Imagen de Portada

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Su, Guinan, Yang, Yanwu, Li, Xueyan, Geiping, Jonas
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models
por: Geiping, Jonas, et al.
Publicado: (2025)

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
por: Li, Xueyan, et al.
Publicado: (2025)

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging
por: Su, Guinan, et al.
Publicado: (2025)

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
por: Su, Guinan, et al.
Publicado: (2025)

Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert models
por: Su, Guinan, et al.
Publicado: (2025)

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
por: Li, Xueyan, et al.
Publicado: (2026)

Efficiently Dispatching Flash Attention For Partially Filled Attention Masks
por: Sharma, Agniv, et al.
Publicado: (2024)

Leviathan: Decoupling Input and Output Representations in Language Models
por: Batley, Reza T., et al.
Publicado: (2026)

Answer Matching Outperforms Multiple Choice for Language Model Evaluation
por: Chandak, Nikhil, et al.
Publicado: (2025)

A Watermark for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)

Residual Stream Analysis with Multi-Layer SAEs
por: Lawson, Tim, et al.
Publicado: (2024)

Coercing LLMs to do and reveal (almost) anything
por: Geiping, Jonas, et al.
Publicado: (2024)

LMD3: Language Model Data Density Dependence
por: Kirchenbauer, John, et al.
Publicado: (2024)

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
por: Boreiko, Valentyn, et al.
Publicado: (2024)

State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning
por: Aviss, Thea
Publicado: (2026)

Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism
por: Sohn, Gina, et al.
Publicado: (2025)

Scaling Open-Ended Reasoning to Predict the Future
por: Chandak, Nikhil, et al.
Publicado: (2025)

The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
por: Kerce, J. Clayton, et al.
Publicado: (2026)

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models
por: Dam, Harvey, et al.
Publicado: (2025)

Understanding Gated Neurons in Transformers from Their Input-Output Functionality
por: Gerstner, Sebastian, et al.
Publicado: (2025)

Stream of Search (SoS): Learning to Search in Language
por: Gandhi, Kanishk, et al.
Publicado: (2024)

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern
por: Tang, Hongyin, et al.
Publicado: (2024)

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
por: Li, Shiwei, et al.
Publicado: (2025)

One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space
por: Addanki, Raghav, et al.
Publicado: (2023)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
por: Hans, Abhimanyu, et al.
Publicado: (2024)

Parallel Scaling Law for Language Models
por: Chen, Mouxiang, et al.
Publicado: (2025)

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
por: Li, Zihao, et al.
Publicado: (2025)

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
por: Yang, Zhipeng, et al.
Publicado: (2025)

On the Reliability of Watermarks for Large Language Models
por: Kirchenbauer, John, et al.
Publicado: (2023)

Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
por: Kavumba, Pride, et al.
Publicado: (2026)

Residual Matrix Transformers: Scaling the Size of the Residual Stream
por: Mak, Brian, et al.
Publicado: (2025)

Online Cascade Learning for Efficient Inference over Streams
por: Nie, Lunyiu, et al.
Publicado: (2024)

MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation
por: Yang, Yanwu, et al.
Publicado: (2025)

SpeakStream: Streaming Text-to-Speech with Interleaved Data
por: Bai, Richard He, et al.
Publicado: (2025)

Capability-Based Scaling Trends for LLM-Based Red-Teaming
por: Panfilov, Alexander, et al.
Publicado: (2025)

Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
por: Bai, Junwen, et al.
Publicado: (2024)

Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
por: Goh, Hui Wen, et al.
Publicado: (2026)

Small Language Models Improve Giants by Rewriting Their Outputs
por: Vernikos, Giorgos, et al.
Publicado: (2023)

SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale
por: Gueuwou, Shester, et al.
Publicado: (2024)

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
por: McLeish, Sean, et al.
Publicado: (2025)