ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
arxiv.org·4d
🕯️Candle
NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
arxiv.org·3d
🤖AI
Smoothing Slot Attention Iterations and Recurrences
arxiv.org·3d
🔢SIMD Programming
Building Effective Safety Guardrails in AI Education Tools
arxiv.org·3d
🎮Game Engines
Six Guidelines for Trustworthy, Ethical and Responsible Automation Design
arxiv.org·6d
🔒Hardware Security
Elucidating the Role of Feature Normalization in IJEPA
arxiv.org·5d
🕯️Candle
Sam I Am
lesswrong.com·3d
🦀Rust
An Interpretable Multi-Plane Fusion Framework With Kolmogorov-Arnold Network Guided Attention Enhancement for Alzheimer's Disease Diagnosis
arxiv.org·6h
🤖AI
ProCut: LLM Prompt Compression via Attribution Estimation
arxiv.org·6d
🏗️LLVM
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
arxiv.org·6d
🎨Computer Graphics
LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
arxiv.org·5d
🧮Linear Algebra
Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
arxiv.org·4d
🎨Computer Graphics
A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models
arxiv.org·4d
🕯️Candle
Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
arxiv.org·4d
🤖AI
Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
arxiv.org·3d
🤖AI
Hessian analysis with JAX: a platform-agnostic, high-performance approach
lesswrong.com·6d
🕯️Candle
Online EFX Allocations with Predictions
arxiv.org·3d
🎮Game Engines
GENIE: Gaussian Encoding for Neural Radiance Fields Interactive Editing
arxiv.org·5d
🎨Computer Graphics
FedGIN: Federated Learning with Dynamic Global Intensity Non-linear Augmentation for Organ Segmentation using Multi-modal Images
arxiv.org·3d
🕯️Candle
RooseBERT: A New Deal For Political Language Modelling
arxiv.org·5d
🕯️Candle