Machine Learning RSS Feeds

Directory247 machine learning feeds · 390 articlesEnglish only →

Latest

Machine Learning articles

Artificial Scientists That Self-Invent Experiments Through Neural Networks

There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given questions, but also continually invent new questions, by proposing hypothese

Insighteducationsciencemachine learning

arxiv.org·Twitter AI·13h ago·2 min read

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

Insighttechnologyscience

Shared by @realDanFu ↗

arxiv.org18h ago

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

Codetechnologymachine learning

Shared by @QuixiAI ↗

github.com20h 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.org20h 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.

Insighttechnologyscienceartificial intelligence

arxiv.org·Twitter AI·1d ago·2 min read

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·1d 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·1d ago·2 min read

OriginBlame: A Record-Level Data Provenance System for Precise AI Training Data Removal

When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author. Existing provenance systems operate at file or dataset level

Insighttechnologyscience

Shared by @arxiv-daily-bot.bsky.social ↗

arxiv.org1d ago

A Step-by-Step Guide to Your First Machine Learning Project in Python

technologyeducation

Shared by @gp_pulipaka ↗

geni.us1d ago

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

Insighttechnologyscience