Agentic Coding Things That Didn’t Work
lucumr.pocoo.org·3d·
Discuss: Lobsters, Hacker News
🎭Proc Macros
Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI)
lesswrong.com·22h
🎮Game Engines
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
arxiv.org·1d
🕯️Candle
Research Areas in Information Theory and Cryptography (The Alignment Project by UK AISI)
lesswrong.com·22h
🔒Hardware Security
RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
arxiv.org·2d
🕯️Candle
Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI)
lesswrong.com·22h
⏱️Real-time Systems
Investigating the Invertibility of Multimodal Latent Spaces: Limitations of Optimization-Based Methods
arxiv.org·1d
🕯️Candle
SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention
arxiv.org·3d
🕯️Candle
Deciphering interventional dynamical causality from non-intervention complex systems
arxiv.org·1d
🧮Linear Algebra
An LLM Driven Agent Framework for Automated Infrared Spectral Multi Task Reasoning
arxiv.org·3d
🕯️Candle
I am worried about near-term non-LLM AI developments
lesswrong.com·1d
🏗️LLVM
Efficacy of AI RAG Tools for Complex Information Extraction and Data Annotation Tasks: A Case Study Using Banks Public Disclosures
arxiv.org·3d
🗄️Database Internals
FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
arxiv.org·1d
🕯️Candle
Research Areas in Cognitive Science (The Alignment Project by UK AISI)
lesswrong.com·22h
🌍Distributed Systems
DICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction
arxiv.org·1d
🗄️Database Internals
Learning from Limited and Imperfect Data
arxiv.org·3d
🕯️Candle
SketchMind: A Multi-Agent Cognitive Framework for Assessing Student-Drawn Scientific Sketches
arxiv.org·1d
🎮Game Engines
Hybrid Particle Swarm Optimization for Fast and Reliable Parameter Extraction in Thermoreflectance
arxiv.org·1d
🕯️Candle
Provable In-Context Learning of Nonlinear Regression with Transformers
arxiv.org·4d
🕯️Candle
Wall Shear Stress Estimation in Abdominal Aortic Aneurysms: Towards Generalisable Neural Surrogate Models
arxiv.org·2d
🎨Computer Graphics