CCTest · Blog
MC-Sparse Narrows the Dense–Sparse Attention Gap in Diffusion Transformers
Diffusion Models
cctest.ai
Diffusion Models

MC-Sparse Narrows the Dense–Sparse Attention Gap in Diffusion Transformers

MC-Sparse analyzes why sparse attention can damage fidelity in long-sequence diffusion generation and introduces a training-free approach built around fine-grained KV selection and metadata reuse. The method reports substantial denoising speedups for video and 3D generation with negligible quality loss.

Read more
CCTest · Blog
When Clinical AI Listens Too Much: How Irrelevant Speech Enters Patient Notes
Evaluation & Benchmarks
cctest.ai

When Clinical AI Listens Too Much: How Irrelevant Speech Enters Patient Notes

A new study finds that language models can carry small talk and background speech into clinical notes, sometimes misattributing it or using it in reasoning. The results suggest that medical AI needs dedicated tests for resistance to incidental information, not just conventional quality scores.

Read more
CCTest · Blog
SparseDecoding Makes LLM Pruning Aware of Generation
Inference & Serving
cctest.ai

SparseDecoding Makes LLM Pruning Aware of Generation

SparseDecoding targets two practical gaps in LLM inference: pruning calibration often uses data unlike the model’s own generated tokens, while existing sparse kernels frequently emphasize SpMM rather than decoding-heavy SpMV. Its decoding-aware method and N:M sparse kernel deliver up to 1.48× end-to-end decoding speedup on A100 GPUs.

Read more