Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
Look-m: Look-once optimization in kv cache for efficient multimodal long-context inference
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Attention sinks arise from variance discrepancy in self-attention value aggregation, amplified by super neurons and first-token dimension disparity, and can be mitigated by head-wise RMSNorm to accelerate pre-training convergence.
Geo3DPruner uses geometry-aware global attention and two-stage voxel pruning to remove 90% of visual tokens from spatial videos while keeping over 90% of original performance on 3D scene benchmarks.
A structure-aware sequential compression of KV cache during prefill reduces peak memory usage in MLLMs while keeping generative performance nearly intact.
RetentiveKV uses entropy to drive state-space model transitions that retain and reactivate low-attention visual tokens in a continuous memory instead of pruning them, delivering 5x KV cache compression and 1.5x faster decoding.
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
Attention sinks emerge in language models from softmax-induced token dependence on attention scores and do not appear when using sigmoid attention without normalization in models up to 1B parameters.
VisionPulse is a step-wise visual token pruning method for LMMs that retains 5% of tokens per step, shortens reasoning traces by 11.2%, and maintains accuracy.
KVCapsule compresses KV cache in VLMs by 60% to deliver up to 2x higher tokens-per-second and 2.4x memory reduction with negligible accuracy loss.
citing papers explorer
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
-
The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity
Attention sinks arise from variance discrepancy in self-attention value aggregation, amplified by super neurons and first-token dimension disparity, and can be mitigated by head-wise RMSNorm to accelerate pre-training convergence.
-
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
Geo3DPruner uses geometry-aware global attention and two-stage voxel pruning to remove 90% of visual tokens from spatial videos while keeping over 90% of original performance on 3D scene benchmarks.
-
Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines
A structure-aware sequential compression of KV cache during prefill reduces peak memory usage in MLLMs while keeping generative performance nearly intact.
-
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
RetentiveKV uses entropy to drive state-space model transitions that retain and reactivate low-attention visual tokens in a continuous memory instead of pruning them, delivering 5x KV cache compression and 1.5x faster decoding.
-
POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs
POINTS-Long is a dual-mode multimodal large language model that uses dynamic visual token scaling to retain 97.7-99.7% accuracy on long-form tasks with 1/40 to 1/10th the tokens and supports streaming via detachable KV-cache.
-
When Attention Sink Emerges in Language Models: An Empirical View
Attention sinks emerge in language models from softmax-induced token dependence on attention scores and do not appear when using sigmoid attention without normalization in models up to 1B parameters.
-
VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
VisionPulse is a step-wise visual token pruning method for LMMs that retains 5% of tokens per step, shortens reasoning traces by 11.2%, and maintains accuracy.
-
KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
KVCapsule compresses KV cache in VLMs by 60% to deliver up to 2x higher tokens-per-second and 2.4x memory reduction with negligible accuracy loss.