arXiv (OAI Expanded)
open access
Sparse Weight and Edge Circuit Discovery in Transformer-based Acoustic Models
Transformer-based foundation models are powerful but opaque, motivating Mechanistic Interpretation methods to uncover the black-box by identifying small computation subgraphs responsible for a task. DiscoGP is a joint weight-and-edge circuit discovery framework originally developed for text decoders
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models#927171
- FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs#1143498
- Cross-Layer Discrete Concept Discovery for Interpreting Language Models#1142543
- Harmonizing Spectral Evolution in Conditional Flow Matching for TTS#1128701
- Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference#1062509
Record · ID 1083226
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive