Generative Interpretability via Scalable Neuro-Symbolic Models
Paper • 2609.13529 • Published • 2
Xiaocong Yang
xiaocong01
AI & ML interests
AI Interpretability; LLM Architectures
Recent Activity
upvoted a paper 12 days ago
Generative Interpretability via Scalable Neuro-Symbolic Models upvoted a paper 16 days ago
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching upvoted a paper 16 days ago
Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole FilesOrganizations
upvoted a paper 12 days ago
upvoted 4
papers 16 days ago
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching
Paper • 2610.19636 • Published • 8
Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
Paper • 2610.21073 • Published • 4
Resisting Harmful Instructions through Training-Free Weight Editing
Paper • 2610.21189 • Published • 4
DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections
Paper • 2610.19625 • Published • 9