pith. sign in

Aashiq Muhamed

Identifiers

  • name variant Aashiq Muhamed 0.60 · backfill

Papers (9)

  1. Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? cs.LG · 2026 · author #2
  2. CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation cs.CL · 2025 · author #1
  3. Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs cs.LG · 2025 · author #2
  4. SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs cs.LG · 2025 · author #1
  5. CoRAG: Collaborative Retrieval-Augmented Generation cs.AI · 2025 · author #1
  6. NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA cs.LG · 2024 · author #12
  7. Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models cs.LG · 2024 · author #1
  8. Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients cs.LG · 2024 · author #1
  9. An In-depth Look at Gemini's Language Abilities cs.CL · 2023 · author #3

Mentions

  • 2506.20128 #1 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2411.03730 #12 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2505.20254 #2 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2504.08192 #1 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2504.01883 #1 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2411.00743 #1 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2406.17660 #1 · arxiv_oai · confidence 0.70 Aashiq Muhamed
  • 2312.11444 #3 · arxiv_oai · confidence 0.70 Aashiq Muhamed

Frequent Coauthors