paper-with-me

홈 › Papers

A request for clarity over the End of Sequence token in the Self-Critical Sequence Training

2023-05-20 · Jia Cheng Hu, Roberto Cavicchioli, Alessandro Capotondi

The Image Captioning research field is currently compromised by the lack of transparency and awareness over the End-of-Sequence token (<Eos>) in the Self-Critical Sequence Training. If the <Eos> token is omitted, a model can boost its performance up to +4.1 CIDEr-D using trivial sentence fragments. While this phenomenon poses an obstacle to a fair evaluation and comparison of established works, people involved in new projects are given the arduous choice between lower scores and unsatisfactory descriptions due to the competitive nature of the research. This work proposes to solve the problem by spreading awareness of the issue itself. In particular, we invite future works to share a simple and informative signature with the help of a library called SacreEOS. Code available at \emph{\href{https://github.com/jchenghu/sacreeos}{https://github.com/jchenghu/sacreeos}}

📄 PDF Abstract BibTeX arXiv:2305.12254

Code (2)

jchenghu/captioning_eos 공식 구현 pytorch
jchenghu/sacreeos 공식 구현 pytorch

Tasks

Image CaptioningSentence

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference

2026-03-13 · Huamin Chen, Xunzhuo Liu, Junchen Jiang, Bowei He 외 arxiv

Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and simultaneously triggering KV-cache failures -- OOM crashes, preemption …

CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies

2025-12-18 · John M. Statheros, Hairong Wang, Richard Klein arxiv

The interpretation of chest X-rays (CXRs) poses significant challenges, particularly in achieving accurate multi-label pathology classification and spatial localization. These tasks demand different levels of annotation …

Multi-Label Classification

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

2024-11-07 · Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-b…

Code GenerationLanguage ModelingLanguage ModellingLarge Language Model+3

MoLoRA: Composable Specialization via Per-Token Adapter Routing

2026-03-16 · Shrey Shah, Justin Wagle arxiv

Multi-adapter serving systems route entire sequences to a single adapter, forcing a choice when requests span multiple domains. This assumption fails in two important settings: (1) multimodal generation, where text and i…

multimodal generation

Intra-request branch orchestration for efficient LLM reasoning

2025-09-29 · Weifan Jiang, Rana Shahout, Yilun Du, Michael Mitzenmacher 외 arxiv

Large Language Models (LLMs) increasingly rely on inference-time reasoning algorithms such as chain-of-thought and multi-branch reasoning to improve accuracy on complex tasks. These methods, however, substantially increa…