Our picks for October’s Papers of the Month are here. Out of 49 shortlisted papers, we spotlight 4 that stand out for their clever ideas on making #LLMs faster, smarter, and more efficient! 📊 First up, Grouped Lattice Vector Quantisation introduces a novel technique for a

✨ Check out our summaries and follow our blog ✨

Learn more by signing up here!

LLM using too many reasoning tokens? 😕 Generation slow? 🐌 Or simply too many steps before EOS? 🪜🪜🪜 Douglas Orr (@douglasahorr), our beloved research scientist, has got you covered! He will tell you the remedies to all of the above in the shortest time possible. Registration

✨ https://t.co/USO1ctukVr ✨

September's Papers of the Month is here, and this month is all about LLMs! 🧠 Out of all papers released this month, our editor @robhu92 has curated: 📊 "FlowRL: Matching Reward Distributions for LLM Reasoning“ (review by @samot_gc): A clever usage of #GFlowNets to align an #RL

Finally, Graph-R1 is another addition to the stack of agentic RAG approaches, but this time, using knowledge hypergraphs! Summary:

Next, Guiding Diffusion Models with RL for Stable Molecule Generation introduces reinforcement learning with physical feedback to accomplish exactly as its name suggests! Summary:

First up, ADMIRE-BayesOpt addresses the question of finding the optimal mixture of multiple datasets. And the answer, sequential iterative search using Multi-Fidelity Bayesian Optimization! Summary:

Summer may be over, but Papers of the Month certainly isn’t! For August’s edition, we covered the following papers: ➡️ ADMIRE-BayesOpt ➡️ Guiding Diffusion Models with RL for Stable Molecule Generation ➡️ Graph-R1 🧵

Finally, DataRater addresses dataset quality: a ‘rater’ is meta-learned to curate training data without manual filtering. Summary:

Mixture of Recursions brings a twist to token-level computation: the model learns to recurse adaptively, allocating compute per token dynamically. Summary:

First up, Subliminal Learning explores a question in model distillation: “Can we control so that a student learns desirable, but avoids undesirable, traits?” Summary:

July's Papers of the Month are here! 🧠 Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data 💽 Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation 📊 DataRater: Meta-Learned Dataset Curation 🧵⬇️

That's all for this month! To keep up with our monthly summaries, blog posts, and new research, follow us on @GCResearchTeam or subscribe here: https://t.co/YgQxvhvgHT

For additional information, check out these excellent threads by the original authors ⬇️ @aaron_defazio https://t.co/eDTPNzuO3X @shizhediao https://t.co/v8GpDQjdOH @peter9863 https://t.co/lSsU0aOiku

Finally, we look at AAPT, a fresh approach from the ByteDance Seed team that turns pre-trained offline diffusion models into real-time video generators via adversarial post-training. https://t.co/zeurS9U1ro

Next, in ProRL, NVIDIA researchers dive into the evolving topic of large language model reasoning, showing how prolonged reinforcement learning can indeed introduce novel reasoning abilities. https://t.co/YOlLuVyj8B

Firstly, a researcher from FAIR explores the puzzling phenomenon of increasing gradient magnitudes during training, offering an elegant mathematical explanation and a simple remedy. https://t.co/zSryHkH07B

It's time for June's Papers of the Month! This time, we cover: ➡️Why Gradients Rapidly Increase Near the End of Training ➡️ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries ➡️Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation 🧵