Content Feed

The latest content from across the network

Ranked Latest Top this week
[2604.00830] Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Machine Learning

[2604.00830] Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

Abstract page for arXiv paper 2604.00830: Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

arXiv - Machine Learning · 4 min ·
[2604.00821] Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation
Llms

[2604.00821] Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation

Abstract page for arXiv paper 2604.00821: Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation

arXiv - Machine Learning · 3 min ·
[2604.00812] Cost-Penalized Fitness in FMA-Orchestrated Mixture of Experts: Experimental Evidence for Molecular Memory in Domain Adaptation
Llms

[2604.00812] Cost-Penalized Fitness in FMA-Orchestrated Mixture of Experts: Experimental Evidence for Molecular Memory in Domain Adaptation

Abstract page for arXiv paper 2604.00812: Cost-Penalized Fitness in FMA-Orchestrated Mixture of Experts: Experimental Evidence for Molecu...

arXiv - Machine Learning · 3 min ·
[2604.00785] Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer
Llms

[2604.00785] Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer

Abstract page for arXiv paper 2604.00785: Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer

arXiv - AI · 4 min ·
[2604.00801] Routing-Free Mixture-of-Experts
Machine Learning

[2604.00801] Routing-Free Mixture-of-Experts

Abstract page for arXiv paper 2604.00801: Routing-Free Mixture-of-Experts

arXiv - AI · 3 min ·
[2604.00800] MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning
Machine Learning

[2604.00800] MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning

Abstract page for arXiv paper 2604.00800: MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological...

arXiv - Machine Learning · 4 min ·
[2604.00779] Using predefined vector systems to speed up neural network multimillion class classification
Machine Learning

[2604.00779] Using predefined vector systems to speed up neural network multimillion class classification

Abstract page for arXiv paper 2604.00779: Using predefined vector systems to speed up neural network multimillion class classification

arXiv - Machine Learning · 4 min ·
[2604.00770] Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
Llms

[2604.00770] Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning

Abstract page for arXiv paper 2604.00770: Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning

arXiv - AI · 4 min ·
[2604.00767] ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
Machine Learning

[2604.00767] ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding

Abstract page for arXiv paper 2604.00767: ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding

arXiv - Machine Learning · 4 min ·
[2604.00739] BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction
Machine Learning

[2604.00739] BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction

Abstract page for arXiv paper 2604.00739: BioCOMPASS: Integrating Biomarkers into Transformer-Based Immunotherapy Response Prediction

arXiv - AI · 3 min ·
[2604.00698] Learning to Hint for Reinforcement Learning

[2604.00698] Learning to Hint for Reinforcement Learning

Abstract page for arXiv paper 2604.00698: Learning to Hint for Reinforcement Learning

arXiv - AI · 4 min ·
[2604.00733] Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction
Llms

[2604.00733] Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction

Abstract page for arXiv paper 2604.00733: Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and S...

arXiv - Machine Learning · 4 min ·
[2604.00689] Performance of Neural and Polynomial Operator Surrogates
Machine Learning

[2604.00689] Performance of Neural and Polynomial Operator Surrogates

Abstract page for arXiv paper 2604.00689: Performance of Neural and Polynomial Operator Surrogates

arXiv - Machine Learning · 4 min ·
[2604.00726] Exploring Silent Data Corruption as a Reliability Challenge in LLM Training
Llms

[2604.00726] Exploring Silent Data Corruption as a Reliability Challenge in LLM Training

Abstract page for arXiv paper 2604.00726: Exploring Silent Data Corruption as a Reliability Challenge in LLM Training

arXiv - Machine Learning · 3 min ·
[2604.00686] Full-Gradient Successor Feature Representations

[2604.00686] Full-Gradient Successor Feature Representations

Abstract page for arXiv paper 2604.00686: Full-Gradient Successor Feature Representations

arXiv - Machine Learning · 3 min ·
[2604.00669] Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
Machine Learning

[2604.00669] Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics

Abstract page for arXiv paper 2604.00669: Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics

arXiv - Machine Learning · 4 min ·
[2604.00653] Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction
Machine Learning

[2604.00653] Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction

Abstract page for arXiv paper 2604.00653: Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction

arXiv - Machine Learning · 4 min ·
[2604.00626] A Survey of On-Policy Distillation for Large Language Models
Llms

[2604.00626] A Survey of On-Policy Distillation for Large Language Models

Abstract page for arXiv paper 2604.00626: A Survey of On-Policy Distillation for Large Language Models

arXiv - Machine Learning · 4 min ·
[2604.00599] Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations
Machine Learning

[2604.00599] Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations

Abstract page for arXiv paper 2604.00599: Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations

arXiv - Machine Learning · 4 min ·
[2604.00580] Representation choice shapes the interpretation of protein conformational dynamics

[2604.00580] Representation choice shapes the interpretation of protein conformational dynamics

Abstract page for arXiv paper 2604.00580: Representation choice shapes the interpretation of protein conformational dynamics

arXiv - Machine Learning · 3 min ·