Machine Learning RSS Feeds

Directory250 machine learning feeds · 411 articlesShow all languages →

Latest

Machine Learning articles

Improving Binary Code Representation Learning Through Instruction Alignment Training

Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largel

Insighttechnologycybersecuritymachine learning

arxiv.org·Tech by Flipboard·3d ago·2 min read

Study Finds Refusal Behavior in LLMs Is Concentrated in MLP Layers and Mid-Network Blocks

Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters. This work addresses where safety-a

Insighttechnologyscience

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

arxiv.org3d ago

Twelve practical guidelines for applying deep learning to bioacoustic animal sound analysis

technologyscience

Shared by @bffo.bsky.social ↗

journals.plos.org3d ago

The shared principle behind data compression and large language models

Insighttechnologymachine learning

ngrok.com5d ago

Georgia Tech Student Shares NFL Run/Pass Prediction Data Mining Project

Research paper on methods to model a prediction on whether an offense is running or passing the ball.

Insighteducationsportsmachine learning

adityaanalytics.substack.com·Tech by Flipboard·8d ago·2 min read

Echoverse: A System for Generating Deep, Co-Evolving Synthetic Environments to Train Computer-Use Agents

Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and stateful, so synthetic environments stand in for them. Recent pipelines gene

Insighttechnologyartificial intelligencemachine learning

arxiv.org·Tech by Flipboard·16d ago·2 min read

OpenADMET: Building machine learning models for toxicity and ADME prediction through measured data

“Quantity has a quality all of its own” Original source unknown The quote with which I’ve opened the post on the OpenADMET initiative is of...

Insighttechnologysciencemachine learning

fbdd-lit.blogspot.com·Science·18d ago·15 min read

GROCLM: A Fine-Tuned Language Model for Grocery Category Recommendation in E-Commerce

The rapid growth of online grocery shopping requires recommendation systems that capture cyclical purchasing behavior and diverse user intents. Traditional item-level methods face scalability and accuracy challenges, motivating category-level recommendati

Insighttechnologyscience

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

arxiv.org18d ago

Compiler-Grounded Hierarchical Diagnosis Framework Achieves 4.35× Speedup for LLM-Based Triton Kernel Optimization on NPUs

Recent advances in large language models (LLMs) have enabled automated kernel generation and optimization, but most existing approaches rely on surface signals such as compilation feedback and profiling metrics. These signals reveal that a kernel is slow

Insighttechnologymachine learning

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

arxiv.org18d ago

JAXBench: A TPU-Native Benchmark Suite for AI-Driven Kernel Optimization

Rigorous benchmarks have driven progress in autonomous GPU kernel performance optimization by establishing a shared target to hillclimb on, but no equivalent exists for TPUs. We present JAXBench, a TPU-native benchmark suite for AI-generated kernel optimi

Insighttechnologymachine learning

Shared by @ai-firehose.column.social ↗

arxiv.org21d ago

How I Became a Research Engineer at Mistral: A Strategic Career Journey in Machine Learning

Insighttechnologyeducation

maxmynter.com22d ago

Routing Between Kimi K3 and Fable 5 Achieves State-of-the-Art Results at Fraction of Cost

Insighttechnologymachine learning

fireworks.ai26d ago

SALR: A Sparsity-Aware Low-Rank Fine-Tuning Method That Reduces LLM Model Size by 2x While Maintaining Performance

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation (LoRA) reduces trai

Insighttechnologyscience

Shared by @ai-firehose.column.social ↗

arxiv.org26d ago

BONSAI: Optimizing Decoding Tries for LLM-Based Generative Recommendation

Generative recommendation (GR) is an increasingly popular paradigm in recommender systems, with a prominent line of work using LLMs as autoregressive backbones to predict the next item's term IDs (e.g., titles or keywords). The success of autoregressive g

Insighttechnologysciencemachine learning

arxiv.org·Tech by Flipboard·26d ago·2 min read

UAME: An Uncertainty-Aware Framework to Mitigate Satisfaction Label Bias in Short Video Recommendation Ranking

The core objective of short video recommendation is to model users' unobservable true satisfaction with recommended videos. As the dominant industrial framework, end-to-end multi-objective ensemble ranking models are typically trained with multi-dimension

Newstechnologyscience

Shared by @reachsumit.com ↗

arxiv.org26d ago

The Anatomy of AI: A Developer's Field Guide to Neural Networks, Transformers, and Reasoning Models

Insighttechnologyartificial intelligence

Shared by @hackernoon.com ↗

hackernoon.com26d ago

OpenAI's GPT-5.6 Introduces Multi-Level Reasoning Effort Controls for LLMs

Insighttechnologymachine learning

magazine.sebastianraschka.com27d ago

lora-speedrun: A public leaderboard for competitive LoRA fine-tuning speed on Qwen2.5-1.5B with GSM8K

Codetechnologymachine learning

github.com27d ago

Towards Data Science3

s3.us-east-1.amazonaws.com19

BenchLM3

Latest AI & ML News, Insights, and Trends - Times of AI7

MachineLearningMastery6

arxiviq.substack.com2

s3.ap-southeast-2.amazonaws.com5

Analytics Vidhya4

vLLM3

buildfastwithai.com1

PyTorch12

aichatdaily.com3

AImagazine1

neuralbuddies.com2

neurips.cc16

theaiaura.com1

nb-data.com3

theaiinnovator.com1

metr.org1

ICML5

LM Studio1

Owl Posting2

vanderschaar-lab.com4

PixLab133

proceedings.mlr.press3

leehanchung.github.io2

TensorFlow2

sander.ai2

sites.bu.edu1

Machine Learning Street Talk1

Stack Abuse1

Improving Binary Code Representation Learning Through Instruction Alignment Training

Study Finds Refusal Behavior in LLMs Is Concentrated in MLP Layers and Mid-Network Blocks

Twelve practical guidelines for applying deep learning to bioacoustic animal sound analysis

The shared principle behind data compression and large language models

Georgia Tech Student Shares NFL Run/Pass Prediction Data Mining Project

Echoverse: A System for Generating Deep, Co-Evolving Synthetic Environments to Train Computer-Use Agents

OpenADMET: Building machine learning models for toxicity and ADME prediction through measured data

GROCLM: A Fine-Tuned Language Model for Grocery Category Recommendation in E-Commerce

Compiler-Grounded Hierarchical Diagnosis Framework Achieves 4.35× Speedup for LLM-Based Triton Kernel Optimization on NPUs

JAXBench: A TPU-Native Benchmark Suite for AI-Driven Kernel Optimization

How I Became a Research Engineer at Mistral: A Strategic Career Journey in Machine Learning

Routing Between Kimi K3 and Fable 5 Achieves State-of-the-Art Results at Fraction of Cost

SALR: A Sparsity-Aware Low-Rank Fine-Tuning Method That Reduces LLM Model Size by 2x While Maintaining Performance

BONSAI: Optimizing Decoding Tries for LLM-Based Generative Recommendation

UAME: An Uncertainty-Aware Framework to Mitigate Satisfaction Label Bias in Short Video Recommendation Ranking

The Anatomy of AI: A Developer's Field Guide to Neural Networks, Transformers, and Reasoning Models

OpenAI's GPT-5.6 Introduces Multi-Level Reasoning Effort Controls for LLMs

lora-speedrun: A public leaderboard for competitive LoRA fine-tuning speed on Qwen2.5-1.5B with GSM8K