As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model performance. Existing methods often measure diversity directly in the original embedding space, where geometric metrics entangle dominant semantic directions, fine-grained supervision differences, and local noise. We address this limitation by formulating data selection as a coarse-to-fine hierarchical coverage problem and propose MASS. MASS learns low-dimensional principal manifold coordinates with a dense autoencoder for coarse semantic grouping, and then performs quality-aware sparse feature coverage within each group using a TopK sparse autoencoder. Experiments on Vision Flan and LLaVA-CoT show that MASS consistently outperforms strong data selection baselines across multiple budgets, and in several settings matches or surpasses full data training with only a small subset of data.
Few-shot segmentation (FSS) commonly assumes clean pixel-level support masks, yet practical support supervision often uses boxes, scribbles, coarse masks, or pseudo-masks. These weak annotations may include texture-similar distractors and background context alongside the target, contaminating class prototypes or visual prompts before query prediction. We introduce SADe, a predictor-agnostic support decontamination layer that estimates the reliability of selected support patches without query information. Central to SADe is sparse autoencoder (SAE) atom evidence: dense similarity may respond to both target and texture-similar context, whereas contrasting atom activations inside and outside the weak-support region provides factor-level reliability cues. A lightweight router combines atom evidence with dense similarity and episode statistics to predict patch reliability and generate a cleaned support mask. Trained once on synthetic weak-support episodes from FSS-1000, the router is frozen for all target evaluations. The resulting mask supports standalone prediction or can be supplied to heterogeneous FSS models through native support interfaces without altering query-side inference. Under a matched weak-support protocol, SADe achieves the highest query mIoU in six of nine standalone prompt-shot combinations. With the same ProMi query head, it is within 0.03 mIoU of SAM3-derived masks under tight boxes and surpasses them by 11.17 and 19.49 points under box-r2 and box-r4, respectively. As a plug-in, SADe improves over raw support in 70 of 72 matched box-family comparisons across four frozen downstream models and two datasets. On point and scribble prompts, its average performance remains close to the corresponding raw-support baseline. Ablations and atom-removal controls show that atom evidence contributes reliability information beyond dense similarity.
Héctor Laria, Yiping Han, Julian D. Santamaria +4cs.CV
Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse autoencoder analysis and zero-shot classification, we demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface: when damage is severe enough for FID and KID to respond, the model is already nearly unusable; when the model remains functional, FID and KID stay flat while specific classes silently suffer worst-case zero-shot accuracy drops of up to 18.9 points and concept-level distributions shift dramatically. This pattern appears at both ends of the adaptation spectrum (concept customization and concept unlearning), suggesting it is a systematic consequence of weight-level modification rather than an artifact of any particular method. To surface this hidden drift before deployment, we introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them. DriftScope optimizes a soft prompt to attribute drift at the token level without requiring access to real data or model internals. The result is an interpretable, concept-level audit that aggregate evaluation cannot provide.
Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and interpretability question: when a foundation-style model can reproduce known continuum dynamics, what internal mechanism supports that behavior, is the internal behaviour consistent with known physics, and how does it relate to where the emulator succeeds or fails? We investigate a cross-domain foundation model for continuum dynamics, Walrus by Polymathic, using mechanistic interpretability guided by physical principles. We apply a sparse autoencoder (SAE) to probe a selected layer, and address the practical challenge of triaging a large feature set (over 20,000) using enstrophy as a physically grounded metric. As a deliberately simple testbed, we focus on shear flow and compare feature recruitment across multiple shear-flow setups, i.e. parameter values in the numerical simulation. Across setups we find evidence of piecewise consistency, with subsets of features recurring in similar roles, but this structure is intermittent and does not map cleanly onto standard physical decompositions. In parallel, direct comparisons between numerical simulation and the emulator reveal systematic output-level discrepancies, including regimes where energy/structures become too diffuse or too localized. We connect parts of these discrepancies to changes in specific SAE feature usage. Our work highlights open questions for scientific foundation models: how to robustly prioritize mechanistically meaningful features, how to separate stable structure from analysis artifacts (including single-layer and SAE limitations), and how to use established benchmarks to decide when "different" internal representations are genuinely informative rather than merely effective.
Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K. We show that sparse autoencoder (SAE) feature extraction resolves this: K=2 becomes optimal for 12/14 categories on Qwen3.5-9B, achieving 96-99% accuracy per category on our BeaverTails classification benchmark, largely eliminating the need for exhaustive sweeps (K=4-25 with random initialization). This convergence to two planes is consistent with the Linear Representation Hypothesis, providing suggestive evidence that safety boundaries in this setting admit a low-dimensional linear description in the SAE feature space. Building on this geometric perspective, we introduce a cone constraint whose learnable aperture adapts to each category's cluster concentration, stabilized by a three-phase training
We propose a five-stage methodology for causal feature analysis in transformer language models (probe design, feature extraction, causal validation, robustness testing, and deployment integration) and demonstrate it end-to-end on GPT-2 small performing the Indirect Object Identification (IOI) task. Activation patching recovers the canonical IOI circuit (layer-9 head 9 alone gives recovery +1.02). A sparse autoencoder recovers per-name selective features with effect sizes of 30 to 50 activation units. Causal validation finds these features specifically but only partially causal: ablating fifteen of them leaves the model accurate on 98% of prompts. Two NLA-inspired evaluations strengthen this picture: the fifteen selective features explain only 31% of activation variance versus the SAE's 99.7%, and selectivity ratio anticorrelates with causal force (r = -0.56). Robustness testing under three distribution shifts finds that the circuit transfers cleanly but feature ablation effects degrade substantially, exposing a gap between detection robustness and causal robustness. A cost-based deployment evaluation (assumed $50/FN, $0.42/FP, 2% error rate) finds an optimal monitor configuration yielding $8.96 per 1000 queries against a $1000 baseline, a 99.1% saving. Optimal composition strategy varies with cost ratio and base rate. The conjunction of stages produces findings no single stage would.