Copertina

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pan, Miao, Gan, Wangjie, Chen, Jintao, Zhang, Wenqi, Sun, Bing, Yin, Jianwei, Zhang, Xuhong
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

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
di: Gan, Wangjie, et al.
Pubblicazione: (2026)

SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification
di: Xiong, Ke, et al.
Pubblicazione: (2026)

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
di: Guo, Pinxue, et al.
Pubblicazione: (2025)

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
di: Liu, Yanming, et al.
Pubblicazione: (2026)

See or Guess: Counterfactually Regularized Image Captioning
di: Cao, Qian, et al.
Pubblicazione: (2024)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
di: Tang, Feilong, et al.
Pubblicazione: (2025)

Vision Language Models See What You Want but not What You See
di: Gao, Qingying, et al.
Pubblicazione: (2024)

"Can You See Me Think?" Grounding LLM Feedback in Keystrokes and Revision Patterns
di: Zafar, Samra, et al.
Pubblicazione: (2025)

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
di: Jiang, Yankai, et al.
Pubblicazione: (2026)

What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation
di: Yin, Xin, et al.
Pubblicazione: (2024)

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
di: Liu, Yanming, et al.
Pubblicazione: (2024)

Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
di: Liu, Zhaoyang, et al.
Pubblicazione: (2025)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
di: Li, Qiaoru, et al.
Pubblicazione: (2026)

What You See is What You Ask: Evaluating Audio Descriptions
di: Kala, Divy, et al.
Pubblicazione: (2025)

What You See is What You Classify: Black Box Attributions
di: Stalder, Steven, et al.
Pubblicazione: (2022)

Do MLLMs See What We See? Analyzing Visualization Literacy Barriers in AI Systems
di: Mengli, et al.
Pubblicazione: (2026)

Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs
di: Narnaware, Vishal, et al.
Pubblicazione: (2026)

Visual Room 2.0: Seeing is Not Understanding for MLLMs
di: Li, Haokun, et al.
Pubblicazione: (2025)

FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
di: Yin, Zhihan, et al.
Pubblicazione: (2026)

Spatially Selective Imaging in Color: What You See is What You Want
di: John You En Chan, et al.
Pubblicazione: (2024)

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
di: Bao, Yuntai, et al.
Pubblicazione: (2026)

SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
di: Yang, Jingxiao, et al.
Pubblicazione: (2026)

What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
di: Li, Haoxi, et al.
Pubblicazione: (2026)

Explore the Hallucination on Low-level Perception for MLLMs
di: Sun, Yinan, et al.
Pubblicazione: (2024)

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
di: Lin, Weifeng, et al.
Pubblicazione: (2024)

Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things
di: Cheng, Ye, et al.
Pubblicazione: (2025)

Neural Diversity Regularizes Hallucinations in Language Models
di: Chakrabarti, Kushal, et al.
Pubblicazione: (2025)

Mitigating Image Captioning Hallucinations in Vision-Language Models
di: Zhao, Fei, et al.
Pubblicazione: (2025)

Image Embedding Sampling Method for Diverse Captioning
di: Waheed, Sania, et al.
Pubblicazione: (2025)

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
di: Bao, Yuntai, et al.
Pubblicazione: (2026)

What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learning
di: Mohan, Arvind, et al.
Pubblicazione: (2024)

What You See Is Not Always What You Get: Evaluating GPT's Comprehension of Source Code
di: Wen, Jiawen, et al.
Pubblicazione: (2024)

LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning
di: Chao, Lianying, et al.
Pubblicazione: (2026)

See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops
di: Dong, Zixuan, et al.
Pubblicazione: (2025)

Aesthetic Image Captioning with Saliency Enhanced MLLMs
di: Tao, Yilin, et al.
Pubblicazione: (2025)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
di: Zhang, Qizhe, et al.
Pubblicazione: (2025)

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
di: Li, Qinfeng, et al.
Pubblicazione: (2026)

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
di: Jin, Heng, et al.
Pubblicazione: (2026)

Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs
di: Tasnim, Nazia, et al.
Pubblicazione: (2025)

VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning
di: Teng, Fu, et al.
Pubblicazione: (2025)