Content Feed

The latest content from across the network

Ranked Latest Top this week
[2604.02765] Towards Realistic Class-Incremental Learning with Free-Flow Increments

[2604.02765] Towards Realistic Class-Incremental Learning with Free-Flow Increments

Abstract page for arXiv paper 2604.02765: Towards Realistic Class-Incremental Learning with Free-Flow Increments

arXiv - Machine Learning · 3 min ·
[2604.02756] STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation
Machine Learning

[2604.02756] STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation

Abstract page for arXiv paper 2604.02756: STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation

arXiv - Machine Learning · 4 min ·
[2604.02751] Understanding Latent Diffusability via Fisher Geometry
Machine Learning

[2604.02751] Understanding Latent Diffusability via Fisher Geometry

Abstract page for arXiv paper 2604.02751: Understanding Latent Diffusability via Fisher Geometry

arXiv - Machine Learning · 3 min ·
[2604.02718] Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
Llms

[2604.02718] Generative Frontiers: Why Evaluation Matters for Diffusion Language Models

Abstract page for arXiv paper 2604.02718: Generative Frontiers: Why Evaluation Matters for Diffusion Language Models

arXiv - Machine Learning · 4 min ·
[2604.02715] FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
Llms

[2604.02715] FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving

Abstract page for arXiv paper 2604.02715: FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving

arXiv - Machine Learning · 3 min ·
[2604.02697] LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks
Machine Learning

[2604.02697] LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Abstract page for arXiv paper 2604.02697: LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to...

arXiv - Machine Learning · 4 min ·
[2604.02691] Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism
Machine Learning

[2604.02691] Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

Abstract page for arXiv paper 2604.02691: Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts M...

arXiv - Machine Learning · 3 min ·
[2604.02686] Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
Machine Learning

[2604.02686] Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Abstract page for arXiv paper 2604.02686: Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

arXiv - AI · 3 min ·
[2604.02685] Finding Belief Geometries with Sparse Autoencoders
Llms

[2604.02685] Finding Belief Geometries with Sparse Autoencoders

Abstract page for arXiv paper 2604.02685: Finding Belief Geometries with Sparse Autoencoders

arXiv - AI · 4 min ·
[2604.02670] Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network
Machine Learning

[2604.02670] Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network

Abstract page for arXiv paper 2604.02670: Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with...

arXiv - Machine Learning · 3 min ·
[2604.02663] A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation
Machine Learning

[2604.02663] A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation

Abstract page for arXiv paper 2604.02663: A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Adva...

arXiv - Machine Learning · 4 min ·
[2604.02659] Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
Machine Learning

[2604.02659] Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Abstract page for arXiv paper 2604.02659: Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

arXiv - AI · 3 min ·
[2604.02653] Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
Machine Learning

[2604.02653] Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

Abstract page for arXiv paper 2604.02653: Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

arXiv - Machine Learning · 3 min ·
[2604.02652] Generalization Limits of Reinforcement Learning Alignment
Llms

[2604.02652] Generalization Limits of Reinforcement Learning Alignment

Abstract page for arXiv paper 2604.02652: Generalization Limits of Reinforcement Learning Alignment

arXiv - AI · 3 min ·
[2604.02651] Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
Machine Learning

[2604.02651] Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

Abstract page for arXiv paper 2604.02651: Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

arXiv - AI · 4 min ·
[2604.02644] Conditional Sampling via Wasserstein Autoencoders and Triangular Transport
Machine Learning

[2604.02644] Conditional Sampling via Wasserstein Autoencoders and Triangular Transport

Abstract page for arXiv paper 2604.02644: Conditional Sampling via Wasserstein Autoencoders and Triangular Transport

arXiv - Machine Learning · 3 min ·
[2604.02638] AXELRAM: Quantize Once, Never Dequantize

[2604.02638] AXELRAM: Quantize Once, Never Dequantize

Abstract page for arXiv paper 2604.02638: AXELRAM: Quantize Once, Never Dequantize

arXiv - Machine Learning · 3 min ·
[2604.02633] Analytic Drift Resister for Non-Exemplar Continual Graph Learning

[2604.02633] Analytic Drift Resister for Non-Exemplar Continual Graph Learning

Abstract page for arXiv paper 2604.02633: Analytic Drift Resister for Non-Exemplar Continual Graph Learning

arXiv - AI · 3 min ·
[2604.02615] Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems
Machine Learning

[2604.02615] Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems

Abstract page for arXiv paper 2604.02615: Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems

arXiv - Machine Learning · 3 min ·
[2604.02608] Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens
Llms

[2604.02608] Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Abstract page for arXiv paper 2604.02608: Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

arXiv - Machine Learning · 4 min ·