Skip to content

Reading Notes

55 arXiv papers I've read

All 2-bit Quantization AI Security Academic Review Action Prediction Ad Systems Adversarial Attacks Adversarial Robustness Adversarial Training Attention Fusion Attention Mechanism Attention Mechanisms Automated Metrics Automatic Bidding Benchmarking Butterfly Transform Citation Bias Code Completion Code Generation Compositional Understanding Concept Erasure Constrained Optimization Contextual Integrity Contrastive Learning Conversational Agent Creativity Credit Assignment Daily Care Dataset Debate Mechanisms Deep Learning Delayed Feedback Diffusion Geometry Diffusion Language Models Domain Adaptation Dual-branch Network Embodied AI Flow Matching Fluid Dynamics Gaussian Processes Generative AI Safety Generative Models Geometric Modeling Geospatial Graph Analysis Graph Neural Networks Hallucination Detection Health Monitoring Heart Rate Variability High-Fidelity Human Evaluation Hybrid Methods Image Editing Inference Acceleration Inference Intervention Inversion Attacks KV Cache Kernel Methods Knowledge Distillation LLM LLM Agents LLM Confidence LLM Evaluation LLM Hallucination LLM Judge LLM Optimization LLM Quantization LLM Security LLM-as-Judge Label Quantization Large Language Models Lifelong Learning Lightweight Models Linear Attention Log-Probabilities Logistics Dispatch Long Context Long-form Text Generation Low-Bit Activations Low-Resource Learning MLLMs Machine Unlearning Mamba Manifold Learning Masked Modeling Memory Management Memory Modeling Mixture of Experts Model Compression Model Distillation Model Evaluation Model Pruning Model Quantization Model Scaling Multi-Agent Debate Multi-Agent Reinforcement Learning Multi-Agent Systems Multi-task Learning Multilingual Robustness Multimodal LLMs Multimodal Large Language Models Multimodal Large Models Multimodal Learning Offline Reinforcement Learning Optimal Transport Pairwise Comparison Parallel Decoding Parameter-Efficient Fine-Tuning Pediatric Intensive Care Periodic Signals Periodicity Learning Physics-driven Policy Optimization Post-Training Quantization Post-training Optimization Prediction Markets Primal-Dual Methods Privacy Protection Protein Design Quantization-Aware Training Real-time Monitoring Reasoning Diagnosis Reasoning Evaluation Reinforcement Learning Representation Alignment Representation Analysis Reproducibility Research Standards Retrieval Augmentation Riemannian Metric Robot Learning Robotic Control Robustness Role-Playing Routing Strategy Safe Reinforcement Learning Safety Constraints Security Self-Recovery Self-Supervised Learning Signal Regression Social Simulation Spectral Attention Split Learning Spreadsheets Temporal Modeling Test-Time Learning Text-Attributed Graphs Text-to-Image Token Pruning Tool Use Trustworthy AI UI State Unsupervised Learning User Experience Vector Quantization Vision-Language Models Vision-Language-Action Models Visual Robustness World Models Zero-shot Detection rPPG