Machine Learning RSS Feeds

Directory236 machine learning feeds · 385 articlesShow all languages →

Latest

Machine Learning articles

Parcae: A Stable Looped Language Model Architecture with Predictable Scaling Laws

Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential alternative is looped architectures, which instead increase F

Insighttechnologysciencemachine learning

arxiv.org·Twitter AI (high signal)·5h ago·2 min read

Swordfish: Blackwell-Native GEMM Kernel Family for GPU Inference (PR #1707)

Codetechnologymachine learning

Shared by @QuixiAI ↗

github.com6h ago

Jenga: A Memory Allocation Framework for Heterogeneous LLM Inference

Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory efficiently is crucial. While PagedAttention has recently been proposed to

Insighttechnologyscience

Shared by @vllm_project ↗

arxiv.org6h ago

GFlowRL: A Scalable Distribution-Matching RL Algorithm for Large Language Models

Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes.

Insighttechnologyscience

Shared by @dair_ai ↗

arxiv.org12h ago

Detecting LLM-Generated Fiction Using Classical Machine Learning: Statistical Patterns in AI Text

.admonition { margin: .75em 0; padding: .6rem; overflow: hidden; font-size: 12px; page-break-inside: avoid; border-left: .3rem solid #42b983; border-radius: .3rem; box-shadow: 0 0.1re

Insighttechnologymachine learningprogramming

blog.lyc8503.net·Hacker News: Front Page·13h ago·13 min read

WaterMoE: A Low-Overhead Watermarking Method for Mixture-of-Experts LLMs

Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these techniques have rarely been adopted in practice mainly f

Insighttechnologyscienceartificial intelligence

arxiv.org·Tech by Flipboard·13h ago·2 min read

OAT: An Efficient Unsupervised Method for Failure Attribution in LLM Agentic Systems

Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which ar

Insighttechnologysciencemachine learning

arxiv.org·Twitter AI (high signal)·1d ago·2 min read