on a single GPU🤯
- 1 reply
posted
an
update
2 months ago
Post
1743
Triton nanoGPT now has a custom cross entropy loss kernel 🚀
Next: matmul, gradually overthrowing all major PyTorch ops:)
Simplified pseudo for parallel cross-entropy loss compute:
- init program: get pid, compute offsets, load targets.
- init row_max and row_sum.
- for-loop1 (find max logits): update row_max with max logits.
- for-loop2 (compute softmax and loss): compute row_sum, update loss.
- add log(row_sum) and store loss.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/triton_nanoGPT.ipynb
Next: matmul, gradually overthrowing all major PyTorch ops:)
Simplified pseudo for parallel cross-entropy loss compute:
- init program: get pid, compute offsets, load targets.
- init row_max and row_sum.
- for-loop1 (find max logits): update row_max with max logits.
- for-loop2 (compute softmax and loss): compute row_sum, update loss.
- add log(row_sum) and store loss.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/triton_nanoGPT.ipynb
posted
an
update
2 months ago
Post
405
This has to be the first peak performance level use case of a non-autoregressive architecture for TTS. Flow matching for the win!!
Demo: mrfakename/E2-F5-TTS
Model: SWivid/E2-TTS
Demo: mrfakename/E2-F5-TTS
Model: SWivid/E2-TTS
posted
an
update
3 months ago
Post
1153
Lightweight implementation of newly introduced “Differential Transformer”:
Proposes differential attention mechanism which computes attention scores as a difference between two separate softmax attention maps thereby reducing noise in attention blocks. [[[Differential nanoGPT]]] :)
Code: https://github.com/Jaykef/ai-algorithms/blob/main/DIFF_Transformer.ipynb
YT Video: https://youtu.be/9V4mJA5y7dg
Proposes differential attention mechanism which computes attention scores as a difference between two separate softmax attention maps thereby reducing noise in attention blocks. [[[Differential nanoGPT]]] :)
Code: https://github.com/Jaykef/ai-algorithms/blob/main/DIFF_Transformer.ipynb
YT Video: https://youtu.be/9V4mJA5y7dg
reacted to
clem's
post with 👍
3 months ago
Post
4161
Open-source AI creates healthy competition in a field where natural tendencies lead to extreme concentration of power. Imagine a world where only one or two companies could build software. This is the biggest risk and ethical challenge of them all IMO. Let's fight this!
- 3 replies
reacted to
clem's
post with 👍
3 months ago
Post
3709
Very few people realize that most of the successful AI startups got successful because they were focused on open science and open-source for at least their first few years. To name but a few, OpenAI (GPT, GPT2 was open-source), Runway & Stability (stable diffusion), Cohere, Mistral and of course Hugging Face!
The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!
More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!
The reasons are not just altruistic, it's also because sharing your science and your models pushes you to build AI faster (which is key in a fast-moving domain like AI), attracts the best scientists & engineers and generates much more visibility, usage and community contributions than if you were 100% closed-source. The same applies to big tech companies as we're seeing with Meta and Google!
More startups and companies should release research & open-source AI, it's not just good for the world but also increases their probability of success!
- 4 replies
posted
an
update
3 months ago
Post
2585
New hobby: creating AI research paper arts lol, using pymupdf to extract text and add background then animate with runway:) code coming soon…
posted
an
update
3 months ago
Post
373
Triton-accelerated nanoGPT🤕
The WHY behind this ordeal - After practicing triton for about 2 weeks now, I challenged myself into implementing custom triton kernels for Karpathy's nanoGPT and quite an ordeal it was but somehow got something working, not perfect but getting there:), contributions are welcomed.
Code: https://github.com/Jaykef/Triton-nanoGPT
The WHY behind this ordeal - After practicing triton for about 2 weeks now, I challenged myself into implementing custom triton kernels for Karpathy's nanoGPT and quite an ordeal it was but somehow got something working, not perfect but getting there:), contributions are welcomed.
Code: https://github.com/Jaykef/Triton-nanoGPT
posted
an
update
3 months ago
Post
1946
This is supercool!!
LlaVA-3D: adds 3D-awareness to LVMs without compromising 2D understanding capabilities.
Method: they developed a unified architecture that maps 2D clip patch features to their corresponding positions in 3D space - enabling joint 2D and 3D vision-language instruction tuning.
Project: https://zcmax.github.io/projects/LLaVA-3D/
LlaVA-3D: adds 3D-awareness to LVMs without compromising 2D understanding capabilities.
Method: they developed a unified architecture that maps 2D clip patch features to their corresponding positions in 3D space - enabling joint 2D and 3D vision-language instruction tuning.
Project: https://zcmax.github.io/projects/LLaVA-3D/
posted
an
update
3 months ago
Post
1340
Some interesting findings in this paper:
- They consider o1 a Large Reasoning Model (LRM) with a different arch from SOTA LLMs.
- Creative justifications: “It is almost as if o1 has gone from hallucinating to gaslighting!”. This is so true, I noticed also it can “hallucinate” its chain-of-thoughts lol.
- Accuracy/Cost Tradeoffs: o1 provides high accuracy but at significant computational and monetary costs due to hidden "reasoning tokens."
Paper: https://www.arxiv.org/abs/2409.13373
- They consider o1 a Large Reasoning Model (LRM) with a different arch from SOTA LLMs.
- Creative justifications: “It is almost as if o1 has gone from hallucinating to gaslighting!”. This is so true, I noticed also it can “hallucinate” its chain-of-thoughts lol.
- Accuracy/Cost Tradeoffs: o1 provides high accuracy but at significant computational and monetary costs due to hidden "reasoning tokens."
Paper: https://www.arxiv.org/abs/2409.13373
posted
an
update
3 months ago
Post
1488
nanoGPT with Sigmoid Self-Attention
I couldn’t resist had to give it a try:)
Some observations on M2:
SSA was ~5-10% faster in training with similar final loss values, slightly less coherent text generation, marginally higher perplexity, and lower memory usage compared to softmax.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/sigmoid_attn.ipynb
I couldn’t resist had to give it a try:)
Some observations on M2:
SSA was ~5-10% faster in training with similar final loss values, slightly less coherent text generation, marginally higher perplexity, and lower memory usage compared to softmax.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/sigmoid_attn.ipynb