Cover Image

Token-Level Inference-Time Alignment for Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Kejia, Zhang, Jiawen, Hu, Jiacong, Gao, Kewei, Lou, Jian, Feng, Zunlei, Song, Mingli
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
by: Chen, Kejia, et al.
Published: (2025)

Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
by: Zhang, Shengxuming, et al.
Published: (2024)

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
by: Hu, Jiacong, et al.
Published: (2022)

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
by: Chen, Kejia, et al.
Published: (2025)

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
by: Chen, Kejia, et al.
Published: (2026)

A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
by: Bei, Yijun, et al.
Published: (2024)

Rethinking Token Reduction for Large Vision-Language Models
by: Wang, Yi, et al.
Published: (2026)

Knowledge Amalgamation for Object Detection with Transformers
by: Zhang, Haofei, et al.
Published: (2022)

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
by: Zhang, Jiawen, et al.
Published: (2025)

Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
by: Liu, Kejia, et al.
Published: (2026)

Improving Adversarial Robustness via Feature Pattern Consistency Constraint
by: Hu, Jiacong, et al.
Published: (2024)

$D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation
by: Wang, Ruizhi, et al.
Published: (2026)

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
by: Yang, Cheng, et al.
Published: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
by: Zhang, Jusheng, et al.
Published: (2025)

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
by: Li, Kaiyuan, et al.
Published: (2025)

Dynamic Token Reduction during Generation for Vision Language Models
by: Liang, Xiaoyu, et al.
Published: (2025)

SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
by: Qian, Chen, et al.
Published: (2026)

Collaborative Edge-to-Server Inference for Vision-Language Models
by: Song, Soochang, et al.
Published: (2025)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
by: Meng, Yu, et al.
Published: (2025)

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
by: Zhang, Kewei, et al.
Published: (2026)

Deep Feature Response Discriminative Calibration
by: Xu, Wenxiang, et al.
Published: (2024)

Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
by: Yang, Jiazhen, et al.
Published: (2026)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
by: Feng, Qianhan, et al.
Published: (2024)

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
by: Arif, Kazi Hasan Ibn, et al.
Published: (2024)

Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios
by: Wang, Yuxin, et al.
Published: (2024)

RS3DBench: A Comprehensive Benchmark for 3D Spatial Perception in Remote Sensing
by: Wang, Jiayu, et al.
Published: (2025)

Object-Centric Vision Token Pruning for Vision Language Models
by: Li, Guangyuan, et al.
Published: (2025)

Safety Alignment for Vision Language Models
by: Liu, Zhendong, et al.
Published: (2024)

ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition
by: Xue, Mengqi, et al.
Published: (2022)

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
by: He, Jialuo, et al.
Published: (2026)

TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
by: Li, Ao, et al.
Published: (2025)

CorrDetail: Visual Detail Enhanced Self-Correction for Face Forgery Detection
by: Zhou, Binjia, et al.
Published: (2025)

Enhancing Vision-Language Model with Unmasked Token Alignment
by: Liu, Jihao, et al.
Published: (2024)

B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
by: Lu, Zhuqiang, et al.
Published: (2024)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
by: Shaulov, Ariel, et al.
Published: (2026)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
by: Kang, Beomseok, et al.
Published: (2026)

Subspace Alignment for Vision-Language Model Test-time Adaptation
by: Zeng, Zhichen, et al.
Published: (2026)

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
by: Saini, Harshvardhan, et al.
Published: (2026)

Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
by: Chen, Shimin, et al.
Published: (2024)