Papers Token Reduction
“Token Reduction” 태그가 달린 논문 78편 · 필터 해제
Learning Compact Vision Tokens for Efficient Large Multimodal Models
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 ReductionToken Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
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 ReductionAstraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
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 GenerationTowards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
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 ReductionSiLVR: A Simple Language-based Video Reasoning Framework
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+2One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
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+1VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
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 ReductionFlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
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 ReductionThe Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
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 ReductionToken Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality
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 ReductionNot All Tokens Are What You Need In Thinking
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 ReductionPlan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning
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+1CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms
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 ReductionStreamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM
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 ReductionDRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
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 LearningSTAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
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 ReductionAttend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
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 ReductionEcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
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+2Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method
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+1DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
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