REVIEW 6 cited by
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
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
read the original abstract
Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with token pruning, which identifies the redundant tokens in MLLMs and then prunes them to reduce the computation and KV storage costs, leading to significant acceleration without training. While these methods claim efficiency gains, critical questions about their fundamental design and evaluation remain unanswered: Why do many existing approaches underperform even compared to naive random token selection? Are attention-based scoring sufficient for reliably identifying redundant tokens? Is language information really helpful during token pruning? What makes a good trade-off between token importance and duplication? Are current evaluation protocols comprehensive and unbiased? The ignorance of previous research on these problems hinders the long-term development of token pruning. In this paper, we answer these questions one by one, providing insights into the design of future token pruning methods.
Forward citations
Cited by 6 Pith papers
-
ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression
ORCA compresses 3D CT tokens into organ-guided connected regions with sinusoidal centroid encoding, outperforming grid average and other compressors at matched budgets.
-
C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs
C-PTQ weights quantization error by per-channel Fisher information of the task loss, improving low-bit accuracy of multimodal LLMs by small margins over existing channel-wise scaling methods.
-
EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent
EgoPrune prunes egomotion video tokens by homography-based frame alignment and MMR selection, keeping accuracy close to the full-token baseline while reducing compute.
-
GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models
A training-free token pruning method that combines cosine-similarity saliency with greedy redundancy removal to preserve accuracy at high compression ratios.
-
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
CDPruner prunes visual tokens in MLLMs by maximizing instruction-conditioned diversity via a determinantal point process, preserving accuracy at high reduction ratios.
-
Towards General Continuous Memory for Vision-Language Models
A vision-language model can act as its own continuous memory encoder, compressing external multimodal knowledge into eight embeddings that improve reasoning when prepended to the frozen model.
Discussion (0). Sign in to comment.