Chenxu Niu

Chenxu Niu, Yiming Sun · nvidia

Understanding the geographic reach and community structure of one's scholarly citations is increasingly valuable for career development, grant applications, and collaboration discovery -- yet accessible tools for answering these questions remain scarce. Existing bibliometric platforms either require costly institutional subscriptions or expose only aggregate citation counts without granular per-author metadata. We present CiteRadar, an open-source system that accepts a single Google Scholar user identifier and automatically produces a structured output folder containing: the author's complete publication list, all retrieved citing papers with enriched author metadata, two ranked author tables (by citation frequency and by h-index), a plain-text statistical summary, and a self-contained interactive HTML world map -- all from a single command-line invocation. CiteRadar integrates five heterogeneous data sources -- Google Scholar, OpenAlex, CrossRef, Semantic Scholar, and OpenStreetMap Nominatim -- through a carefully engineered five-stage pipeline. Key technical contributions include: (1) a Scholar meta-string parser resilient to Unicode non-breaking-space separators, a pervasive but undocumented quirk in Scholar's HTML that silently corrupts venue and year fields when unhandled; (2) a two-stage author disambiguation system using stop-word-filtered institution name similarity to guard against the well-known same-name entity-merging failure mode in bibliometric databases, demonstrated to eliminate h-index attribution errors of up to 9x the correct value; (3) an OpenAlex web-URL to API-URL conversion fix that raises the fraction of author records with city-level location data from 0% to ~60%; and (4) a logarithmically-scaled interactive Folium world map with per-city researcher popups, rendered as a fully self-contained HTML file.

Chenxu Niu, Wei Zhang, Jie Li et al.

Large language model (LLM) services now answer billions of queries per day, and industry reports show that inference, not training, accounts for more than 90% of total power consumption. However, existing benchmarks focus on either training/fine-tuning or performance of inference and provide little support for power consumption measurement and analysis of inference. We introduce TokenPowerBench, the first lightweight and extensible benchmark designed for LLM-inference power consumption studies. The benchmark combines (i) a declarative configuration interface covering model choice, prompt set, and inference engine, (ii) a measurement layer that captures GPU-, node-, and system-level power without specialized power meters, and (iii) a phase-aligned metrics pipeline that attributes energy to the prefill and decode stages of every request. These elements make it straight-forward to explore the power consumed by an LLM inference run; furthermore, by varying batch size, context length, parallelism strategy and quantization, users can quickly assess how each setting affects joules per token and other energy-efficiency metrics. We evaluate TokenPowerBench on four of the most widely used model series (Llama, Falcon, Qwen, and Mistral). Our experiments cover from 1 billion parameters up to the frontier-scale Llama3-405B model. Furthermore, we release TokenPowerBench as open source to help users to measure power consumption, forecast operating expenses, and meet sustainability targets when deploying LLM services.

Zixian Huang, Chenxu Niu, Yu Gu et al.

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a bottleneck limiting the generation speed. In this paper, we propose a new decoder architecture that efficiently generates text in parallel for context-aware generation tasks. Our proposed pipelined decoder initiates the generation of multiple subsequences simultaneously, and, at each time-step, it generates a new token for each subsequence to realize parallelism. Experiments on multiple text generation tasks, including question answering, text summarization, and keyphrase generation, show that our pipelined decoder significantly improves the generation speed without a significant loss of generation quality or additional memory consumption.