REVIEW 10 cited by
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
read the original abstract
The visual projector, which bridges the vision and language modalities and facilitates cross-modal alignment, serves as a crucial component in MLLMs. However, measuring the effectiveness of projectors in vision-language alignment remains under-explored, which currently can only be inferred from the performance of MLLMs on downstream tasks. Motivated by the problem, this study examines the projector module by interpreting the vision-language semantic flow within MLLMs. Specifically, we trace back the semantic relevance flow from generated language tokens to raw visual encoder patches and the intermediate outputs produced by projectors. Our findings reveal that compressive projectors (e.g., QFormer), abstract visual patches into a limited set of semantic concepts, such as objects or attributes, resulting in a 'double abstraction' phenomenon. This involves a first visual semantic abstraction by the projector referring to pre-defined query tokens, and a second extraction by the LLM based on text instructions. The double abstraction is inefficient in training and will result in cumulative vision semantics deficiency. To mitigate this issue, we propose the key insight of 'Decouple Compression from Abstraction (DeCo), that is compressing the visual token number at the patch level by projectors and allowing the LLM to handle visual semantic abstraction entirely. Consequently, we adopt a simple compressor, i.e., 2D Adaptive Pooling, to downsample visual patches in a parameter-free manner. Empirical evaluation demonstrates that DeCo surpasses traditional compressive projectors regarding both performance and efficiency. It achieves performance gains of 0.9%, 7.1%, and 2.9% across the MLLM Benchmarks, Visual Localization, and Open-ended VQA tasks with fewer trainable parameters and faster convergence speed.
Forward citations
Cited by 10 Pith papers
-
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
EgoSAT is the first benchmark unifying retrospective, online, and prospective reasoning tasks in egocentric streaming video to evaluate VLMs, revealing struggles with temporal modeling and mis-calibration.
-
Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temp...
-
DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
DocPrune is a training-free token pruning method that removes background and irrelevant tokens from document images using question and comprehension signals, yielding 3x encoder and 3.3x decoder throughput gains plus ...
-
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
CRISP unifies model compression and parameter-efficient fine-tuning by decomposing weights into shared bases and small mixers, reporting 1-5% gains over prior dual-task and specialized methods.
-
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
-
Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
DeSAP uses decoupled cross-modal similarity plus visual saliency to prune visual tokens in LVLMs, retaining 11.1% tokens for 10x FLOPs reduction and 98.1% performance on LLaVA-1.5-7B.
-
Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion
UniCodec uses LLM-driven semantic disentanglement at the encoder and diffusion-based compositional generation at the decoder to enable one codec for both human perception and machine vision tasks without task-specific...
-
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
SparseVLM uses text-guided attention to prune and recycle visual tokens in VLMs, delivering 54% FLOPs reduction and 37% lower latency with 97% accuracy retention on LLaVA.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Efficient3D prunes visual tokens in 3D MLLMs via DVTIE and ATR modules, reporting better performance than unpruned baselines on Scan2Cap and other benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.