CrossTrace: Efficient Cross-Thread and Cross-Service Span Correlation in Distributed Tracing for Microservices
arxiv.org·2d
📊AI Performance Profiling
Transient Stability Analysis for Grid Following Converters in Low-Inertia Power Systems by Direct Method
arxiv.org·23h
✨Model optimizations in LLMs
Adaptive Cardio Load Targets for Improving Fitness and Performance
arxiv.org·2d
💬Prompt optimizations for LLM serving
Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation
arxiv.org·2d
🧠Large Language Models (LLMs)
G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
arxiv.org·2d
📊AI Performance Profiling
When Algorithms Mirror Minds: A Confirmation-Aware Social Dynamic Model of Echo Chamber and Homogenization Traps
arxiv.org·2d
🔍Retrieval-augmented generation
Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation
arxiv.org·2d
🔍Retrieval-augmented generation
A Cooperative Game-Based Multi-Criteria Weighted Ensemble Approach for Multi-Class Classification
arxiv.org·2d
📊AI Performance Profiling
Delving into Dynamic Scene Cue-Consistency for Robust 3D Multi-Object Tracking
arxiv.org·2d
📊AI Performance Profiling
Deploying Your Omniverse Kit Apps at Scale
developer.nvidia.com·2d
⚙️AI Infrastructure Automation
MCP-Guard: A Defense Framework for Model Context Protocol Integrity in Large Language Model Applications
arxiv.org·2d
🧠Large Language Models (LLMs)
Towards Efficient Hash Maps in Functional Array Languages
arxiv.org·2d
🔧Systems-level optimizations for LLM serving
3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
arxiv.org·2d
⚙️AI Infrastructure Automation
Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
arxiv.org·1d
🧠Large Language Models (LLMs)
Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
arxiv.org·2d
🧠Large Language Models (LLMs)
ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning
arxiv.org·6d
🧠Large Language Models (LLMs)
ASP-Completeness Proofs of Puzzles Using the T-Metacell Framework
arxiv.org·2d
💬Prompt optimizations for LLM serving
Active Fault Identification and Robust Control for Unknown Bounded Faults via Volume-Based Costs
arxiv.org·1d
⚙️AI Infrastructure Automation
E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
arxiv.org·2d
🧠Large Language Models (LLMs)
Use of a genetic algorithm to find solutions to introductory physics problems
arxiv.org·2d
🧠Large Language Models (LLMs)