{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs","json":"https://digestai.news/story/researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs.json","markdown":"https://digestai.news/story/researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs.md","slug":"researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs","headline":"Researchers propose tracequery to cut diffusion LLM inference costs","summary":"A new method called TRACEQUERY aims to reduce the computational cost of diffusion-based large language models (dLLMs) by focusing recomputation on relevant parts of the generation trajectory. The paper, posted on arXiv, argues that existing cache-based approaches waste resources by recomputing tokens on a fixed schedule or based on heuristics. Instead, TRACEQUERY uses full-denoising trajectories to predict which positions need recomputation, minimizing fresh calculations while maintaining accuracy.\n\nThe authors claim TRACEQUERY outperforms other cache-based methods in balancing quality and computation efficiency. It works across tasks, model variants, and families, according to the paper. The code is available on GitHub under the repository [tracequery](https://github.com/fish1928/tracequery.git).","keyPoints":["TRACEQUERY predicts trajectory-relevant positions to reduce token recomputation in dLLMs","Method claims stronger quality-computation trade-off than existing cache-based approaches","Code released on GitHub for further research and implementation"],"whyItMatters":"If validated, TRACEQUERY could lower inference costs for diffusion models, making them more practical for real-time applications.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["diffusion large language models (dLLMs)"],"people":[]},"firstPublishedAt":"2026-10-27T04:00:00Z","updatedAt":"2026-10-27T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"TraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models","url":"https://arxiv.org/abs/2610.33008","publishedAt":"2026-10-27T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose tracequery to cut diffusion LLM inference costs\", 27 October 2026, https://digestai.news/story/researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs","publisher":"Digest AI","title":"Researchers propose tracequery to cut diffusion LLM inference costs","datePublished":"2026-10-27T04:00:00Z","url":"https://digestai.news/story/researchers-propose-tracequery-to-cut-diffusion-llm-inference-costs"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}