🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

"RL with only one training example" and "Test-Time RL" are two recent papers that I found fascinating. In the "One Training example" paper the authors find one question and ask the model to solve it again and again. Every time, the model tries 8 times (the Group in GRPO), and

11 alignment and optimization algorithms for LLMs ▪️ PPO (Proximal Policy Optimization) ▪️ DPO (Direct Preference Optimization) ▪️ GRPO (Group Relative Policy Optimization) ▪️ DAPO (Decoupled Clip and Dynamic sAmpling Policy Optimization) ▪️ AMPO (Active Multi-Preference

we get a lot of questions about which model to use in Cursor, so we put together a guide on how you can think about selecting models based on what we've seen work well

People aren’t talking enough about how most of OpenAI’s tech stack runs on Python.

SFT Qwen3 without lossing thinking capabilities - from official qwen doc: qwen.readthedocs.io/en/latest/trai…

Adapting pretrained LLMs for vision tasks often degrades their language abilities or requires full retraining. X-Fusion introduces a dual-tower design. It freezes LLM weights, adding a trainable vision tower. This enables multimodal tasks while preserving original language

🐂🍺Introducing our recent preprint: Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training! We present PRIOR, a simple vision-language pre-training algorithm that addresses the challenge of irrelevant textual content in image-caption pairs. PRIOR enhances

J1 just launched on Hugging Face A Reinforcement Learning recipe for training Thinking-LLM-as-a-Judge models. It trains J1-Llama-8B and J1-Llama-70B that outperform existing models.

Could a major opportunity to improve representation in deep learning be hiding in plain sight? Check out our new position paper: Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis. The idea stems from a little-known

I am pleased to announce a new version of my RL tutorial. Major update to the LLM chapter (eg DPO, GRPO, thinking), minor updates to the MARL and MBRL chapters and various sections (eg offline RL, DPG, etc). Enjoy! arxiv.org/abs/2412.05265

it's been more than a decade since KD was proposed, and i've been using it all along .. but why does it work? too many speculations but no simple explanation. Sungmin Cha and i decided to see if we can come up with the simplest working description of KD in this work. we ended

🚨 Paper Alert: “RL Finetunes Small Subnetworks in Large Language Models” From DeepSeek V3 Base to DeepSeek R1 Zero, a whopping 86% of parameters were NOT updated during RL training 😮😮 And this isn’t a one-off. The pattern holds across RL algorithms and models. 🧵A Deep Dive

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets Presents an autoregressive U-Net that processes raw bytes and learns hierarchical token representation Matches strong BPE baselines, with deeper hierarchies demonstrating promising scaling trends

Understanding and Coding KV Caching From Scratch -- The Extended Edition magazine.sebastianraschka.com/p/coding-the-k…

Ok a few quick things. Most CS students who get into elite PhD programs in AI especially have already usually published multiple first author papers in "top" conferences. 1/

We made a Guide on mastering LoRA Hyperparameters, so you can learn to fine-tune LLMs correctly! Learn to: • Train smarter models with fewer hallucinations • Choose optimal: learning rates, epochs, LoRA rank, alpha • Avoid overfitting & underfitting 🔗docs.unsloth.ai/get-started/fi…

went through this but don't just only skim over it ig. every question is a good research paper and worth a read.

What’s really going on inside LLMs when they handle non-English queries? Niyati Bafna's recent work introduces the **translation barrier hypothesis**, a framework for understanding multilingual model behavior. This hypothesis says that : (1) Multilingual generation, internally,

Reinforcement Learning of Large Language Models, Spring 2025(UCLA) Great set of new lectures on reinforcement learning of LLMs. Covers a wide range of topics related to RLxLLMs such as basics/foundations, test-time compute, RLHF, and RL with verifiable rewards(RLVR).

Stop optimizing your retrieval. Fix your chunking first. It's not your embedding model, prompt engineering, or vector database. It's your chunking strategy creating invisible walls between your users and the information they need. 𝗖𝗵𝘂𝗻𝗸𝗶𝗻𝗴 is the pre-processing step of