This page shows the most relevant public items for cs.LG, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Feb 16, 2026 • arXiv • MiniMax Research Team
Training agents for industrial-scale deployment requires extreme stability and data throughput. We present Minimax M2.5, a model trained using a novel asynchronous RL architecture designed to proce...
Paper • Feb 19, 2026 • arXiv • Xiaoliang Fu, Jiaye Lin, Yangyi Fang
Policy optimization for Large Language Models often suffers from gradient instability and reward signal unreliability, particularly in mathematical and verifiable reasoning tasks. We introduce MASP...
Paper • Feb 18, 2026 • arXiv • Adam Zweiger, Xinghong Fu, Han Guo, MIT Team
Large Language Models struggle with memory overhead during long-context inference due to the linear growth of the Key-Value (KV) cache. We propose Attention Matching (AM), a framework for high-qual...
Paper • Feb 19, 2026 • arXiv • Yue Liu, Zhiyuan Hu, Flood Sung
Current LLM agents frequently fail in tasks requiring hundreds of steps due to error accumulation and context overflow. We introduce KLong, an agentic framework that utilizes 'Trajectory-Splitting ...
Paper • Feb 17, 2026 • arXiv • Moritz Miller, Florent Draye, Bernhard Schölkopf
This paper addresses the fundamental challenge of 'feature disentanglement' in modern deep learning. We propose an Orthogonality Regularization technique to identify features that are both interpre...
Paper • Feb 19, 2015 • arXiv • John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, Philipp Moritz
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical ...
Paper • Dec 8, 2021 • arXiv • Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Eleni Elia, Danilo J. Rezende, Vinyals, Simonyan
Language modelling provides a step towards intelligent communication systems by harnessing large datasets and expressive models. We provide an analysis of Transformer-based language model architect...
Paper • Feb 4, 2016 • arXiv • Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present as...
Paper • May 12, 2022 • arXiv • Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez Colmenarejo, Nando de Freitas
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato,...
Paper • Feb 21, 2026 • arXiv • Zhixuan Fang, Yisong Yue, Anima Anandkumar
Long-horizon autonomous agents suffer from 'context rot,' a phenomenon where the accumulation of irrelevant interaction history severely degrades the model's reasoning capabilities over time. We pr...
Paper • Feb 4, 2026 • arXiv • Fan Yang, Rui Meng, Trudi Di Qi, Ali Ezzati, Yuxin Wen
Direct Preference Optimization (DPO) and its variants have revolutionized LLM alignment, yet they struggle when the preferred choice requires deep, multi-step reasoning. We introduce KEPO, a framew...
Paper • Feb 13, 2026 • arXiv • Miaosen Zhang, Xu Yang, Qi Dai, Chong Luo
Supervised fine-tuning (SFT) is efficient but often yields inferior generalization compared to RL, a gap driven by RL's use of on-policy data. We propose a framework to bridge this chasm by enablin...
Paper • Feb 8, 2026 • arXiv • Fan Yang, Rui Meng, Trudi Di Qi, Yuxin Wen
We argue that while replacing data with model parameters characterizes the present of Federated Learning (FL), replacing parameters with preferences represents a more scalable and privacy-preservin...
Paper • Feb 12, 2026 • arXiv • Xiaoxiao Wang, Chunxiao Li, Junying Wang, Zicheng Zhang
The paper introduces STAR (STatistical and Agentic Reasoning), a novel framework designed to predict the performance of large models across diverse benchmarks from limited observations. Existing st...
Paper • Feb 12, 2026 • arXiv • Yurong Chen, Yu He, Michael I. Jordan, Fan Yao
Modern language agents must operate over long-horizon, multi-turn interactions, but most rely on full-context prompting which leads to unbounded memory growth. We introduce MEM1, an end-to-end rein...
Paper • Feb 8, 2026 • arXiv • Hao Li, Richard Peng, Sanjit Singh, Gregory D. Lyng
SkillRL is a framework that enables LLM agents to learn high-level, reusable behavioral patterns from past experiences. While traditional memory-based methods store redundant and noisy raw trajecto...
Paper • Feb 13, 2026 • arXiv • Zhiwei Liu, Yuan He, Hao Peng, Zhiqiang Chen
Recently, diffusion LLMs have emerged as a promising alternative to autoregressive models. Diffusion LLMs address traditional limitations with two advances, including multi-token prediction (i.e., ...
It ranks public content for cs.LG using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to cs.LG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to cs.LG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to cs.LG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to cs.LG topic page on Attendemia and is written so it still makes sense without reading other sections on the page.