Moravec's Paradox: Towards an Auditory Turing Test
arxiv.org·3d·
Discuss: Hacker News
🧠Large Language Models (LLMs)
EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO
arxiv.org·5d
🧠Large Language Models (LLMs)
SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering
arxiv.org·5d
🔍Retrieval-augmented generation
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
arxiv.org·4d
📊AI Performance Profiling
CLIPTime: Time-Aware Multimodal Representation Learning from Images and Text
arxiv.org·20h
🧠Large Language Models (LLMs)
Stabilization of Age-Structured Competing Populations
arxiv.org·3d
⚙️AI Infrastructure Automation
Improving Generative Ad Text on Facebook using Reinforcement Learning
arxiv.org·5d
🧠Large Language Models (LLMs)
Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
arxiv.org·4d
🔧Systems-level optimizations for LLM serving
AQUA: A Large Language Model for Aquaculture & Fisheries
arxiv.org·6d
🧠Large Language Models (LLMs)
SLA-Centric Automated Algorithm Selection Framework for Cloud Environments
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
The Carbon Cost of Conversation, Sustainability in the Age of Language Models
arxiv.org·6d
🧠Large Language Models (LLMs)
Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
arxiv.org·5d
💬Prompt optimizations for LLM serving
Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
arxiv.org·5d
✨Model optimizations in LLMs
Prompt template for a fictitious LLM agent in a content-flagging experiment
arxiv.org·5d
🏋️LLM training frameworks
Comparing Normalizing Flows with Kernel Density Estimation in Estimating Risk of Automated Driving Systems
arxiv.org·4d
✨Model optimizations in LLMs
Knowledge-Guided Memetic Algorithm for Capacitated Arc Routing Problems with Time-Dependent Service Costs
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
CUDA Pro Tip: Increase Performance with Vectorized Memory Access
developer.nvidia.com·1d
🔧Systems-level optimizations for LLM serving
Training language models to be warm and empathetic makes them less reliable and more sycophantic
arxiv.org·5d
🧠Large Language Models (LLMs)
Tropical solution of discrete best approximation problems
arxiv.org·4d
✨Model optimizations in LLMs
Invisible Architectures of Thought: Toward a New Science of AI as Cognitive Infrastructure
arxiv.org·3d
⚙️AI Infrastructure Automation