paper-with-me

Papers Token Reduction

“Token Reduction” 태그가 달린 논문 78편 · 필터 해제

Learning Compact Vision Tokens for Efficient Large Multimodal Models

2025-06-08 · Hao Tang, Chengchao Shen

Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we ex…

Multimodal ReasoningToken Reduction

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration

2025-06-06 · Fanhu Zeng, Deli Yu, Zhenglun Kong, Hao Tang

Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods ma…

Depth Estimationobject-detectionObject DetectionToken Reduction

Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers

2025-06-05 · Haosong Liu, Yuge Cheng, Zihan Liu, Aiyue Chen 외

Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment. While existing acceleration methods …

GPUText-to-Video GenerationToken ReductionVideo Generation

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

2025-06-05 · Yubo Ma, Jinsong Li, Yuhang Zang, Xiaobao Wu 외

Despite the strong performance of ColPali/ColQwen2 in Visualized Document Retrieval (VDR), it encodes each page into multiple patch-level embeddings and leads to excessive memory usage. This empirical study investigates …

RetrievalToken Reduction

SiLVR: A Simple Language-based Video Reasoning Framework

2025-05-30 · Ce Zhang, Yan-Bo Lin, Ziyang Wang, Mohit Bansal 외

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilit…

MathMMEMMLUToken Reduction+2

One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory

2025-05-29 · Chenhao Zheng, Jieyu Zhang, Mohammadreza Salehi, Ziqi Gao 외

Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens and computational inefficiencies. The best…

Contrastive LearningText RetrievalToken ReductionVideo-Text Retrieval+1

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models

2025-05-28 · Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu 외

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer…

Language ModelingLanguage ModellingToken Reduction

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

2025-05-26 · Jintao Tong, Wenwei Jin, Pengda Qin, Anqi Li 외

Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically rely on single-layer attention scores to …

Token Reduction

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

2025-05-25 · Weize Chen, Jiarui Yuan, Tailin Jin, Ning Ding 외

Recent large language models (LLMs) exhibit impressive reasoning but often over-think, generating excessively long responses that hinder efficiency. We introduce DIET ( DIfficulty-AwarE Training), a framework that system…

Reinforcement Learning (RL)Token Reduction

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

2025-05-23 · Zhenglun Kong, Yize Li, Fanhu Zeng, Lei Xin 외

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel atten…

In-Context LearningToken Reduction

Not All Tokens Are What You Need In Thinking

2025-05-23 · Hang Yuan, Bin Yu, Haotian Li, Shijun Yang 외

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption,…

AllToken Reduction

Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning

2025-05-22 · Junhong Lin, Xinyue Zeng, Jie Zhu, Song Wang 외

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, wh…

Language ModelingLanguage ModellingLarge Language ModelScheduling+1

CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

2025-05-22 · Shilin Yan, Jiaming Han, Joey Tsai, Hongwei Xue 외

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, parti…

Token Reduction

Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM

2025-05-21 · Penghao Wu, Lewei Lu, Ziwei Liu

Large multimodal models excel in multimodal tasks but face significant computational challenges due to excessive computation on visual tokens. Unlike token reduction methods that focus on token-level redundancy, we ident…

DecoderToken Reduction

DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models

2025-05-20 · YuXuan Jiang, Dawei Li, Frank Ferraro

While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively verbose reasoning traces, resulting in su…

GSM8KMathematical ReasoningToken ReductionTransfer Learning

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference

2025-05-18 · Yichen Guo, Hanze Li, Zonghao Zhang, Jinhao You 외

Although large vision-language models (LVLMs) leverage rich visual token representations to achieve strong performance on multimodal tasks, these tokens also introduce significant computational overhead during inference.…

Token Reduction

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration

2025-05-16 · CVPR 2025 1 · Haipeng Fang, Sheng Tang, Juan Cao, Enshuo Zhang 외

Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens hav…

DenoisingToken Reduction

EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation

2025-05-16 · Ruobing Yao, Yifei Zhang, Shuang Song, Neng Gao 외

Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-spe…

DiversityRAGRetrievalRetrieval-augmented Generation+2

Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method

2025-05-12 · Chris Forrester, Octavia Sulea

Compute optimization using token reduction of LLM prompts is an emerging task in the fields of NLP and next generation, agentic AI. In this white paper, we introduce a novel (patent pending) text representation scheme an…

Semantic CompressionSemantic SimilaritySemantic Textual SimilarityText Compression+1

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs

2025-04-23 · Zhenhailong Wang, Senthil Purushwalkam, Caiming Xiong, Silvio Savarese 외

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components…

Token ReductionVideo Understanding
1–20 / 78 다음 →