Imagen de Portada

Cognitive Chunking for Soft Prompts: Accelerating Compressor Learning via Block-wise Causal Masking

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Guojie, Wang, Yiqi, Yang, Yanfeng, Fan, Wenqi, Jian, Songlei, Zhang, Jianfeng, Yu, Jie
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Training Long-Context LLMs Efficiently via Chunk-wise Optimization
por: Li, Wenhao, et al.
Publicado: (2025)

Block-wise Adaptive Caching for Accelerating Diffusion Policy
por: Ji, Kangye, et al.
Publicado: (2025)

FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training
por: Cai, Fuhan, et al.
Publicado: (2025)

RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts
por: Yang, Jing, et al.
Publicado: (2024)

Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model
por: Peng, Shuhai, et al.
Publicado: (2026)

Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices
por: Lee, Hayun, et al.
Publicado: (2024)

MeLeMaD: Adaptive Malware Detection via Chunk-wise Feature Selection and Meta-Learning
por: K, Ajvad Haneef, et al.
Publicado: (2025)

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
por: Wang, Xi, et al.
Publicado: (2026)

DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
por: Shing, Makoto, et al.
Publicado: (2025)

Block Cascading: Training Free Acceleration of Block-Causal Video Models
por: Bandyopadhyay, Hmrishav, et al.
Publicado: (2025)

MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning
por: Liu, Jie, et al.
Publicado: (2023)

Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context
por: Ji, Shihao, et al.
Publicado: (2026)

CAFE-GB: Scalable and Stable Feature Selection for Malware Detection via Chunk-wise Aggregated Gradient Boosting
por: K, Ajvad Haneef, et al.
Publicado: (2026)

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
por: Li, Ji-Fu, et al.
Publicado: (2026)

TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding
por: Ding, Kuiye, et al.
Publicado: (2025)

SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
por: Wang, Fangyuan, et al.
Publicado: (2022)

Learning Native Continuation for Action Chunking Flow Policies
por: Liu, Yufeng, et al.
Publicado: (2026)

PromptEmbedder:: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
por: Tsai, Yu-Che, et al.
Publicado: (2026)

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
por: Wang, Xi, et al.
Publicado: (2025)

Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
por: Ye, Tiandi, et al.
Publicado: (2025)

Differentially Private Block-wise Gradient Shuffle for Deep Learning
por: Zagardo, David
Publicado: (2024)

COLI: A Hierarchical Efficient Compressor for Large Images
por: Wang, Haoran, et al.
Publicado: (2025)

Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
por: Yang, Juncheng, et al.
Publicado: (2024)

DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach
por: Chen, Qin, et al.
Publicado: (2025)

Adaptive Action Chunking via Multi-Chunk Q Value Estimation
por: Shin, Yongjae, et al.
Publicado: (2026)

Diffusion Generative Recommendation with Continuous Tokens
por: Qu, Haohao, et al.
Publicado: (2025)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
por: Zhang, Ruyi, et al.
Publicado: (2026)

Resource Efficient Sleep Staging via Multi-Level Masking and Prompt Learning
por: Ai, Lejun, et al.
Publicado: (2025)

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
por: Jiang, Yanfeng, et al.
Publicado: (2024)

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
por: Li, Yiqi, et al.
Publicado: (2025)

Chunk-Guided Q-Learning
por: Song, Gwanwoo, et al.
Publicado: (2026)

StableMask: Refining Causal Masking in Decoder-only Transformer
por: Yin, Qingyu, et al.
Publicado: (2024)

An Efficient Training Algorithm for Models with Block-wise Sparsity
por: Zhu, Ding, et al.
Publicado: (2025)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
por: Qin, Jiayu, et al.
Publicado: (2025)

Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action
por: Wang, Hong, et al.
Publicado: (2025)

Reinforcement Learning with Action Chunking
por: Li, Qiyang, et al.
Publicado: (2025)

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
por: Ouyang, Haojie, et al.
Publicado: (2025)

Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation
por: Li, Xinshu, et al.
Publicado: (2025)

Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
por: Yang, Shu, et al.
Publicado: (2025)

CausalRec: A CausalBoost Attention Model for Sequential Recommendation
por: Hou, Yunbo, et al.
Publicado: (2025)