🔬 AI Research - inarcissuss

Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

💬LLM Prompting arXiv·

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

🧠LLM Engineering arXiv·

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

🔬ML Research arXiv·

TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting

🤖AI Development arXiv·

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

🔬ML Research arXiv·

Recency/Frequency Adaptive KV Caching for Large Language Model Serving

🧠LLM Research arXiv·

Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners

🤖LLM, Agent arXiv·

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

📄AI Papers arXiv·

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

🔬ML Research arXiv·

SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis

🔬ML Research arXiv·

Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

✨Generative AI arXiv·

Co-occurring associated retained concepts in Diffusion Unlearning

🏆LLM Benchmarking arXiv·

Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization

📄AI Papers arXiv·

A Rank-One Popularity Component in Dot-Product Recommender Scores:Population Theory and Prior-Separation Evidence

🤖人工智能 arXiv·

A Fair Evaluation of Graph Foundation Models for Node Property Prediction

🎮Reinforcement Learning arXiv·

FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

🤖AI/ML arXiv·

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

💬LLM Prompting arXiv·

RoFormer: Enhanced Transformer with Rotary Position Embedding

ForensicsTok: Forensics-Guided Tokenized Modeling for Image Tampering Localization

Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting

Lightweight Transformer Models for On-Device Fault Detection: A Benchmark Study on Resource-Constrained Deployment

Recency/Frequency Adaptive KV Caching for Large Language Model Serving

Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis

Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

Co-occurring associated retained concepts in Diffusion Unlearning

Reasoning as Attractor Dynamics: Latent Memory Retrieval via Gibbs-Weighted Energy Minimization

A Rank-One Popularity Component in Dot-Product Recommender Scores:Population Theory and Prior-Separation Evidence

A Fair Evaluation of Graph Foundation Models for Node Property Prediction

FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

GRAFT: Graph-Based Affordance Transfer via Part Correspondence