Research / AI/ML Paper
arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.
The page clearly describes an AI/ML research contribution focused on LLM inference acceleration. The abstract gives enough evidence for a useful public listing: it states the problem, the proposed method, the hardware co-design angle, and reported benchmark gains.
This is only the arXiv abstract page, so visitors cannot see implementation details, code availability, datasets, or whether the approach is reproducible outside the paper.
Last evaluated 4 days ago. Current rank #411. Holding steady in the rankings.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.
