Pedestrian Dead Reckoning using Invariant Extended Kalman Filter
arxiv.org·21h
🔢Quantization of LLMs
CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion
arxiv.org·21h
🔍Retrieval-augmented generation
Delving into Dynamic Scene Cue-Consistency for Robust 3D Multi-Object Tracking
arxiv.org·21h
⚡Real-time AI Systems
StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translation
arxiv.org·21h
🔍Retrieval-augmented generation
\(X\)-evolve: Solution space evolution powered by large language models
arxiv.org·6d
🧠Large Language Models (LLMs)
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
arxiv.org·6d
✨Model optimizations in LLMs
UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles
arxiv.org·4d
⚙️AI Infrastructure Automation
Collective dynamics of strategic classification
arxiv.org·4d
🧠Large Language Models (LLMs)
HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
arxiv.org·3d
🧠Large Language Models (LLMs)
DriveSimQuest: A VR Driving Simulator and Research Platform on Meta Quest with Unity
arxiv.org·21h
⚡Real-time AI Systems
Real-time deep learning phase imaging flow cytometer reveals blood cell aggregate biomarkers for haematology diagnostics
arxiv.org·4d
🔢Quantization of LLMs
MultiPark: Multimodal Parking Transformer with Next-Segment Prediction
arxiv.org·21h
⚡Real-time AI Systems
Hybrid Node-Destroyer Model with Large Neighborhood Search for Solving the Capacitated Vehicle Routing Problem
arxiv.org·5d
⚙️AI Infrastructure Automation
Pareto Multi-Objective Alignment for Language Models
arxiv.org·6d
🧠Large Language Models (LLMs)
CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
arxiv.org·21h
🧠Large Language Models (LLMs)
Banking 2.0: The Stablecoin Banking Revolution -- How Digital Assets Are Reshaping Global Finance
arxiv.org·21h
⚡Real-time AI Systems
Do AI Companies Make Good on Voluntary Commitments to the White House?
arxiv.org·5d
⚙️AI Infrastructure Automation
ViPE: Video Pose Engine for 3D Geometric Perception
arxiv.org·21h
📊AI Performance Profiling
Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset
arxiv.org·3d
🧠Large Language Models (LLMs)
Mitigating Exponential Mixed Frequency Growth through Frequency Selection and Dimensional Separation in Quantum Machine Learning
arxiv.org·3d
🔢Quantization of LLMs