Cover Image

Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stevens, Samuel, Beattie, Jacob, Berger-Wolf, Tanya, Su, Yu
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interpretable and Testable Vision Features via Sparse Autoencoders
by: Stevens, Samuel, et al.
Published: (2025)

BioBench: A Blueprint to Move Beyond ImageNet for Scientific ML Benchmarks
by: Stevens, Samuel
Published: (2025)

Leveraging Latent Visual Reasoning in Silence
by: Zhu, Dongyao, et al.
Published: (2026)

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
by: Liu, Ye, et al.
Published: (2024)

Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
by: Zhang, Ziheng, et al.
Published: (2025)

Open-Det: An Efficient Learning Framework for Open-Ended Detection
by: Cao, Guiping, et al.
Published: (2025)

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
by: Zhang, Zhixiong, et al.
Published: (2026)

Generative Region-Language Pretraining for Open-Ended Object Detection
by: Lin, Chuang, et al.
Published: (2024)

Tracking Phenological Status and Ecological Interactions in a Hawaiian Cloud Forest Understory using Low-Cost Camera Traps and Visual Foundation Models
by: Meyers, Luke, et al.
Published: (2026)

Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation
by: Zhao, Zhonghan, et al.
Published: (2024)

Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels
by: Liang, Tianming, et al.
Published: (2024)

MediX-R1: Open Ended Medical Reinforcement Learning
by: Mullappilly, Sahal Shaji, et al.
Published: (2026)

OpenREAD: Reinforced Open-Ended Reasoning for End-to-End Autonomous Driving with LLM-as-Critic
by: Zhang, Songyan, et al.
Published: (2025)

OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes
by: Kurkova, Regina, et al.
Published: (2026)

AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding
by: Xu, Weili, et al.
Published: (2025)

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
by: Rajan, Anirudh Sundara, et al.
Published: (2026)

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
by: Lin, Zhiwei, et al.
Published: (2024)

SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detection
by: Nanaumi, Tomoyasu, et al.
Published: (2026)

LyTimeT: Towards Robust and Interpretable State-Variable Discovery
by: Yu, Kuai, et al.
Published: (2025)

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities
by: Ghosh, Adhiraj, et al.
Published: (2024)

SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
by: Park, Sangha, et al.
Published: (2025)

MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark
by: Shaar, Shaden, et al.
Published: (2026)

Towards Open-ended Visual Quality Comparison
by: Wu, Haoning, et al.
Published: (2024)

BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models
by: Zhang, Ziheng, et al.
Published: (2025)

Sparse Autoencoders are Topic Models
by: Girrbach, Leander, et al.
Published: (2025)

Automatic Discovery of Visual Circuits
by: Rajaram, Achyuta, et al.
Published: (2024)

MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI
by: Yao, Huanjin, et al.
Published: (2025)

PitVQA++: Vector Matrix-Low-Rank Adaptation for Open-Ended Visual Question Answering in Pituitary Surgery
by: He, Runlong, et al.
Published: (2025)

DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery
by: Mall, Utkarsh, et al.
Published: (2025)

Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
by: Ro, Yusung, et al.
Published: (2026)

Interpretability Transfer from Language to Vision via Sparse Autoencoders
by: Kravets, Alexey, et al.
Published: (2026)

Visual Variational Autoencoder Prompt Tuning
by: Xiao, Xi, et al.
Published: (2025)

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
by: Li, Haodong, et al.
Published: (2026)

Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset
by: Huang, Wenhui, et al.
Published: (2026)

HotSpotter - Patterned Species Instance Recognition
by: Crall, Jonathan P., et al.
Published: (2025)

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites
by: Lei, Zhenxin, et al.
Published: (2025)

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
by: Zhang, Kai, et al.
Published: (2024)

SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarios
by: Cheng, Ning, et al.
Published: (2025)

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
by: Nakka, Krishna Kanth
Published: (2025)

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
by: Morelli, Fabian, et al.
Published: (2026)