From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
arxiv.org·6d
⚙️AI Infrastructure Automation
Large Language Models Still Exhibit Bias in Long Text
arxiv.org·5d
🧠Large Language Models (LLMs)
Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration
arxiv.org·5d
⚙️AI Infrastructure Automation
JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
arxiv.org·5d
🧠Large Language Models (LLMs)
Deformable Attention Graph Representation Learning for Histopathology Whole Slide Image Analysis
arxiv.org·5d
🧠Large Language Models (LLMs)
Towards MR-Based Trochleoplasty Planning
arxiv.org·2d
🔢Quantization of LLMs
Causality-Driven Audits of Model Robustness
arxiv.org·6d
✨Model optimizations in LLMs
Continual Multiple Instance Learning for Hematologic Disease Diagnosis
arxiv.org·6d
⚡Real-time AI Systems
A Novel Image Similarity Metric for Scene Composition Structure
arxiv.org·5d
🔍Retrieval-augmented generation
R²D²: Boost Robot Training with World Foundation Models and Workflows from NVIDIA Research
developer.nvidia.com·6d
⚙️AI Infrastructure Automation
ANPrompt: Anti-noise Prompt Tuning for Vision-Language Models
arxiv.org·6d
🧠Large Language Models (LLMs)
Benchmarking Foundation Models for Mitotic Figure Classification
arxiv.org·6d
🧠Large Language Models (LLMs)
Latent Preference Bandits
arxiv.org·5d
🧠Large Language Models (LLMs)
Honest and Reliable Evaluation and Expert Equivalence Testing of Automated Neonatal Seizure Detection
arxiv.org·5d
🧠Large Language Models (LLMs)
Unsupervised Graph Deep Learning Reveals Emergent Flood Risk Profile of Urban Areas
arxiv.org·5d
🧠Large Language Models (LLMs)
Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
arxiv.org·5d
🧠Large Language Models (LLMs)
Mining the Social Fabric: Unveiling Communities for Fake News Detection in Short Videos
arxiv.org·1d
🧠Large Language Models (LLMs)
Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patients
arxiv.org·2d
⚡Real-time AI Systems
Improve Retinal Artery/Vein Classification via Channel Couplin
arxiv.org·6d
🔢Quantization of LLMs
Enhancing Systematic Interoperability: Convergences and Mismatches between Web 3.0 and the EU Data Act
arxiv.org·1d
🔧Systems-level optimizations for LLM serving