Machine Learning

ML algorithms, training, and inference

This Week's Best | Monthly Best | Guide | Trending

Top This Week

Machine learning analysis of CT scans
Machine Learning

Machine learning analysis of CT scans

An AI-powered tool can interpret 3D images from CT scans and diagnose certain disorders.

AI News - General · 5 min ·
Teaching AI models to say “I’m not sure”
Machine Learning

Teaching AI models to say “I’m not sure”

MIT CSAIL's “Reinforcement Learning with Calibration Rewards” technique improves AI confidence estimates without sacrificing perform...

AI News - General · 7 min ·
Accelerating science with AI and simulations
Machine Learning

Accelerating science with AI and simulations

MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...

AI News - General · 10 min ·

All Content

[2604.01740] DDCL: Deep Dual Competitive Learning: A Differentiable End-to-End Framework for Unsupervised Prototype-Based Representation Learning
Machine Learning

[2604.01740] DDCL: Deep Dual Competitive Learning: A Differentiable End-to-End Framework for Unsupervised Prototype-Based Representation Learning

Abstract page for arXiv paper 2604.01740: DDCL: Deep Dual Competitive Learning: A Differentiable End-to-End Framework for Unsupervised Pr...

arXiv - Machine Learning · 4 min ·
[2604.01730] Koopman-Based Nonlinear Identification and Adaptive Control of a Turbofan Engine
Machine Learning

[2604.01730] Koopman-Based Nonlinear Identification and Adaptive Control of a Turbofan Engine

Abstract page for arXiv paper 2604.01730: Koopman-Based Nonlinear Identification and Adaptive Control of a Turbofan Engine

arXiv - Machine Learning · 4 min ·
[2604.01727] MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction
Machine Learning

[2604.01727] MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction

Abstract page for arXiv paper 2604.01727: MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction

arXiv - Machine Learning · 3 min ·
[2604.01712] Transformer self-attention encoder-decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring
Machine Learning

[2604.01712] Transformer self-attention encoder-decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring

Abstract page for arXiv paper 2604.01712: Transformer self-attention encoder-decoder with multimodal deep learning for response time seri...

arXiv - Machine Learning · 4 min ·
[2604.01694] MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning
Llms

[2604.01694] MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning

Abstract page for arXiv paper 2604.01694: MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning

arXiv - Machine Learning · 3 min ·
[2604.01683] Coupled Query-Key Dynamics for Attention
Llms

[2604.01683] Coupled Query-Key Dynamics for Attention

Abstract page for arXiv paper 2604.01683: Coupled Query-Key Dynamics for Attention

arXiv - Machine Learning · 4 min ·
[2604.01653] Cognitive Energy Modeling for Neuroadaptive Human-Machine Systems using EEG and WGAN-GP
Machine Learning

[2604.01653] Cognitive Energy Modeling for Neuroadaptive Human-Machine Systems using EEG and WGAN-GP

Abstract page for arXiv paper 2604.01653: Cognitive Energy Modeling for Neuroadaptive Human-Machine Systems using EEG and WGAN-GP

arXiv - Machine Learning · 4 min ·
[2604.01651] Label Shift Estimation With Incremental Prior Update
Machine Learning

[2604.01651] Label Shift Estimation With Incremental Prior Update

Abstract page for arXiv paper 2604.01651: Label Shift Estimation With Incremental Prior Update

arXiv - Machine Learning · 4 min ·
[2604.01634] CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning
Machine Learning

[2604.01634] CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning

Abstract page for arXiv paper 2604.01634: CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning

arXiv - Machine Learning · 3 min ·
[2604.01622] Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
Llms

[2604.01622] Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

Abstract page for arXiv paper 2604.01622: Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

arXiv - Machine Learning · 4 min ·
[2604.01613] Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error
Machine Learning

[2604.01613] Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error

Abstract page for arXiv paper 2604.01613: Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error

arXiv - Machine Learning · 4 min ·
[2604.01601] Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling
Llms

[2604.01601] Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling

Abstract page for arXiv paper 2604.01601: Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling

arXiv - Machine Learning · 4 min ·
[2604.01597] Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training
Llms

[2604.01597] Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training

Abstract page for arXiv paper 2604.01597: Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training

arXiv - Machine Learning · 3 min ·
[2604.01595] Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach
Machine Learning

[2604.01595] Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach

Abstract page for arXiv paper 2604.01595: Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Superv...

arXiv - Machine Learning · 4 min ·
[2604.01587] Variational LSTM with Augmented Inputs: Nonlinear Response History Metamodeling with Aleatoric and Epistemic Uncertainty
Machine Learning

[2604.01587] Variational LSTM with Augmented Inputs: Nonlinear Response History Metamodeling with Aleatoric and Epistemic Uncertainty

Abstract page for arXiv paper 2604.01587: Variational LSTM with Augmented Inputs: Nonlinear Response History Metamodeling with Aleatoric ...

arXiv - Machine Learning · 4 min ·
[2604.01577] Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
Machine Learning

[2604.01577] Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling

Abstract page for arXiv paper 2604.01577: Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling

arXiv - Machine Learning · 3 min ·
[2604.01576] Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents
Llms

[2604.01576] Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents

Abstract page for arXiv paper 2604.01576: Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents

arXiv - Machine Learning · 3 min ·
[2604.01552] ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor
Machine Learning

[2604.01552] ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

Abstract page for arXiv paper 2604.01552: ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor

arXiv - Machine Learning · 3 min ·
[2604.01506] Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking
Machine Learning

[2604.01506] Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking

Abstract page for arXiv paper 2604.01506: Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking

arXiv - Machine Learning · 4 min ·
[2604.01499] Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training
Llms

[2604.01499] Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

Abstract page for arXiv paper 2604.01499: Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

arXiv - Machine Learning · 4 min ·
Previous Page 240 Next

Related Topics

Large Language Models Generative AI Natural Language Processing Computer Vision Robotics & Embodied AI AI Safety & Ethics

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime