paper-with-me

Papers Long-Context Understanding

“Long-Context Understanding” 태그가 달린 논문 134편 · 필터 해제

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

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

2026-07-01 · Ji Ha Jang, Hayeon Kim, Chulwon Lee, Junghun James Kim 외 arxiv

CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions (>77 tokens) due to absolute positional encoding and pretraining on …

Long-Context UnderstandingCross-Modal Retrieval

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

2026-06-25 · Aoyang Fang, Yifan Yang, Jin'ao Shang, Qisheng Lu 외 arxiv

Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suffer from a fundamental gap: they label on…

Long-Context Understanding

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

2026-06-05 · Rishi Desai, Jesse Hu, Joan Cabezas, Neel Harsola 외 arxiv

AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form ta…

Long-Context Understanding

Personal AI Agent for Camera Roll VQA

2026-06-03 · Thao Nguyen, Krishna Kumar Singh, Donghyun Kim, Yong Jae Lee 외 arxiv

We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from si…

Long-Context UnderstandingVisual Question Answering

Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders

2026-05-28 · Pierre-Antoine Lequeu, Camille Barboule, Benjamin Piwowarski arxiv

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still s…

Long-Context Understanding

MiA-Signature: Approximating Global Activation for Long-Context Understanding

2026-05-07 · Yuqing Li, Jiangnan Li, Mo Yu, Zheng Lin 외 arxiv

A growing body of work in cognitive science suggests that reportable conscious access is associated with \emph{global ignition} over distributed memory systems, while such activation is only partially accessible as indiv…

Long-Context Understanding

On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility

2026-05-02 · Zhitao He, Haolin Yang, Rui Min, Zeyu Qin 외 arxiv

Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volat…

Long-Context Understanding

FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control

2026-04-21 · Pingwei Sun, Yuxuan Hu, Jianchao Tan, Xue Wang 외 arxiv

Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have …

Long-Context UnderstandingComputational Efficiency

Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation

2026-04-15 · Zichong Li, Chen Liang, Liliang Ren, Tuo Zhao 외 arxiv

Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation and multi-document reasoning. A common strategy is to fine-tune pretr…

Long-Context Understanding

Mi:dm K 2.5 Pro

2026-03-19 · KT Tech innovation Group arxiv

The evolving LLM landscape requires capabilities beyond simple text generation, prioritizing multi-step reasoning, long-context understanding, and agentic workflows. This shift challenges existing models in enterprise en…

Long-Context UnderstandingReinforcement LearningText Generation

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

2026-03-11 · Jinwoo Ahn, Ingyu Seong, Akhil Kedia, Junhan Kim 외 arxiv

Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearl…

Long-Context Understanding

Sabiá-4 Technical Report

2026-03-10 · Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior 외 arxiv

This technical report presents Sabiá-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: con…

Long-Context UnderstandingInstruction Following

AutoFigure-Edit: Generating Editable Scientific Illustration

2026-03-03 · Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li 외 arxiv

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We…

Long-Context Understanding

Memory Caching: RNNs with Growing Memory

2026-02-27 · Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong 외 arxiv

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval t…

Long-Context Understanding
1–20 / 134 다음 →