Content Feed

The latest content from across the network

Ranked Latest Top this week
[2604.02447] PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction
Machine Learning

[2604.02447] PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction

Abstract page for arXiv paper 2604.02447: PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction

arXiv - AI · 4 min ·
[2604.02429] Photonic convolutional neural network with pre-trained in-situ training
Machine Learning

[2604.02429] Photonic convolutional neural network with pre-trained in-situ training

Abstract page for arXiv paper 2604.02429: Photonic convolutional neural network with pre-trained in-situ training

arXiv - Machine Learning · 4 min ·
[2604.02372] Backdoor Attacks on Decentralised Post-Training
Llms

[2604.02372] Backdoor Attacks on Decentralised Post-Training

Abstract page for arXiv paper 2604.02372: Backdoor Attacks on Decentralised Post-Training

arXiv - Machine Learning · 3 min ·
[2604.02361] TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning
Machine Learning

[2604.02361] TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

Abstract page for arXiv paper 2604.02361: TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

arXiv - AI · 3 min ·
[2604.02360] Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations
Llms

[2604.02360] Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations

Abstract page for arXiv paper 2604.02360: Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations

arXiv - AI · 3 min ·
[2604.02356] MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites
Machine Learning

[2604.02356] MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites

Abstract page for arXiv paper 2604.02356: MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning ...

arXiv - Machine Learning · 3 min ·
[2604.03226] Enhancing Robustness of Federated Learning via Server Learning
Machine Learning

[2604.03226] Enhancing Robustness of Federated Learning via Server Learning

Abstract page for arXiv paper 2604.03226: Enhancing Robustness of Federated Learning via Server Learning

arXiv - AI · 3 min ·
[2604.03208] Hierarchical Planning with Latent World Models
Machine Learning

[2604.03208] Hierarchical Planning with Latent World Models

Abstract page for arXiv paper 2604.03208: Hierarchical Planning with Latent World Models

arXiv - Machine Learning · 3 min ·
[2604.03197] Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis
Machine Learning

[2604.03197] Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis

Abstract page for arXiv paper 2604.03197: Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis

arXiv - Machine Learning · 4 min ·
[2604.03190] Gradient Boosting within a Single Attention Layer
Machine Learning

[2604.03190] Gradient Boosting within a Single Attention Layer

Abstract page for arXiv paper 2604.03190: Gradient Boosting within a Single Attention Layer

arXiv - AI · 3 min ·
[2604.03189] Reflective Context Learning: Studying the Optimization Primitives of Context Space
Machine Learning

[2604.03189] Reflective Context Learning: Studying the Optimization Primitives of Context Space

Abstract page for arXiv paper 2604.03189: Reflective Context Learning: Studying the Optimization Primitives of Context Space

arXiv - AI · 4 min ·
[2604.03180] PRISM: LLM-Guided Semantic Clustering for High-Precision Topics
Llms

[2604.03180] PRISM: LLM-Guided Semantic Clustering for High-Precision Topics

Abstract page for arXiv paper 2604.03180: PRISM: LLM-Guided Semantic Clustering for High-Precision Topics

arXiv - Machine Learning · 3 min ·
[2604.03179] Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
Llms

[2604.03179] Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

Abstract page for arXiv paper 2604.03179: Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning ...

arXiv - AI · 4 min ·
[2604.03154] DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
Machine Learning

[2604.03154] DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation

Abstract page for arXiv paper 2604.03154: DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation

arXiv - Machine Learning · 3 min ·
[2604.03150] HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging
Machine Learning

[2604.03150] HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging

Abstract page for arXiv paper 2604.03150: HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectrosco...

arXiv - Machine Learning · 4 min ·
[2604.03128] Self-Distilled RLVR
Llms

[2604.03128] Self-Distilled RLVR

Abstract page for arXiv paper 2604.03128: Self-Distilled RLVR

arXiv - Machine Learning · 3 min ·
[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 ·