cs.AINov 19, 2026

MambaLIFT: Reference-Based Mechanism-Aware Attribution for VMamba

Authors: Jintu Kakati, Niladri B. Puhan

Organizations: School of Electrical and Computer Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar 752050, India

Abstract

Attributing predictions of visual state-space models remains challenging because input-dependent selective dynamics couple feature selection, recurrent state propagation, and shared computational pathways. We introduce MambaLIFT, a reference-based, multiplier-first attribution framework for VMamba that propagates contributions through its computational graph using interaction-aware rules for selective-scan injection, recurrent memory, LayerNorm, and shared pathways. MambaLIFT decomposes the reference-relative class-logit difference, fc(x)−fc(x0)f_c(x)-f_c(x^0), by spatial position, VSS block, scan direction, and computational mechanism. Experiments on ImageNet-1K evaluate VMamba-T and VMamba-B, with hyperparameters selected on a calibration set and faithfulness assessed on a disjoint held-out evaluation set. MambaLIFT achieves numerical conservation to floating-point precision across audited attribution interfaces in both configurations. Under mean-colour pixel flipping, it achieves significantly higher mean faithfulness scores than MambaLRP on both configurations and the highest scores among the evaluated methods, including Integrated Gradients with matched references. Under blurred replacement, MambaLIFT is non-inferior to MambaLRP on VMamba-T and equivalent on VMamba-B, indicating that its advantage depends on the replacement protocol. Ablations on VMamba-T show that interaction allocation, temporal propagation, and pathway composition affect attribution maps. Mechanism-level analyses further show that exact relevance conservation does not imply additive effects under finite interventions: the mechanism decomposition accounts for the reference-relative logit difference but does not estimate intervention effects or establish causal validity.

Figures & tables

Explore similar work

Nov 14, 2026

Size-Matched Nulls Reveal What Block Ablation Measures in MambaVision

Hybrid vision backbones interleave Mamba state-space mixers with self-attention, and a block's role is usually probed by removing it and measuring the damage. We test what that measurement means in MambaVision. On all 50,000 ImageNet validation images and three model sizes, every block ablation is paired with a size-matched null, the same perturbation with its channels shuffled or their signs flipped. In top-1 accuracy and in true-class rank, real and null damage are nearly indistinguishable in absolute terms: pooled over the blocks of MambaVision-T, the content effect lies within [-0.044,+0.016] percentage points (90% interval). Two attention-only controls show that the test detects content, with real ablations worse than their nulls by up to 4.2 points in DeiT-Small and 1.0 point in Swin-T. Part of MambaVision's near-equivalence reflects how little damage its blocks do (0.11--0.34 points on average, against 1.7 and 2.1). Scaled by damage, its content share is comparable to Swin-T's in accuracy, lower in rank, and far below DeiT-Small's: single-block damage in MambaVision is small and mostly positional. Ablation also hides what blocks carry together: removing all blocks of one type compounds damage to 3.7--8.4 times the sum of single effects, far more than size-matched nulls, including nulls that keep the alignment between the blocks' perturbations; for adjacent pairs, aligned nulls reproduce most of it. Freezing input-dependent selection in all Mamba mixers shows that it accounts for 20--32% of the Mamba contribution, mainly through the B and C projections. We turn these results into a protocol for causal attribution in hybrid networks.
Jul 7, 2026

A Good Initialization is All You Need for Faithful Visual Attribution

Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by masking regions and measuring score changes, but they usually output a complete ordering of all regions. Many applications, especially MLLM attribution and repair, only need a compact top-kk evidence mask. We study this mask-first attribution problem. An exactly kk-region mask is combinatorial: useful evidence can depend on interactions among fine regions. Coarse grouping can stabilize early search but aggregates redundant content, whereas one-step scoring can miss high-value combinations. We introduce two forward-only methods. CoPAIR uses a PhaseWin--Greedy gap diagnosis to construct coarse singleton/pair candidates that warm-start full-ordering search. TRACE directly searches fixed-cardinality fine-region masks with cross-entropy sampling, elite retention, and distribution updates, with a finite-budget recovery analysis. The resulting evidence set can be returned as a compact attribution mask or used to initialize Greedy or PhaseWin when a complete ranking is required. Across ImageNet classification with CLIP ViT-L/14, CLIP RN101, and ResNet-101, our initialized search methods establish a new state-of-the-art frontier for faithful full-ordering attribution under inclusive forward-call accounting. On POPE and RePOPE with Qwen2.5-VL-3B-Instruct and LLaVA-v1.5-7B, TRACE+Greedy gives the strongest search-based MLLM attribution results. Direct TRACE masks further achieve single-point RePOPE repair rates of 94.44%94.44\% and 96.00%96.00\%, showing that compact evidence masks can be actionable attribution outputs, not merely prefixes of full rankings.
Oct 9, 2026

READ: Reading the Selective Scan for Faithful Video Attribution

Selective state-space models are an efficient approach to long-sequence video modeling. However, their recurrent computation makes it difficult to determine which video tokens drive a prediction. Existing attribution methods often require additional backward passes or repeated model evaluations, making them substantially more expensive than the forward inference they aim to explain. In this work, we introduce READ, a parameter-free attribution method for selective state-space models that unrolls the recurrence at the position read by the classifier. READ traces the contribution accumulated in the recurrent state back to the video tokens that contribute to the final prediction. By anchoring attribution at the classifier's readout, it produces a single spatiotemporal relevance map from which frame- and region-level relevance can be obtained directly. Despite requiring only one forward pass, READ achieves competitive faithfulness and localisation compared with substantially more expensive attribution methods. Experimental results show that READ avoids the systematic relevance biases of existing methods while recovering meaningful temporal and class-specific structure across datasets and backbones. More broadly, our results show that the recurrence underlying selective state-space models is not only an efficient mechanism for inference, but also a direct source of interpretable evidence for their predictions.