Agentic Witnessing enables privacy-preserving auditing of semantic properties in private data by running an LLM auditor in a TEE that answers binary queries and produces cryptographic transcripts of its reasoning.
arXiv preprint arXiv:2502.04563 (2025)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Runtime compute relocation via utility chiplets cuts communication cost on multi-bandwidth chiplet fabrics, delivering multi-x gains on LLM inference in simulation.
MOCAP proposes MBKR and LBCP techniques for chunked pipelining on wafer-scale chips to reduce memory imbalance and latency skew in prefill LLM inference, reporting 76.4% lower latency and 3.24x throughput vs GPipe.
citing papers explorer
-
Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing
Agentic Witnessing enables privacy-preserving auditing of semantic properties in private data by running an LLM auditor in a TEE that answers binary queries and produces cryptographic transcripts of its reasoning.
-
SHIFT: Dynamic Compute Relocation Framework for Communication-Aware Chiplet-Based Systems
Runtime compute relocation via utility chiplets cuts communication cost on multi-bandwidth chiplet fabrics, delivering multi-x gains on LLM inference in simulation.
-
MOCAP: Wafer-Scale-Chip-Oriented Memory-Orchestrated Chunked Pipelining Framework for Prefill-Only LLM Inference
MOCAP proposes MBKR and LBCP techniques for chunked pipelining on wafer-scale chips to reduce memory imbalance and latency skew in prefill LLM inference, reporting 76.4% lower latency and 3.24x throughput vs GPipe.