Image de couverture de livre

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Xinyu, Liu, Xin, Jin, Bo, Zhao, Runsong, Huang, Pengcheng, Ruan, Junhao, Li, Bei, Xiao, Chunyang, Wang, Chenglong, Xiao, Tong, Zhu, Jingbo
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
par: Zhao, Runsong, et autres
Publié: (2024)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
par: Liu, Xin, et autres
Publié: (2025)

Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
par: Liu, Xinyu, et autres
Publié: (2024)

NDP: Next Distribution Prediction as a More Broad Target
par: Ruan, Junhao, et autres
Publié: (2024)

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
par: Zhao, Runsong, et autres
Publié: (2026)

Translate-and-Revise: Boosting Large Language Models for Constrained Translation
par: Huang, Pengcheng, et autres
Publié: (2024)

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method
par: Liu, Xinyu, et autres
Publié: (2025)

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
par: Zhao, Runsong, et autres
Publié: (2026)

MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
par: Ruan, Junhao, et autres
Publié: (2026)

Causal Autoregressive Diffusion Language Model
par: Ruan, Junhao, et autres
Publié: (2026)

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment
par: Fan, Yuchun, et autres
Publié: (2025)

MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
par: Wang, Jianjin, et autres
Publié: (2025)

Hybrid Alignment Training for Large Language Models
par: Wang, Chenglong, et autres
Publié: (2024)

MemoBrain: Executive Memory as an Agentic Brain for Reasoning
par: Qian, Hongjin, et autres
Publié: (2026)

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval
par: Zhang, Yuwei, et autres
Publié: (2025)

CoMemo: LVLMs Need Image Context with Image Memory
par: Liu, Shi, et autres
Publié: (2025)

EIT: Enhanced Interactive Transformer
par: Zheng, Tong, et autres
Publié: (2022)

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
par: Luo, Yingfeng, et autres
Publié: (2026)

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
par: Du, Junhao, et autres
Publié: (2026)

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
par: Tang, Jiwei, et autres
Publié: (2026)

ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
par: Ho, Matthew, et autres
Publié: (2025)

Memo
Publié: (2020)

Foundations of Large Language Models
par: Xiao, Tong, et autres
Publié: (2025)

MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
par: Wang, Chenglong, et autres
Publié: (2025)

MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
par: Tan, Xingyu, et autres
Publié: (2025)

CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework
par: Wu, Wentao, et autres
Publié: (2025)

Efficient Prompting Methods for Large Language Models: A Survey
par: Chang, Kaiyan, et autres
Publié: (2024)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
par: Zeng, Fanhu, et autres
Publié: (2025)

Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study
par: Mu, Yongyu, et autres
Publié: (2025)

APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
par: Chang, Kaiyan, et autres
Publié: (2026)

SUBQRAG: Sub-Question Driven Dynamic Graph RAG
par: Li, Jiaoyang, et autres
Publié: (2025)

Storyline Memo
par: Anonymous
Publié: (2025)

Prior Constraints-based Reward Model Training for Aligning Large Language Models
par: Zhou, Hang, et autres
Publié: (2024)

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
par: Tong, Yujia, et autres
Publié: (2026)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
par: Yu, Hanxun, et autres
Publié: (2026)

MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
par: Qian, Hongjin, et autres
Publié: (2024)

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
par: Huang, Yuxiang, et autres
Publié: (2025)

QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression
par: Wang, Wenshan, et autres
Publié: (2024)

GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning
par: Wang, Chenglong, et autres
Publié: (2025)

PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning
par: Xiao, Hengbo, et autres
Publié: (2025)