Metaprogramming, Code Generation, Derive Macros, Syntax Extensions
TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
arxiv.org·6d
Against functionalism: a self dialogue
lesswrong.com·1d
Modeling Rapid Contextual Learning in the Visual Cortex with Fast-Weight Deep Autoencoder Networks
arxiv.org·3d
LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
arxiv.org·5d
LLMs Have a Heart of Stone: Demystifying the Soft Thinking Ability of Large Reasoning Models
arxiv.org·5d
Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives
arxiv.org·5d
Open weights == Closed source
lesswrong.com·4d
Statistical takes for mech interp research and beyond
lesswrong.com·4d
JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
arxiv.org·3d
MalFlows: Context-aware Fusion of Heterogeneous Flow Semantics for Android Malware Detection
arxiv.org·5d
Loading...Loading more...