Copertina

VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lim, Hyesu, Choi, Jinho, Kim, Taekyung, Heo, Byeongho, Choo, Jaegul, Han, Dongyoon
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
di: Choi, Jinho, et al.
Pubblicazione: (2025)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
di: Oh, Changdae, et al.
Pubblicazione: (2023)

Morphing Tokens Draw Strong Masked Image Models
di: Kim, Taekyung, et al.
Pubblicazione: (2023)

Learning with Unmasked Tokens Drives Stronger Vision Learners
di: Kim, Taekyung, et al.
Pubblicazione: (2023)

Sparse autoencoders reveal selective remapping of visual concepts during adaptation
di: Lim, Hyesu, et al.
Pubblicazione: (2024)

Scratching Visual Transformer's Back with Uniform Attention
di: Hyeon-Woo, Nam, et al.
Pubblicazione: (2022)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
di: Kim, Donghu, et al.
Pubblicazione: (2024)

RL makes MLLMs see better than SFT
di: Song, Junha, et al.
Pubblicazione: (2025)

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
di: Song, Junha, et al.
Pubblicazione: (2026)

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
di: Hwang, Dongyoon, et al.
Pubblicazione: (2025)

Masking meets Supervision: A Strong Learning Alliance
di: Heo, Byeongho, et al.
Pubblicazione: (2023)

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
di: Lee, Jung Hyun, et al.
Pubblicazione: (2024)

EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
di: Kim, Jinhee, et al.
Pubblicazione: (2024)

When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection
di: Kim, Dongmin, et al.
Pubblicazione: (2023)

Do's and Don'ts: Learning Desirable Skills with Instruction Videos
di: Kim, Hyunseung, et al.
Pubblicazione: (2024)

Exploring Conditions for Diffusion models in Robotic Control
di: Shin, Heeseong, et al.
Pubblicazione: (2025)

Token Bottleneck: One Token to Remember Dynamics
di: Kim, Taekyung, et al.
Pubblicazione: (2025)

Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision
di: Kim, Jinhee, et al.
Pubblicazione: (2024)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
di: Kim, Donghyun, et al.
Pubblicazione: (2024)

Synthesizing Visual Concepts as Vision-Language Programs
di: Wüst, Antonia, et al.
Pubblicazione: (2025)

Self-Supervised Contrastive Learning for Long-term Forecasting
di: Park, Junwoo, et al.
Pubblicazione: (2024)

Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models
di: Park, Cheonbok, et al.
Pubblicazione: (2025)

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
di: Kim, Jeongho, et al.
Pubblicazione: (2024)

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
di: Jung, Kyudan, et al.
Pubblicazione: (2026)

Rotary Position Embedding for Vision Transformer
di: Heo, Byeongho, et al.
Pubblicazione: (2024)

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
di: Kim, Taesan, et al.
Pubblicazione: (2026)

Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
di: Kim, Taehee, et al.
Pubblicazione: (2026)

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
di: Dong, Xinpeng, et al.
Pubblicazione: (2026)

Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
di: Theodoridis, Nikos, et al.
Pubblicazione: (2026)

PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask
di: Kim, Jeongho, et al.
Pubblicazione: (2024)

Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering
di: Park, ChaeHun, et al.
Pubblicazione: (2024)

Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information
di: Cho, Hojun, et al.
Pubblicazione: (2025)

Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas
di: Choi, Nayoung, et al.
Pubblicazione: (2026)

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning
di: Lee, Hojoon, et al.
Pubblicazione: (2024)

Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual Distillation
di: Song, Sangmim, et al.
Pubblicazione: (2026)

Single Ground Truth Is Not Enough: Adding Flexibility to Aspect-Based Sentiment Analysis Evaluation
di: Yang, Soyoung, et al.
Pubblicazione: (2024)

Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
di: Gwak, Daehoon, et al.
Pubblicazione: (2024)

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
di: Lee, Jewon, et al.
Pubblicazione: (2025)

InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
di: Jin, Hoiyeong, et al.
Pubblicazione: (2025)

Sparse Visual Thought Circuits in Vision-Language Models
di: Zhou, Yunpeng
Pubblicazione: (2026)