Buchumschlag

OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Deng, Yuchen, Cai, Zidang, Zheng, Hai-Tao, Wang, Jie, Yang, Feidiao, Han, Yuxing
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
von: Kim, Jaeik, et al.
Veröffentlicht: (2026)

OmniRefiner: Reinforcement-Guided Local Diffusion Refinement
von: Liu, Yaoli, et al.
Veröffentlicht: (2025)

Beyond Boundary Frames: Context-Centric Video Interpolation with Audio-Visual Semantics
von: Deng, Yuchen, et al.
Veröffentlicht: (2025)

OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
von: Tao, Keda, et al.
Veröffentlicht: (2025)

DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression
von: Li, Bingzhou, et al.
Veröffentlicht: (2026)

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
von: Li, Yunxin, et al.
Veröffentlicht: (2025)

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
von: Luo, Run, et al.
Veröffentlicht: (2025)

Demographic and Linguistic Bias Evaluation in Omnimodal Language Models
von: Elobaid, Alaa
Veröffentlicht: (2026)

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
von: Yang, Morunliu, et al.
Veröffentlicht: (2026)

Model Compression and Efficient Inference for Large Language Models: A Survey
von: Wang, Wenxiao, et al.
Veröffentlicht: (2024)

BackSlash: Rate Constrained Optimized Training of Large Language Models
von: Wu, Jun, et al.
Veröffentlicht: (2025)

Direct Alignment of Language Models via Quality-Aware Self-Refinement
von: Yu, Runsheng, et al.
Veröffentlicht: (2024)

Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
von: Li, Yinghui, et al.
Veröffentlicht: (2025)

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models
von: Wu, Hui, et al.
Veröffentlicht: (2026)

Scaling Language-Centric Omnimodal Representation Learning
von: Xiao, Chenghao, et al.
Veröffentlicht: (2025)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
von: Wu, Yecheng, et al.
Veröffentlicht: (2026)

Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Models
von: Zhao, Jie, et al.
Veröffentlicht: (2025)

ChronusOmni: Improving Time Awareness of Omni Large Language Models
von: Chen, Yijing, et al.
Veröffentlicht: (2025)

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
von: Liu, Xuxu, et al.
Veröffentlicht: (2025)

FLAME: Factuality-Aware Alignment for Large Language Models
von: Lin, Sheng-Chieh, et al.
Veröffentlicht: (2024)

IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
von: Zhang, Yiming, et al.
Veröffentlicht: (2025)

RoboEgo System Card: An Omnimodal Model with Native Full Duplexity
von: Yao, Yiqun, et al.
Veröffentlicht: (2025)

EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
von: Yao, Yiqun, et al.
Veröffentlicht: (2025)

ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models
von: Yoon, Junho, et al.
Veröffentlicht: (2025)

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
von: Oh, Yeongtak, et al.
Veröffentlicht: (2026)

When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models
von: Wang, Weilan, et al.
Veröffentlicht: (2025)

LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
von: Yang, Ge, et al.
Veröffentlicht: (2024)

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
von: Hong, Jack, et al.
Veröffentlicht: (2025)

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
von: Yan, Xinru, et al.
Veröffentlicht: (2026)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
von: Liu, Biao, et al.
Veröffentlicht: (2025)

Multimodal Quantitative Language for Generative Recommendation
von: Zhai, Jianyang, et al.
Veröffentlicht: (2025)

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
von: Ding, Yue, et al.
Veröffentlicht: (2026)

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
von: Guan, Tong, et al.
Veröffentlicht: (2025)

FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
von: Deng, Yuchen, et al.
Veröffentlicht: (2025)

OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing
von: Bie, Fuqing, et al.
Veröffentlicht: (2025)

R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning
von: Shan, Hongyu, et al.
Veröffentlicht: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
von: Xi, Zhiheng, et al.
Veröffentlicht: (2023)

Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning
von: Li, Zhaoxing, et al.
Veröffentlicht: (2026)

MAR: Efficient Large Language Models via Module-aware Architecture Refinement
von: Cai, Junhong, et al.
Veröffentlicht: (2026)

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
von: Tang, Jianting, et al.
Veröffentlicht: (2025)