Image de couverture de livre

Concept-Guided Interpretability via Neural Chunking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Shuchen, Alaniz, Stephan, Karthik, Shyamgopal, Dayan, Peter, Schulz, Eric, Akata, Zeynep
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Discovering Chunks in Neural Embeddings for Interpretability
par: Wu, Shuchen, et autres
Publié: (2025)

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
par: Bader, Jessica, et autres
Publié: (2025)

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
par: Pach, Mateusz, et autres
Publié: (2025)

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
par: Singhi, Nishad, et autres
Publié: (2024)

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
par: Kim, Sanghwan, et autres
Publié: (2024)

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
par: Eyring, Luca, et autres
Publié: (2025)

Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences
par: Wu, Shuchen, et autres
Publié: (2024)

From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
par: Wu, Boyong, et autres
Publié: (2026)

DataDream: Few-shot Guided Dataset Generation
par: Kim, Jae Myung, et autres
Publié: (2024)

FINER: MLLMs Hallucinate under Fine-grained Negative Queries
par: Xiao, Rui, et autres
Publié: (2026)

FLAIR: VLM with Fine-grained Language-informed Image Representations
par: Xiao, Rui, et autres
Publié: (2024)

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
par: Eyring, Luca, et autres
Publié: (2023)

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
par: Roschmann, Simon, et autres
Publié: (2025)

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
par: Pach, Mateusz, et autres
Publié: (2026)

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
par: Bader, Jessica, et autres
Publié: (2025)

Post-hoc Probabilistic Vision-Language Models
par: Baumann, Anton, et autres
Publié: (2024)

Vision-by-Language for Training-Free Compositional Image Retrieval
par: Karthik, Shyamgopal, et autres
Publié: (2023)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
par: Lin, Shen, et autres
Publié: (2026)

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
par: Girrbach, Leander, et autres
Publié: (2025)

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
par: Hummel, Thomas, et autres
Publié: (2024)

Explaining CLIP Zero-shot Predictions Through Concepts
par: Ozdemir, Onat, et autres
Publié: (2026)

Sparse Autoencoders are Topic Models
par: Girrbach, Leander, et autres
Publié: (2025)

Simplifying Knowledge Transfer in Pretrained Models
par: Jain, Siddharth, et autres
Publié: (2025)

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
par: Eyring, Luca, et autres
Publié: (2024)

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
par: Haridas, Akash, et autres
Publié: (2026)

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
par: Xu, Xinyue, et autres
Publié: (2024)

Process-Guided Concept Bottleneck Model
par: Asiyabi, Reza M., et autres
Publié: (2026)

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
par: Parekh, Jayneel, et autres
Publié: (2024)

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
par: Chorna, Sofiia, et autres
Publié: (2025)

Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
par: Doumanoglou, Alexandros, et autres
Publié: (2023)

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
par: Agrawal, Susmit, et autres
Publié: (2025)

Unlearning-based Neural Interpretations
par: Choi, Ching Lam, et autres
Publié: (2024)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
par: Jun, Youngjun, et autres
Publié: (2026)

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
par: Kalibhat, Neha, et autres
Publié: (2026)

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
par: Rao, Sukrut, et autres
Publié: (2024)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
par: Chavhan, Ruchika, et autres
Publié: (2024)

VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking
par: Yang, Kichang, et autres
Publié: (2025)

Does a Neural Network Really Encode Symbolic Concepts?
par: Li, Mingjie, et autres
Publié: (2023)

Building Optimal Neural Architectures using Interpretable Knowledge
par: Mills, Keith G., et autres
Publié: (2024)

Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
par: Opsahl, Tobias A., et autres
Publié: (2024)