📉 Embeddings Optimization

Embedding Quantization, Dimensionality Reduction, HNSW Indexing, Latent Space Transformations, Embedding Distillation

TAI #167: US and China’s Open-Weight Divergence; Do You Really Need Open-Weight LLMs?
pub.towardsai.net·12h
📊Model Serving Economics
Large Language Model-Based Automatic Formulation for Stochastic Optimization Models
arxiv.org·23h
🏆LLM Benchmarking
ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
arxiv.org·23h
🔤Font Rendering
Adversarial Examples Are Not Bugs, They Are Superposition
livgorton.com·9h·
Discuss: Hacker News
🛡️AI Security
Multimodal Medical Endoscopic Image Analysis via Progressive Disentangle-aware Contrastive Learning
arxiv.org·23h
🎯Vector Quantization
Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
arxiv.org·23h
🔢BitNet
HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
arxiv.org·23h
🧠LLM Inference
Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
arxiv.org·23h
⚡Hardware Acceleration
Feature-Refined Unsupervised Model for Loanword Detection
arxiv.org·23h
🔎Meilisearch
Multi-modal Knowledge Decomposition based Online Distillation for Biomarker Prediction in Breast Cancer Histopathology
arxiv.org·23h
📊Vector Databases
Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
arxiv.org·23h
📊Embeddings
FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction
arxiv.org·23h
🛡️AI Safety
A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond
arxiv.org·23h
📊Statistical Ranking
Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding
arxiv.org·23h
📊Embeddings
Alternating Training-based Label Smoothing Enhances Prompt Generalization
arxiv.org·23h
🧠LLM Inference
QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
arxiv.org·23h
📑Inverted Indexes
WOMAC: A Mechanism For Prediction Competitions
arxiv.org·23h
📊Statistical Ranking
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
arxiv.org·23h
🧠LLM Inference
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
arxiv.org·23h
🛡️AI Safety
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
arxiv.org·23h
📊Vector Databases