Modelling for Complex Domains
lennardong.bearblog.dev·9h
💾Binary Formats
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
arxiv.org·9h
🔍Information Retrieval
Mitigating Shortcut Learning with InterpoLated Learning
arxiv.org·9h
🕸️Sparse Embeddings
TokenShapley: Token Level Context Attribution with Shapley Value
arxiv.org·9h
💾Prompt Caching
A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation
arxiv.org·9h
🧠Inference Serving
DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning
arxiv.org·9h
🔢BitNet
HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation
arxiv.org·9h
🔄LLM RAG Pipelines
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning
arxiv.org·9h
⏱️Real-time Systems
Accelerate your AI workloads with the Google Cloud Managed Lustre
cloud.google.com·20h
🖥GPUs
Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift
arxiv.org·9h
📊Statistical Ranking
Beating the Best Constant Rebalancing Portfolio in Long-Term Investment: A Generalization of the Kelly Criterion and Universal Learning Algorithm for Markets wi...
arxiv.org·9h
📊Vector Databases
An autonomous agent for auditing and improving the reliability of clinical AI models
arxiv.org·9h
🛡️AI Safety
Robust Speech-Workload Estimation for Intelligent Human-Robot Systems
arxiv.org·9h
⏱️Real-time Systems
CoDy: Counterfactual Explainers for Dynamic Graphs
arxiv.org·9h
🔢BitNet Inference
GATMesh: Clock Mesh Timing Analysis using Graph Neural Networks
arxiv.org·9h
🖥️Hardware Architecture
Estimating prevalence with precision and accuracy
arxiv.org·9h
🔬RaBitQ
Fair Domain Generalization: An Information-Theoretic View
arxiv.org·9h
🛡️AI Safety
TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision
arxiv.org·9h
🔤Font Rendering
From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
arxiv.org·9h
🌐Distributed systems
Skywork-R1V3 Technical Report
arxiv.org·9h
🔍AI Interpretability