Copertina

NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lan, Jian, Liu, Zhicheng, Wang, Xinpeng, Zhou, Yuhao, Chen, Haokun, Lv, Jiancheng, Plank, Barbara, Seidl, Thomas
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
di: Zhou, Yuhao, et al.
Pubblicazione: (2026)

Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models
di: Lan, Jian, et al.
Pubblicazione: (2025)

Style Quantization for Data-Efficient GAN Training
di: Wang, Jian, et al.
Pubblicazione: (2025)

Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA
di: Lan, Jian, et al.
Pubblicazione: (2024)

BINO: Encoder Centric Self Supervised Stereo With Native Pair Input
di: Zhou, Haokun
Pubblicazione: (2026)

Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering
di: Lan, Jian, et al.
Pubblicazione: (2025)

Target-Guided Bayesian Flow Networks for Quantitatively Constrained CAD Generation
di: Zheng, Wenhao, et al.
Pubblicazione: (2025)

UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
di: Ni, Shuo, et al.
Pubblicazione: (2026)

GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning
di: Ma, Mingchuan, et al.
Pubblicazione: (2025)

FACT: A Simple and Efficient Framework for Active Finetuning
di: Xu, Wenshuai, et al.
Pubblicazione: (2026)

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
di: Aravindan, Ashwath Vaithinathan, et al.
Pubblicazione: (2025)

Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases
di: Liu, Xinpeng, et al.
Pubblicazione: (2023)

The Solution for the CVPR2024 NICE Image Captioning Challenge
di: Huang, Longfei, et al.
Pubblicazione: (2024)

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
di: Liu, Peng, et al.
Pubblicazione: (2025)

VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
di: Hong, Hyesoo, et al.
Pubblicazione: (2026)

CLGRPO: Reasoning Ability Enhancement for Small VLMs
di: Wang, Fanyi, et al.
Pubblicazione: (2025)

Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels
di: Tian, Yuxin, et al.
Pubblicazione: (2024)

FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking
di: Song, Rongzihan, et al.
Pubblicazione: (2024)

ARTeFACT: Benchmarking Segmentation Models on Diverse Analogue Media Damage
di: Ivanova, Daniela, et al.
Pubblicazione: (2024)

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
di: Wang, Jiancheng, et al.
Pubblicazione: (2026)

Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs
di: Yu, Jiaao, et al.
Pubblicazione: (2025)

DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
di: Pan, Jiazhen, et al.
Pubblicazione: (2026)

DISSECT: Diagnosing Where Vision Ends and Language Priors Begin in Scientific VLMs
di: Kukreja, Dikshant, et al.
Pubblicazione: (2026)

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs
di: Li, Weiming, et al.
Pubblicazione: (2025)

Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning
di: Xie, Zhuofan, et al.
Pubblicazione: (2026)

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
di: Berman, Shmuel, et al.
Pubblicazione: (2025)

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
di: Ge, Yuyao, et al.
Pubblicazione: (2025)

Caption This, Reason That: VLMs Caught in the Middle
di: Weng, Zihan, et al.
Pubblicazione: (2025)

Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
di: Elmansoury, Sary, et al.
Pubblicazione: (2025)

ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
di: Huang, Irene, et al.
Pubblicazione: (2024)

TIR-Flow: Active Video Search and Reasoning with Frozen VLMs
di: Jin, Hongbo, et al.
Pubblicazione: (2026)

VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs
di: Törtei, Brigitta Malagurski, et al.
Pubblicazione: (2025)

Benchmarking VLMs' Reasoning About Persuasive Atypical Images
di: Malakouti, Sina, et al.
Pubblicazione: (2024)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
di: Li, Yiwei, et al.
Pubblicazione: (2026)

DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks
di: Zhou, Haokun, et al.
Pubblicazione: (2024)

VisualActBench: Can VLMs See and Act like a Human?
di: Zhang, Daoan, et al.
Pubblicazione: (2025)

[De|Re]constructing VLMs' Reasoning in Counting
di: Alghisi, Simone, et al.
Pubblicazione: (2025)

CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
di: Jian, Ai, et al.
Pubblicazione: (2025)

PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models
di: Mak, Chak-Wing, et al.
Pubblicazione: (2026)

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
di: Li, Jiangyang, et al.
Pubblicazione: (2026)