Copertina

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tong, Jintao, Jin, Wenwei, Qin, Pengda, Li, Anqi, Zou, Yixiong, Li, Yuhong, Li, Yuhua, Li, Ruixuan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling
di: Li, Anqi, et al.
Pubblicazione: (2025)

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
di: Tong, Jintao, et al.
Pubblicazione: (2024)

Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
di: Tong, Jintao, et al.
Pubblicazione: (2025)

Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
di: Zhou, Haichen, et al.
Pubblicazione: (2024)

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
di: Tong, Jintao, et al.
Pubblicazione: (2025)

FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching
di: Sari, Alp Eren, et al.
Pubblicazione: (2025)

MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
di: Zhang, Zhenyu, et al.
Pubblicazione: (2024)

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2026)

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2025)

Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning
di: Jiang, Yongwei, et al.
Pubblicazione: (2025)

Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
di: Ma, Ran, et al.
Pubblicazione: (2024)

Random Registers for Cross-Domain Few-Shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2025)

Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
di: Jiang, Yongwei, et al.
Pubblicazione: (2026)

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2026)

The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
di: Liu, Yuhan, et al.
Pubblicazione: (2025)

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
di: Zhao, Yaze, et al.
Pubblicazione: (2026)

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow
di: Bai, Jiaqi, et al.
Pubblicazione: (2025)

Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition
di: Zhang, Zhenyu, et al.
Pubblicazione: (2024)

ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
di: Mei, Jingbiao, et al.
Pubblicazione: (2025)

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
di: Zhang, Zhenyu, et al.
Pubblicazione: (2026)

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
di: Zou, Yixiong, et al.
Pubblicazione: (2024)

Compositional Few-Shot Class-Incremental Learning
di: Zou, Yixiong, et al.
Pubblicazione: (2024)

Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
di: Zhao, Yaze, et al.
Pubblicazione: (2026)

Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants
di: Li, Chongyang, et al.
Pubblicazione: (2025)

FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference
di: Li, Kunxi, et al.
Pubblicazione: (2025)

Adversarial Attack for Explanation Robustness of Rationalization Models
di: Zhang, Yuankai, et al.
Pubblicazione: (2024)

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2024)

ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
di: Li, Gengyang, et al.
Pubblicazione: (2025)

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

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
di: Xiao, Ruixuan, et al.
Pubblicazione: (2024)

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
di: Tran, Toan, et al.
Pubblicazione: (2025)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
di: Miao, Yongzhu, et al.
Pubblicazione: (2023)

Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
di: Li, Yinghui, et al.
Pubblicazione: (2024)

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following
di: Li, Jinnan, et al.
Pubblicazione: (2025)

Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm
di: Mo, Yuhong, et al.
Pubblicazione: (2024)

CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning
di: Lan, Yangsong, et al.
Pubblicazione: (2026)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
di: Ding, Yi, et al.
Pubblicazione: (2025)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
di: Jin, Zehao, et al.
Pubblicazione: (2026)

Affective Flow Language Model for Emotional Support Conversation
di: Zou, Chenghui, et al.
Pubblicazione: (2026)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
di: Li, Xue, et al.
Pubblicazione: (2025)