Dynamo 0.4 Delivers 4x Faster Performance, SLO-Based Autoscaling, and Real-Time Observability
developer.nvidia.com·6d
📊AI Performance Profiling
Physics-Informed Multimodal Bearing Fault Classification under Variable Operating Conditions using Transfer Learning
arxiv.org·5d
🧠Large Language Models (LLMs)
Selective Contrastive Learning for Weakly Supervised Affordance Grounding
arxiv.org·5d
🔍Retrieval-augmented generation
A Physics-informed Deep Operator for Real-Time Freeway Traffic State Estimation
arxiv.org·5d
✨Model optimizations in LLMs
Evaluating Large Language Models as Expert Annotators
arxiv.org·5d
🧠Large Language Models (LLMs)
Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow
arxiv.org·5d
🧠Large Language Models (LLMs)
InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information
arxiv.org·5d
📊AI Performance Profiling
A Generative Imputation Method for Multimodal Alzheimer's Disease Diagnosis
arxiv.org·3d
🔍Retrieval-augmented generation
Geospatial Diffusion for Land Cover Imperviousness Change Forecasting
arxiv.org·2d
🔍Retrieval-augmented generation
VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
arxiv.org·2d
🔢Quantization of LLMs
Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
arxiv.org·6d
🔍Retrieval-augmented generation
Sample-efficient LLM Optimization with Reset Replay
arxiv.org·6d
✨Model optimizations in LLMs
Efficient and Reliable Hitting-Set Computations for the Implicit Hitting Set Approach
arxiv.org·5d
💬Prompt optimizations for LLM serving
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
arxiv.org·5d
🧠Large Language Models (LLMs)
MuaLLM: A Multimodal Large Language Model Agent for Circuit Design Assistance with Hybrid Contextual Retrieval-Augmented Generation
arxiv.org·5d
🔍Retrieval-augmented generation
Capabilities of GPT-5 on Multimodal Medical Reasoning
arxiv.org·5d·
Discuss: Hacker News
🧠Large Language Models (LLMs)
ThinkTuning: Instilling Cognitive Reflections without Distillation
arxiv.org·5d
🧠Large Language Models (LLMs)
A Stable and Principled Loss Function for Direct Language Model Alignment
arxiv.org·5d
🧠Large Language Models (LLMs)
Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example
arxiv.org·4d
🧠Large Language Models (LLMs)
Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving
arxiv.org·4d
🧠Large Language Models (LLMs)