Content Feed

The latest content from across the network

Ranked Latest Top this week
[2604.02459] On the Geometric Structure of Layer Updates in Deep Language Models
Llms

[2604.02459] On the Geometric Structure of Layer Updates in Deep Language Models

Abstract page for arXiv paper 2604.02459: On the Geometric Structure of Layer Updates in Deep Language Models

arXiv - AI · 4 min ·
[2604.02450] Do We Need Frontier Models to Verify Mathematical Proofs?
Llms

[2604.02450] Do We Need Frontier Models to Verify Mathematical Proofs?

Abstract page for arXiv paper 2604.02450: Do We Need Frontier Models to Verify Mathematical Proofs?

arXiv - AI · 4 min ·
[2604.02445] Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD
Ai Startups

[2604.02445] Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD

Abstract page for arXiv paper 2604.02445: Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD

arXiv - Machine Learning · 3 min ·
[2604.02438] Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models
Machine Learning

[2604.02438] Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models

Abstract page for arXiv paper 2604.02438: Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using P...

arXiv - Machine Learning · 4 min ·
[2604.02430] Self-Directed Task Identification
Machine Learning

[2604.02430] Self-Directed Task Identification

Abstract page for arXiv paper 2604.02430: Self-Directed Task Identification

arXiv - AI · 3 min ·
[2604.02355] From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
Generative Ai

[2604.02355] From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

Abstract page for arXiv paper 2604.02355: From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Imag...

arXiv - Machine Learning · 3 min ·
[2604.02393] Dynamical structure of vanishing gradient and overfitting in multi-layer perceptrons
Machine Learning

[2604.02393] Dynamical structure of vanishing gradient and overfitting in multi-layer perceptrons

Abstract page for arXiv paper 2604.02393: Dynamical structure of vanishing gradient and overfitting in multi-layer perceptrons

arXiv - Machine Learning · 3 min ·
[2604.02378] YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches
Ai Startups

[2604.02378] YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches

Abstract page for arXiv paper 2604.02378: YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches

arXiv - Machine Learning · 3 min ·
[2604.02353] Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning

[2604.02353] Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning

Abstract page for arXiv paper 2604.02353: Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning

arXiv - AI · 4 min ·
[2604.02352] An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
Llms

[2604.02352] An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code

Abstract page for arXiv paper 2604.02352: An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code

arXiv - AI · 3 min ·
[2604.02351] Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
Machine Learning

[2604.02351] Modeling and Controlling Deployment Reliability under Temporal Distribution Shift

Abstract page for arXiv paper 2604.02351: Modeling and Controlling Deployment Reliability under Temporal Distribution Shift

arXiv - Machine Learning · 3 min ·
[2604.02350] Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
Machine Learning

[2604.02350] Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility

Abstract page for arXiv paper 2604.02350: Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned F...

arXiv - AI · 3 min ·
[2604.02349] OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
Data Science

[2604.02349] OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Abstract page for arXiv paper 2604.02349: OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

arXiv - AI · 3 min ·
[2604.02348] Contextual Intelligence The Next Leap for Reinforcement Learning
Machine Learning

[2604.02348] Contextual Intelligence The Next Leap for Reinforcement Learning

Abstract page for arXiv paper 2604.02348: Contextual Intelligence The Next Leap for Reinforcement Learning

arXiv - Machine Learning · 4 min ·
[2604.02347] FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting
Machine Learning

[2604.02347] FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting

Abstract page for arXiv paper 2604.02347: FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Fo...

arXiv - Machine Learning · 4 min ·
[2604.02346] DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery
Llms

[2604.02346] DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery

Abstract page for arXiv paper 2604.02346: DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery

arXiv - AI · 3 min ·
[2604.02345] UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

[2604.02345] UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

Abstract page for arXiv paper 2604.02345: UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics

arXiv - AI · 4 min ·
[2604.02344] Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
Llms

[2604.02344] Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

Abstract page for arXiv paper 2604.02344: Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backen...

arXiv - Machine Learning · 4 min ·
[2604.02343] Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains
Llms

[2604.02343] Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains

Abstract page for arXiv paper 2604.02343: Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains

arXiv - AI · 4 min ·
[2604.02342] Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
Machine Learning

[2604.02342] Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network

Abstract page for arXiv paper 2604.02342: Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network

arXiv - Machine Learning · 3 min ·