oh hey guys...

Has anyone successfully done RL post-training of GPT-oss with meaningful performance gains? What libraries even support it? I guess technically TRL/axolotl, maybe Unsloth... but there are no good examples of doing it...

I have EXCITING news: I've started a company! Introducing Sophont We’re building open multimodal foundation models for the future of healthcare. We need a DeepSeek for medical AI, and @sophontai.bsky.social will be that company! Check out our website & blog post for more info (link below)

NEW BLOG POST: LLMs in medicine: evaluations, advances, and the future www.tanishq.ai/blog/posts/l... A short blog post discussing how LLMs are evaluated for medical capabilities and what's the future for LLMs in medicine (spoiler: it's reasoning!)

I restarted my blog a few weeks ago. The 1st post was: Debunking DeepSeek Delusions I discussed 5 main myths that I saw spreading online back during the DeepSeek hype. It may be a little less relevant now, but hopefully still interesting to folks. Check it out → www.tanishq.ai/blog/posts/d...

Are folks still here? 😅

Okay so this is so far the most important paper in AI of the year

Anthropic, please add a higher tier plan for unlimited messages 😭🙏

Decentralized Diffusion Models UC Berkeley and Luma AI introduce Decentralized Diffusion Models, a way to train diffusion models on decentralized compute with no communication between nodes. abs: arxiv.org/abs/2501.05450 project page: decentralizeddiffusion.github.io

The GAN is dead; long live the GAN! A Modern Baseline GAN This is a very interesting paper, exploring making GANs simpler and more performant. abs: arxiv.org/abs/2501.05441 code: github.com/brownvc/R3GAN

Happy birthday to my incredible and awesome Mamma! 🥳🎉🎂 To many more years of health and happiness. Tiara (my sister) and I love you very much ❤️❤️❤️

Happy 19th birthday to my amazing sister Tiara Abraham! 🥳🎉 🎂 Proud of you graduating with your Master's degree at 18 and starting your doctorate in music degree this past year! Excited to see what this final teen year holds for you!

Inventors of flow matching have released a comprehensive guide going over the math & code of flow matching! Also covers variants like non-Euclidean & discrete flow matching. A PyTorch library is also released with this guide! This looks like a very good read! 🔥 arxiv: arxiv.org/abs/2412.06264

Normalizing Flows are Capable Generative Models Apple introduces TarFlow, a new Transformer-based variant of Masked Autoregressive Flows. SOTA on likelihood estimation for images, quality and diversity comparable to diffusion models. arxiv.org/abs/2412.06329

Normalizing Flows are Capable Generative Models

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relati...

arxiv.org

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models "We introduce a simple strategy that makes refusal behavior controllable at test-time without retraining: the refusal token." arxiv.org/abs/2412.06748

Can foundation models actively gather information in interactive environments to test hypotheses? "Our experiments with Gemini 1.5 reveal significant exploratory capabilities" arxiv.org/abs/2412.06438

Training Large Language Models to Reason in a Continuous Latent Space Introduces a new paradigm for LLM reasoning called Chain of Continuous Thought (COCONUT) Directly feed the last hidden state (a continuous thought) as the input embedding for the next token. arxiv.org/abs/2412.06769

[MASK] is All You Need New paper from CompVis group, introduces a new method called Discrete Interpolants that builds on top of discrete flow matching. Achieves SOTA performance on MS-COCO, competitive results on ImageNet 256. arxiv.org/abs/2412.06787

A new tutorial on RL by Kevin Patrick Murphy, a Research Scientist at Google DeepMind who also wrote several comprehensive, well-regarded textbooks on ML/DL. This ought to be a good read 👀 arxiv.org/abs/2412.05265

Birth and Death of a Rose abs: arxiv.org/abs/2412.05278 Generating temporal object intrinsics - temporally evolving sequences of object geometry, reflectance, and texture, such as blooming of a rose - from pre-trained 2D foundation models.

Frontier Models are Capable of In-context Scheming abs: arxiv.org/abs/2412.04984 "Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities"

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks abs: arxiv.org/abs/2412.04626 project page: bigdocs.github.io BigDocs-7.5M is a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks.

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling abs: arxiv.org/abs/2412.05271 model: huggingface.co/OpenGVLab/In... Introduces new InternVL-2.5 model, the first open-source MLLMs to surpass 70% on the MMMU benchmark

NVILA: Efficient Frontier Visual Language Models abs: arxiv.org/abs/2412.04468 NVIDIA introduces NVILA, a family of open VLMs designed to optimize both efficiency and accuracy.

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis abs: arxiv.org/abs/2412.04431 New visual autoregression framework that performs bitwise token prediction w/ an infinite-vocabulary tokenizer & classifier, a new record for autoregressive text-to-image models.

🤔 Why do we extract diffusion features from noisy images? Isn’t that destroying information? Yes, it is - but we found a way to do better. 🚀 Here’s how we unlock better features, no noise, no hassle. 📝 Project Page: compvis.github.io/cleandift 💻 Code: github.com/CompVis/clea... 🧵👇

Leading computer vision researchers Lucas Beyer (@giffmana.ai), Alexander Kolesnikov (@kolesnikov.ch), Xiaohua Zhai have left Google DeepMind to join OpenAI! They were behind recent SOTA vision approaches and open-source models like ViT, SigLIP, PaliGemma

The AI winter has started 😔

the restrictions on post and video length is gonna make it harder to paper-post here ngl

Reverse Thinking Makes LLMs Stronger Reasoners abs: arxiv.org/abs/2411.19865 Train an LLM to be able to generate forward reasoning from question, backward question, and backward reaoning from backward question Shows an average 13.53% improvement over the student model’s zero-shot performance