Imagen de Portada

Context Distillation as Latent Memory Management

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Ziyang, Li, Zeju, Wen, Xiangyu, Zhong, Jianyuan, Huang, Junhua, Chen, Lei, Yuan, Mingxuan, Xu, Qiang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
por: Li, Zeju, et al.
Publicado: (2026)

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
por: Wen, Xiangyu, et al.
Publicado: (2025)

DeepGate3: Towards Scalable Circuit Representation Learning
por: Shi, Zhengyuan, et al.
Publicado: (2024)

Dyve: Thinking Fast and Slow for Dynamic Process Verification
por: Zhong, Jianyuan, et al.
Publicado: (2025)

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering
por: Xu, Qiang, et al.
Publicado: (2025)

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
por: Li, Zeju, et al.
Publicado: (2025)

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
por: Zhong, Jianyuan, et al.
Publicado: (2025)

Non-Cross Diffusion for Semantic Consistency
por: Zheng, Ziyang, et al.
Publicado: (2023)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
por: Lin, Pengxiao, et al.
Publicado: (2025)

CORE: Contrastive Masked Feature Reconstruction on Graphs
por: Bo, Jianyuan, et al.
Publicado: (2025)

SATformer: Transformer-Based UNSAT Core Learning
por: Shi, Zhengyuan, et al.
Publicado: (2022)

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
por: Ng, Wen Zheng Terence, et al.
Publicado: (2025)

HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
por: Li, Yang, et al.
Publicado: (2023)

Latent Diffusion : Multi-Dimension Stable Diffusion Latent Space Explorer
por: Zhong, Zhihua, et al.
Publicado: (2025)

Quantizing Text-attributed Graphs for Semantic-Structural Integration
por: Bo, Jianyuan, et al.
Publicado: (2025)

RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning
por: Liu, Zehua, et al.
Publicado: (2026)

Large Language Models Explore by Latent Distilling
por: Zeng, Yuanhao, et al.
Publicado: (2026)

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
por: Qiu, Zeju, et al.
Publicado: (2026)

Stabilizing Reinforcement Learning for Diffusion Language Models
por: Zhong, Jianyuan, et al.
Publicado: (2026)

Memory Caching: RNNs with Growing Memory
por: Behrouz, Ali, et al.
Publicado: (2026)

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
por: Zhao, Runsong, et al.
Publicado: (2026)

Towards Mitigating Architecture Overfitting on Distilled Datasets
por: Zhong, Xuyang, et al.
Publicado: (2023)

SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training
por: Li, Zhouyang, et al.
Publicado: (2025)

ContextBench: Modifying Contexts for Targeted Latent Activation
por: Graham, Robert, et al.
Publicado: (2025)

MTLSO: A Multi-Task Learning Approach for Logic Synthesis Optimization
por: Faez, Faezeh, et al.
Publicado: (2024)

Logic Synthesis Optimization with Predictive Self-Supervision via Causal Transformers
por: Karimi, Raika, et al.
Publicado: (2024)

In-Context Compositional Q-Learning for Offline Reinforcement Learning
por: Xu, Qiushui, et al.
Publicado: (2025)

Scaling Up Probabilistic Circuits by Latent Variable Distillation
por: Liu, Anji, et al.
Publicado: (2022)

Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction
por: Qin, Zongyue, et al.
Publicado: (2025)

In-Context Planning with Latent Temporal Abstractions
por: Luo, Baiting, et al.
Publicado: (2026)

Context-Former: Stitching via Latent Conditioned Sequence Modeling
por: Zhang, Ziqi, et al.
Publicado: (2024)

Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
por: Pethkar, Kaustubh, et al.
Publicado: (2026)

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning
por: Zhang, Jianqi, et al.
Publicado: (2026)

Task-Core Memory Management and Consolidation for Long-term Continual Learning
por: Huai, Tianyu, et al.
Publicado: (2025)

MELODI: Exploring Memory Compression for Long Contexts
por: Chen, Yinpeng, et al.
Publicado: (2024)

McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting
por: Wen, Penghui, et al.
Publicado: (2026)

The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation
por: Zhang, Jiaxin, et al.
Publicado: (2026)

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
por: Yu, Hongli, et al.
Publicado: (2025)

NextMem: Towards Latent Factual Memory for LLM-based Agents
por: Zhang, Zeyu, et al.
Publicado: (2026)

Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
por: Sun, Guanglong, et al.
Publicado: (2025)