Content Feed

The latest content from across the network

Ranked Latest Top this week
[2604.03098] Co-Evolution of Policy and Internal Reward for Language Agents
Llms

[2604.03098] Co-Evolution of Policy and Internal Reward for Language Agents

Abstract page for arXiv paper 2604.03098: Co-Evolution of Policy and Internal Reward for Language Agents

arXiv - AI · 4 min ·
[2604.03015] Generating DDPM-based Samples from Tilted Distributions
Generative Ai

[2604.03015] Generating DDPM-based Samples from Tilted Distributions

Abstract page for arXiv paper 2604.03015: Generating DDPM-based Samples from Tilted Distributions

arXiv - Machine Learning · 3 min ·
[2604.02990] FedSQ: Optimized Weight Averaging via Fixed Gating
Machine Learning

[2604.02990] FedSQ: Optimized Weight Averaging via Fixed Gating

Abstract page for arXiv paper 2604.02990: FedSQ: Optimized Weight Averaging via Fixed Gating

arXiv - AI · 4 min ·
[2604.02986] Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
Machine Learning

[2604.02986] Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Abstract page for arXiv paper 2604.02986: Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

arXiv - AI · 3 min ·
[2604.02942] Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in Female Mouse White Adipose Tissue After 37 Days of Microgravity: First AI/ML Analysis of NASA OSD-970
Machine Learning

[2604.02942] Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in Female Mouse White Adipose Tissue After 37 Days of Microgravity: First AI/ML Analysis of NASA OSD-970

Abstract page for arXiv paper 2604.02942: Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in...

arXiv - Machine Learning · 4 min ·
[2604.02927] Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms
Machine Learning

[2604.02927] Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms

Abstract page for arXiv paper 2604.02927: Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms

arXiv - Machine Learning · 4 min ·
[2604.02920] Efficient Logistic Regression with Mixture of Sigmoids

[2604.02920] Efficient Logistic Regression with Mixture of Sigmoids

Abstract page for arXiv paper 2604.02920: Efficient Logistic Regression with Mixture of Sigmoids

arXiv - Machine Learning · 3 min ·
[2604.02899] Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation

[2604.02899] Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation

Abstract page for arXiv paper 2604.02899: Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation

arXiv - Machine Learning · 4 min ·
[2604.02876] Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting
Machine Learning

[2604.02876] Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting

Abstract page for arXiv paper 2604.02876: Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting

arXiv - Machine Learning · 4 min ·
[2604.02788] Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guarantees
Ai Infrastructure

[2604.02788] Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guarantees

Abstract page for arXiv paper 2604.02788: Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preser...

arXiv - Machine Learning · 4 min ·
[2604.02766] Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs
Llms

[2604.02766] Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

Abstract page for arXiv paper 2604.02766: Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

arXiv - AI · 3 min ·
[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 ·