Image de couverture de livre

Harnessing Consistency for Robust Test-Time LLM Ensemble

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zeng, Zhichen, Yu, Qi, Lin, Xiao, Qiu, Ruizhong, Ning, Xuying, Wei, Tianxin, Yan, Yuchen, He, Jingrui, Tong, Hanghang
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Subspace Alignment for Vision-Language Model Test-time Adaptation
par: Zeng, Zhichen, et autres
Publié: (2026)

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
par: Cui, Chengming, et autres
Publié: (2026)

Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning
par: Bao, Wenxuan, et autres
Publié: (2025)

Saffron-1: Safety Inference Scaling
par: Qiu, Ruizhong, et autres
Publié: (2025)

Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics
par: Zeng, Zhichen, et autres
Publié: (2025)

Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation
par: Bao, Wenxuan, et autres
Publié: (2024)

ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification
par: Lin, Xiao, et autres
Publié: (2026)

FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
par: He, Xinrui, et autres
Publié: (2026)

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
par: Liu, Zhining, et autres
Publié: (2025)

CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
par: Lin, Xiao, et autres
Publié: (2025)

AvAtar: Learning to Align via Active Optimal Transport
par: Yu, Qi, et autres
Publié: (2026)

PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
par: Yu, Qi, et autres
Publié: (2025)

TSAQA: Time Series Analysis Question And Answering Benchmark
par: Jing, Baoyu, et autres
Publié: (2026)

Flow Matching Meets Biology and Life Science: A Survey
par: Li, Zihao, et autres
Publié: (2025)

Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
par: Qiu, Ruizhong, et autres
Publié: (2024)

CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
par: Wei, Tianxin, et autres
Publié: (2025)

WAPITI: A Watermark for Finetuned Open-Source LLMs
par: Chen, Lingjie, et autres
Publié: (2024)

AIM: Attributing, Interpreting, Mitigating Data Unfairness
par: Liu, Zhining, et autres
Publié: (2024)

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
par: Bei, Yuanchen, et autres
Publié: (2026)

Graph4MM: Weaving Multimodal Learning with Structural Information
par: Ning, Xuying, et autres
Publié: (2025)

BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
par: Lin, Xiao, et autres
Publié: (2024)

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
par: Xu, Haobo, et autres
Publié: (2026)

Graph Data Selection for Domain Adaptation: A Model-Free Approach
par: Li, Ting-Wei, et autres
Publié: (2025)

TUCKET: A Tensor Time Series Data Structure for Efficient and Accurate Factor Analysis over Time Ranges
par: Qiu, Ruizhong, et autres
Publié: (2025)

How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark
par: Qiu, Ruizhong, et autres
Publié: (2024)

Class-Imbalanced Graph Learning without Class Rebalancing
par: Liu, Zhining, et autres
Publié: (2023)

Joint Optimal Transport and Embedding for Network Alignment
par: Yu, Qi, et autres
Publié: (2025)

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
par: Li, Ting-Wei, et autres
Publié: (2026)

PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis
par: He, Xinyu, et autres
Publié: (2025)

Panda: Test-Time Adaptation with Negative Data Augmentation
par: Deng, Ruxi, et autres
Publié: (2025)

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
par: Ning, Xuying, et autres
Publié: (2026)

Geometric-disentangelment Unlearning
par: Zhou, Duo, et autres
Publié: (2025)

PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
par: Zhao, Yanjun, et autres
Publié: (2026)

Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
par: Qiu, Ruizhong, et autres
Publié: (2025)

Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
par: Qiu, Ruizhong, et autres
Publié: (2026)

ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
par: Ai, Mengting, et autres
Publié: (2025)

Ask, and it shall be given: On the Turing completeness of prompting
par: Qiu, Ruizhong, et autres
Publié: (2024)

LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
par: He, Xinrui, et autres
Publié: (2024)

Logic Query of Thoughts: Guiding Large Language Models to Answer Complex Logic Queries with Knowledge Graphs
par: Liu, Lihui, et autres
Publié: (2024)

Hierarchical LoRA MoE for Efficient CTR Model Scaling
par: Zeng, Zhichen, et autres
Publié: (2025)