How do we most effectively treat a disease or condition? Ideally, we could consult a database of evidence gleaned from clinical trials to answer such questions. Unfortunately, no such database exists; clinical trial results are instead disseminated primarily via lengthy natural language articles. Perusing all such articles would be prohibitively time-consuming for healthcare practitioners; they instead tend to depend on manually compiled systematic reviews of medical literature to inform care.
NLP may speed this process up, and eventually facilitate immediate consult of published evidence. The Evidence Inference dataset was recently released to facilitate research toward this end. This task entails inferring the comparative performance of two treatments, with respect to a given outcome, from a particular article (describing a clinical trial) and identifying supporting evidence. For instance: Does this article report that chemotherapy performed better than surgery for five-year survival rates of operable cancers? In this paper, we collect additional annotations to expand the Evidence Inference dataset by 25\%, provide stronger baseline models, systematically inspect the errors that these make, and probe dataset quality. We also release an abstract only (as opposed to full-texts) version of the task for rapid model prototyping. The updated corpus, documentation, and code for new baselines and evaluations are available at http://evidence-inference.ebm-nlp.com/.
DPUV3INT8: A Compiler View to programmable FPGA Inference Engines
我们有一个FPGA设计，我们使它快速，高效，并测试了几个重要的例子。现在，我们必须推断出一个在数据中心部署的通用解决方案。在这里，我们描述了FPGA DPUV 3 INT 8的设计和我们的编译器的工作。针对Resnet50\_v1的手动调优SW-HW解决方案的每秒图像（吞吐量）比我们最好的FPGA实现高（接近）2倍;编译器将手写技术推广到同一示例，实现了约1.5倍的性能，编译器将优化推广到网络模型动物园，并实现了80+\%的HW效率。
Byte Latent Transformer: Patches Scale Better Than Tokens
FAIR at Meta（Meta FAIR研究院）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；University of Chicago（芝加哥大学）
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
King’s College London（伦敦国王学院）；AQA；The Alan Turing Institute（艾伦·图灵研究所）；Tencent YouTu Lab（腾讯YouTu实验室）；University of Cambridge（剑桥大学）；Queen Mary University of London（伦敦大学玛丽女王学院）
针对 ASAS 中 LLM 评分缺乏可解释性且难以及早发现细微推理错误的问题，本文提出基于结构推理图差异的对比反思合成流程与双模型反思评分框架 DARS，并在全部指标上超越基线。
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Department of Data Science & AI, Monash University（墨尔本大学数据科学与人工智能系）；Faculty of Medicine Dentistry and Health Sciences, University of Melbourne（墨尔本大学医学牙科与健康科学学院）；Department of Computer Science, University College London（伦敦大学学院计算机科学系）
