Efficient Transforms in cuDF Using JIT Compilation
developer.nvidia.com·5d
💬Prompt optimizations for LLM serving
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
arxiv.org·3d
🧠Large Language Models (LLMs)
Dual Signal Decomposition of Stochastic Time Series
arxiv.org·23h
⚡Real-time AI Systems
R²D²: Boost Robot Training with World Foundation Models and Workflows from NVIDIA Research
developer.nvidia.com·5d
📊AI Performance Profiling
ALScope: A Unified Toolkit for Deep Active Learning
arxiv.org·3d
🧠Large Language Models (LLMs)
Telegrapher's Generative Model via Kac Flows
arxiv.org·3d
🧠Large Language Models (LLMs)
Web3 x AI Agents: Landscape, Integrations, and Foundational Challenges
arxiv.org·5d
⚙️AI Infrastructure Automation
Sotopia-RL: Reward Design for Social Intelligence
arxiv.org·4d
🧠Large Language Models (LLMs)
Evaluation of a Sign Language Avatar on Comprehensibility, User Experience \& Acceptability
arxiv.org·3d
🔍Retrieval-augmented generation
Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
arxiv.org·3d
📊AI Performance Profiling
Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks
arxiv.org·3d
🧠Large Language Models (LLMs)
Personalized Recommendation of Dish and Restaurant Collections on iFood
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Deconstructing the Crystal Ball: From Ad-Hoc Prediction to Principled Startup Evaluation with the SAISE Framework
arxiv.org·3d
📊AI Performance Profiling
Toward Energy and Location-Aware Resource Allocation in Next Generation Networks
arxiv.org·3d
🔧Systems-level optimizations for LLM serving
Sprouting technology otherwise, hospicing negative commons -- Rethinking technology in the transition to sustainability-oriented futures
arxiv.org·23h
🔍Retrieval-augmented generation
Getting out of the Big-Muddy: Escalation of Commitment in LLMs
arxiv.org·6d
🧠Large Language Models (LLMs)
MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
arxiv.org·6d
💬Prompt optimizations for LLM serving
KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs
arxiv.org·6d
🧠Large Language Models (LLMs)
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets
arxiv.org·6d
🧠Large Language Models (LLMs)
GTPO: Trajectory-Based Policy Optimization in Large Language Models
arxiv.org·4d
🧠Large Language Models (LLMs)