paper-with-me

Long-Context Understanding

6개 벤치마크 · 논문 134편 · 이 태스크의 논문 보기 →

Benchmarks

AA-LCR

결과 523개

MMNeedle

결과 12개

Ada-LEval (BestAnswer)

결과 10개

Ada-LEval (TSort)

결과 10개

L-Eval

결과 4개

LongBench

결과 3개

Most implemented

GPT-4 Technical Report

2023-03-15 · 구현 11개

K-EXAONE 2.0 Technical Report

2026-08-05 · 구현 8개

Motif 3: Technical Report

2026-08-10 · 구현 6개

Papers

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

2026-09-11 · Zhiwei Li, Lei Zhu, Hao Gu, Xiang Hu 외 hf

Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for each query. Existing trainable methods us…

Long-Context Understanding

Safin-1: Safety from Within through Memory-Native State Evolution

2026-08-31 · Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua 외 hf

Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic property of the model itself, rather than a be…

Long-Context UnderstandingTest-time Adaptation

OmniAlign: A Unified Multilingual Aligner for Word and Sentence Alignment

2026-08-19 · Mengpeng Yang, Jingxu Yang, Chao Chen, Tian Xia 외 arxiv

Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords. Existing tools, however, typically specialize in a …

Long-Context UnderstandingSelf-Supervised LearningWord Alignment

Motif 3: Technical Report

2026-08-10 · Junghwan Lim, Joon Son Chung, Sungmin Lee, Wai Ting Cheung 외 hf

We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each sparse MoE layer contains 384 routed experts, with eight selected per to…

Long-Context UnderstandingReinforcement LearningMathematical ReasoningInstruction Following

K-EXAONE 2.0 Technical Report

2026-08-05 · Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong 외 hf

This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scra…

Long-Context Understanding

LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis

2026-07-07 · Chenhao Yuan, Yinhao Xu, Shuwen Xu, Xizhi Yang 외 arxiv

Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs), yet existing approaches share three limitations: narrow task covera…

Long-Context Understanding

전체 134편 보기 →