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.
Forked History
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
SAC uses CXL to fetch only top-k KV cache entries for sparse attention models, reporting 2.1x throughput, 9.7x lower TTFT and 1.8x lower TBT versus RDMA baselines on DeepSeek-V3.2.
A CPU-GPU hybrid design with stream-loading prefill, expert parallelism, and disaggregation achieves cloud SLOs for local MoE inference on dual-socket CPUs and consumer GPUs.
A method using shared-memory occupancy shaping and elevated communication priority achieves up to 25.5% faster multi-GPU ML execution on NVIDIA and AMD GPUs.
A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.
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.
-
SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXL
SAC uses CXL to fetch only top-k KV cache entries for sparse attention models, reporting 2.1x throughput, 9.7x lower TTFT and 1.8x lower TBT versus RDMA baselines on DeepSeek-V3.2.
-
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
A CPU-GPU hybrid design with stream-loading prefill, expert parallelism, and disaggregation achieves cloud SLOs for local MoE inference on dual-socket CPUs and consumer GPUs.
-
Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads
A method using shared-memory occupancy shaping and elevated communication priority achieves up to 25.5% faster multi-GPU ML execution on NVIDIA and AMD GPUs.
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
A survey of large-model inference optimization, organized as a four-layer 'token-operations' taxonomy: multi-model fusion, model optimization, compute-model fusion, and compute-network-model fusion.