Invisible Architectures of Thought: Toward a New Science of AI as Cognitive Infrastructure
arxiv.org·3d
⚙️AI Infrastructure Automation
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
arxiv.org·4d
🧠Large Language Models (LLMs)
HateBuffer: Safeguarding Content Moderators' Mental Well-Being through Hate Speech Content Modification
arxiv.org·2h
🧠Large Language Models (LLMs)
GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation
arxiv.org·2h
🔍Retrieval-augmented generation
Evaluating COVID 19 Feature Contributions to Bitcoin Return Forecasting: Methodology Based on LightGBM and Genetic Optimization
arxiv.org·2h
✨Model optimizations in LLMs
Tropical solution of discrete best approximation problems
arxiv.org·4d
✨Model optimizations in LLMs
A Compute-Matched Re-Evaluation of TroVE on MATH
arxiv.org·4d
💬Prompt optimizations for LLM serving
RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
arxiv.org·4d
🧠Large Language Models (LLMs)
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
arxiv.org·4d
⚙️AI Infrastructure Automation
FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
arxiv.org·3d
🔍Retrieval-augmented generation
SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology
arxiv.org·3d
🧠Large Language Models (LLMs)
TrajSurv: Learning Continuous Latent Trajectories from Electronic Health Records for Trustworthy Survival Prediction
arxiv.org·2h
🧠Large Language Models (LLMs)
Beamformed 360{\deg} Sound Maps: U-Net-Driven Acoustic Source Segmentation and Localization
arxiv.org·2h
🔢Quantization of LLMs
Memorization in Fine-Tuned Large Language Models
arxiv.org·6d
🧠Large Language Models (LLMs)
FairReason: Balancing Reasoning and Social Bias in MLLMs
arxiv.org·3d
🧠Large Language Models (LLMs)
Active IRS-Enabled Integrated Sensing and Communications with Extended Targets
arxiv.org·2h
🔧Systems-level optimizations for LLM serving
Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Nearest-Better Network for Visualizing and Analyzing Combinatorial Optimization Problems: A Unified Tool
arxiv.org·4d
🔧Systems-level optimizations for LLM serving
AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock
arxiv.org·4d
⚙️AI Infrastructure Automation
The Repeated-Stimulus Confound in Electroencephalography
arxiv.org·2h
🔍Retrieval-augmented generation