Cover Image

Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Narnaware, Vishal, Gupta, Animesh, Zhai, Kevin, Wang, Zhenyi, Shah, Mubarak
Format:	Preprint
Published:	2026
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

BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models
by: Narnaware, Vishal, et al.
Published: (2025)

From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos
by: Gupta, Animesh, et al.
Published: (2025)

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
by: Kang, Weitai, et al.
Published: (2024)

Enhancing Box and Block Test with Computer Vision for Post-Stroke Upper Extremity Motor Evaluation
by: Robinson, David, et al.
Published: (2026)

See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
by: Azeez, Mohammad Anas, et al.
Published: (2026)

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

Cross-View Open-Vocabulary Object Detection in Aerial Imagery
by: Kini, Jyoti, et al.
Published: (2025)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
by: Li, Rong, et al.
Published: (2024)

STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery
by: Robinson, David, et al.
Published: (2025)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
by: Chen, Chen, et al.
Published: (2024)

See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
by: Dai, Ziyun, et al.
Published: (2025)

StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales
by: Siddiqui, Nyle, et al.
Published: (2025)

DRISHTIKON: Visual Grounding at Multiple Granularities in Documents
by: Kasuba, Badri Vishal, et al.
Published: (2025)

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
by: Li, Kunyang, et al.
Published: (2026)

Leveraging Pre-Trained Visual Models for AI-Generated Video Detection
by: Veeramachaneni, Keerthi, et al.
Published: (2025)

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

VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale
by: Kulkarni, Parth Parag, et al.
Published: (2026)

Direct Visual Grounding by Directing Attention of Visual Tokens
by: Esmaeilkhani, Parsa, et al.
Published: (2025)

Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection
by: Vellamcheti, Shanmukha, et al.
Published: (2025)

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
by: Zhang, Xiaofeng, et al.
Published: (2024)

See, Explain, and Intervene: A Few-Shot Multimodal Agent Framework for Hateful Meme Moderation
by: Rizwan, Naquee, et al.
Published: (2026)

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization
by: Pan, Miao, et al.
Published: (2026)

Visual Grounding with Attention-Driven Constraint Balancing
by: Kang, Weitai, et al.
Published: (2024)

Learnability-Guided Diffusion for Dataset Distillation
by: Chan-Santiago, Jeffrey A., et al.
Published: (2026)

PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
by: Li, Kunyang, et al.
Published: (2026)

TimeLogic: A Temporal Logic Benchmark for Video QA
by: Swetha, Sirnam, et al.
Published: (2025)

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
by: He, Zhentao, et al.
Published: (2025)

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
by: Yu, Liu, et al.
Published: (2025)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
by: Li, Bin, et al.
Published: (2025)

ViLL-E: Video LLM Embeddings for Retrieval
by: Gupta, Rohit, et al.
Published: (2026)

Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
by: Liu, Yi, et al.
Published: (2026)

VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues
by: Swetha, Sirnam, et al.
Published: (2025)

See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
by: Zhang, Yongchang, et al.
Published: (2026)

Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
by: Fioresi, Joseph, et al.
Published: (2025)

GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformers
by: Pillai, Manu S, et al.
Published: (2024)

Multi-Modal Hallucination Control by Visual Information Grounding
by: Favero, Alessandro, et al.
Published: (2024)

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
by: Zhang, Jiacheng, et al.
Published: (2026)

Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
by: Huy, Ta Duc, et al.
Published: (2025)

Seeing Culture: A Benchmark for Visual Reasoning and Grounding
by: Satar, Burak, et al.
Published: (2025)

How is Visual Attention Influenced by Text Guidance? Database and Model
by: Sun, Yinan, et al.
Published: (2024)