INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
INSHAPE is a new interpretable time-series classification framework that discovers variable-length discriminative temporal patterns specific to individual instances rather than across the full dataset population. It models temporal dependencies among non-overlapping segments and bridges local and global interpretability via a bottom-up aggregation into prototypical shapelets. Evaluated on 128 UCR and 30 UEA benchmark datasets, INSHAPE outperforms state-of-the-art shapelet-based methods while offering more intuitive instance-level explanations.
Related guides (1)
Related events (8)
Multivariate Probabilistic Time Series Forecasting with Informer
A Hugging Face blog post introduces the Informer model for multivariate probabilistic time series forecasting. The post covers the architecture and usage of Informer, which uses a sparse attention mechanism (ProbSparse) to handle long sequences more efficiently than standard Transformers. It demonstrates how to use the model via the Hugging Face Transformers library for forecasting tasks.
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
AREA is a new method for CLIP-based Class-Incremental Learning (CIL) that decomposes the classification process into attribute extraction and aggregation stages to combat catastrophic forgetting. Extraction is stabilized by anchoring visual and textual attributes on a hyperspherical embedding space via principal geodesic analysis, while aggregation uses lightweight task-specific experts regularized by a variational information bottleneck. Inference employs optimal transport routing over task attribute manifolds. The method is reported to consistently outperform state-of-the-art CIL approaches and is accepted at ICML 2026.
SPEX and ProxySPEX: Scalable Interaction Discovery for LLM Interpretability
Researchers from BAIR introduce SPEX (Spectral Explainer) and ProxySPEX, algorithms for identifying influential feature, data, and model-component interactions in LLMs at scale. The approach exploits sparsity, low-degreeness, and hierarchy properties to reframe interaction discovery as a sparse recovery problem using tools from signal processing and coding theory. ProxySPEX achieves comparable performance to SPEX with roughly 10x fewer ablations by leveraging hierarchical structure. The methods are evaluated on feature attribution (sentiment analysis), data attribution, and mechanistic interpretability tasks, outperforming marginal methods like LIME at long context lengths.
Interpretability-based pipeline for auditing and shaping post-training learning signals
Researchers introduce a data-centric post-training pipeline that applies interpretability methods to preference datasets before optimization, surfacing latent concepts that separate preferred from dispreferred generations. The approach unifies several interpretability-based training protocols as feature or data interventions that shape reward signals. Empirically, the pipeline diagnoses undesirable signals such as sycophancy and over-stylization, mitigates off-target learning, and can amplify desired properties like safety behaviors and model personality. The work reframes post-training from opaque scalar reward optimization into an auditable, concept-level sculpting process.
Pose-ICL: 3D-aware in-context learning for pose-controllable image generation of custom subjects
Researchers introduce Pose-ICL, a tuning-free framework for generating images of user-specified subjects with accurate pose control. The method uses Surface-Anchored Position Embedding (SAPE) to give 2D diffusion models explicit 3D awareness by anchoring image tokens to volumetric bounding box surface coordinates. Evaluations on 3D assets and real-world subjects show improvements over existing methods in both pose accuracy and identity consistency. The framework is designed for compatibility with existing Diffusion Transformer (DiT) models.
Internal Oppenheim-Lim test reveals phase/sign identity codes shared across image classifier architectures
A new arXiv preprint applies a causal intervention inspired by Oppenheim and Lim (1981) to probe whether trained image classifiers encode identity in Fourier phase rather than magnitude within their hidden layers. By transplanting phase or sign components between images at chosen layers in PRISM2D, GFNet, ViT-B/16, and ResNet-50, the authors find that predictions follow the phase/sign donor across all tested architectures, with image-specific magnitude largely dispensable. ResNet-50 requires a pre-ReLU intervention to reveal a latent sign code, exposing how rectification and readout geometry shape the basis in which the code is expressed. The findings offer a mechanistic account of the texture–shape gap between CNNs and attention-based models.
SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit
Hugging Face introduces SetFitABSA, an extension of the SetFit few-shot learning framework for Aspect-Based Sentiment Analysis (ABSA). The approach enables fine-grained sentiment classification at the aspect level with minimal labeled data. This builds on SetFit's contrastive sentence-transformer training paradigm, adapting it to the structured ABSA task of identifying sentiment toward specific aspects within text.
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
IVGT is a new neural architecture that implicitly models continuous 3D geometry from unposed multi-view images without requiring explicit pointmap regression. It learns a continuous neural scene representation in a canonical coordinate system, supporting SDF-based surface queries and color prediction via lightweight decoders. The model is trained with multi-dataset joint optimization using 2D supervision and 3D geometric regularization, achieving strong generalization across mesh reconstruction, novel view synthesis, depth/normal estimation, and camera pose estimation tasks.