Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions

• URL: http://arxiv.org/abs/2608.06174v1
• Date: Thu, 06 Aug 2026 15:38:55 GMT
• Title: Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions
• Abstract summary: We introduce an injectively aligned leave-one-cell-out protocol over support x operation grids and SO-OPF.<n>We separate two questions that aggregate scores conflate: whether the carrier composes held-out bindings when the grid is known, and whether that grid can be recovered from flat cell labels.
• Score: 87.95757610455173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compositional analysis of frozen vision encoders should determine both what changed and where it changed. Standard factor probes score these axes separately, however, and can reward multiple operations that reuse the same predicted slot. We call this failure operation laundering. We introduce an injectively aligned leave-one-cell-out protocol over support x operation grids and SO-OPF, a readout that factors cell energy into support salience and a competitive operation posterior. This formulation separates two questions that aggregate scores conflate: whether the carrier composes held-out bindings when the grid is known, and whether that grid can be recovered from flat cell labels. With frozen DINOv3 features, known factorial assignment reaches 0.874 injective accuracy on Shapes3D-Extended and 0.799 on globally image-disjoint COCO; learning the assignment from flat labels reaches 0.769 and 0.762, respectively. Under matched-axis-aware supervision on Shapes3D, the factored carrier improves learned-assignment accuracy from 0.653 to 0.841 over a dense carrier and eliminates its laundering gap. SigLIP2 replicates the COCO separation. A rebuilt MuJoCo substrate exposes a boundary: learned-assignment accuracy is 0.569 with DINOv3 and 0.484 with SigLIP2, with substantial slot collapse. Thus factored readout and injective evaluation recover held-out bindings on two substrates while exposing, rather than hiding, a renderer-specific failure boundary; they do not establish universal recovery from flat labels.

Related papers

• Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings [0.0]
  We show that balanced k-shot sampling induces an exact, provable degeneracy in a family of small-sample discriminant estimators.<n>We then evaluate the Kernelgression repaired framework on few-shot text classification on frozen embeddings.
  arXiv  Detail & Related papers  (2026-09-09T08:13:54Z)
• When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models [0.0]
  A language model, asked to verify 1,200 logical conclusions, answers YES every time.<n>linear probes on its hidden states read the correct verdict at 0.96 AUC.<n>We ask where the verdict is lost, and find the dominant failure is a single scalar.<n>The diagnosis generalizes: across 90 semantic-label configurations of a five-model, three-family factorial, behavioral accuracy collapses onto a single function of threshold offset.
  arXiv  Detail & Related papers  (2026-09-04T00:26:45Z)
• Forgetful Attention: A Trainable Support-Vector Memory with Certified Selection and Exact Unlearning [0.16921396880325776]
  We introduce Support Vector Attention (SV-Attention), a memory whose weights are support coefficients of a one-class Sfp with fixed box parameter C.<n>Its active-set partition gives reserve tokens exactly zero weight, output weights; a incremental incremental solver token to recover the state produced by retraining without it under the same C.<n>We also demonstrate surgical eviction, exact editing, patient-record deletion, and a forgettable retrieval memory over real sentence embeddings.
  arXiv  Detail & Related papers  (2026-07-13T23:13:57Z)
• Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance [0.6768558752130311]
  We analyze Diffusion-free guidance (CFG) through an integrator-analysis lens.<n>We show that guidance re-stiffens exactly the discriminative subspace to an anomalous 1+w.<n> DDIM is no longer fitted there, and on coarse meshes its guided residual diverges as sigma_min goes zero.
  arXiv  Detail & Related papers  (2026-07-08T17:21:51Z)
• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits [47.668752416295185]
  Conditional Co-Ablation asks how much each remaining unit's ablation effect grows once a primary set has been removed.<n>On the GPT-2-small IOI circuit, CoAx raises backup-head recovery from 0.33 to 0.91 ROC-AUC.
  arXiv  Detail & Related papers  (2026-07-02T09:32:57Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models [0.0]
  We study whether a frozen foundation model represents one sample coherently across its semantic subregions.<n>We introduce Dimensional Coactivation (DCA), a per-dimension instrument for measuring this coherence.<n>DCA depends on a stable per-dimension coordinate system, not on region extraction alone.
  arXiv  Detail & Related papers  (2026-05-07T15:32:47Z)
• Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation [0.05597620745943382]
  Zero-shot vision-language models (VLMs) offer a promptable alternative to task-specific training for gross tumor volume delineation.<n>We study alignment directions in VoxTell on a held-out internal NSCLC tumor dataset.<n> Alignment analyses revealed that anatomical location is the dominant driver of VoxTell's spatial attention.
  arXiv  Detail & Related papers  (2026-05-02T05:49:32Z)
• Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B [0.0]
  Small instruct-tuned LLMs produce degenerate verbal confidence under minimal elicitation.<n>We test whether confidence-conditioned supervised fine-tuning with self-consistency-derived targets can close the gap between internal information and verbal readout.
  arXiv  Detail & Related papers  (2026-04-27T05:53:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.