Large Vision-Language Models

Also known as LVLM

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 36% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 256

All topics

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Sep 26, 2026Junxian Li, Ruixuan Yang, Tianao Zhang +3Efficient VLM Inference VLM Distillation
Shanghai Jiao Tong University · Xi’an Jiaotong University · University of Cambridge +1
RGSQ: Riemannian Geometry-Sensitive Quantization for Large Vision-Language Models
Sep 21, 2026Zhiping Wu, Dongdong Ren, Yangchengyu Zhou +4VLM Quantization Large Vision-Language Models
State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou Campus, Suzhou 215163, China
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
Sep 21, 2026Guangchuan Lv, Dianxing Shi, Dingjie FuEfficient VLM Inference Large Vision-Language Models
Northeastern University · Beihang University · Huazhong University of Science and Technology
Region-Level Policy Optimization for Fine-grained MLLM Perception
Sep 17, 2026Yuheng Shi, Xiaohuan Pei, Minjing Dong +1Efficient VLM Inference Large Vision-Language Models
University of Sydney · City University of Hong Kong
IMFD: End-to-end Multi-Face Forgery Detection through Instruction-based Large Vision-Language Models
Sep 17, 2026Dasom Choi, Sangjun Moon, Hyeongchan Im +5Image Forgery Detection Large Vision-Language Models
Chungnam National University · Institute of Science Tokyo · Nara Institute of Science and Technology (NAIST)
MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education
Sep 16, 2026Luyao Zhu, Xun Wei Yee, Wei Li +2VLM Evaluation Large Vision-Language Models
AI Singapore, National University of Singapore, Singapore · Institute of Advanced Intelligence and Computing, A*STAR · School of Computing, National University of Singapore, Singapore
ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models
Sep 15, 2026Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu +2Vision-Language Models Large Vision-Language Models
Ocean University of China
Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs
Sep 9, 2026Haiji Liang, Pengfei Zhou, Zhenglin Wan +3Efficient VLM Inference Large Vision-Language Models
National University of Singapore · InfRec, Cardinal AI Lab · The Hong Kong University of Science and Technology
SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models
Sep 3, 2026Caoyuan Ma, Tian Gu, Wenpu Liu +11Vision-Language Models Large Vision-Language Models
The University of Tokyo · Wuhan University · Shanghai AI Laboratory +4
RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models
Sep 2, 2026Canjie Liu, Jiawen Kang, Jinbo Wen +1Hallucination Mitigation Large Vision-Language Models
School of Automation, Guangdong University of Technology, Guangzhou, China · Department of Computer Science, City University of Hong Kong, Hong Kong, China · The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
Sep 2, 2026Chengyin Hu, Dingyi Lu, Jiaju Han +5Adversarial Patch Attacks Large Vision-Language Models
Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification
Sep 2, 2026Xuanbing Wen, Boxu Chen, Le Yang +4Hallucination Detection in VLMs Hallucination Detection
Xi’an Jiaotong University, Xi’an 710049, China · Zhongguancun Laboratory, Beijing 100194, China
Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics
Sep 1, 2026Maksim Evdokimov, Matvey Ivanov, Dmitrii Tsiupin +3Training Data Curation Document Information Extraction
T-Tech
IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals
Sep 1, 2026Md. Atabuzzaman, Christian Alexander, Chris ThomasVLM Evaluation Large Vision-Language Models
Department of Computer Science Virginia Tech
The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence
Sep 1, 2026Genpei ZhangVLM Evaluation Large Vision-Language Models
University of Wisconsin–Madison
Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning
Aug 31, 2026Yue Zhou, Yuan Wu, Yi ChangVLM Evaluation Large Vision-Language Models
School of Artificial Intelligence, Jilin University · 2Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China · 3International Center of Future Science, Jilin University
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Aug 31, 2026Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1Hallucination Detection in VLMs VLM Hallucination
School of Computing and Information Systems The University of Melbourne Melbourne, Australia
Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs
Aug 31, 2026Shunjie Wen, Jaeyeon Lee, Dong-Wan ChoiEfficient VLM Inference Large Vision-Language Models
Inha University
Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
Aug 30, 2026Aditi Sarker, Nazreen Shah, Rafi Ibn Sultan +3VLM Evaluation VLM Unlearning
Department of Computer Science, Wayne State University, MI, USA · Department of Electronics & Communications Engineering, IIIT Delhi, India · Institute for AI and Data Science (AIDaS), Wayne State University, MI, USA
RIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding
Aug 30, 2026Shanqing Xu, Meng Luo, Mengchen Qian +7Large Vision-Language Models Long-Video Understanding
Huazhong University of Science and Technology · National University of Singapore · Fudan University
Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization
Aug 30, 2026Aditi Sarker, Rafi Ibn Sultan, Hui Zhu +2VLM Robustness Vision-Language Models
Department of Computer Science, Wayne State University, MI, USA · Institute for AI and Data Science (AIDaS), Wayne State University, MI, USA
Multi-Image Visual Token Pruning in Large Visual Language Models
Aug 27, 2026Rongyang Zhang, Chengqiang Lu, Cong Li +9Efficient VLM Inference Large Vision-Language Models
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Xiaohongshu Inc.
When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs
Aug 25, 2026Zhengxiang Wang, Owen RambowVLM Evaluation Large Vision-Language Models
Department of Linguistics & IACS Stony Brook University
LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
Aug 12, 2026Beomsik Cho, Jinhyeong Kim, Dongseok Lee +1VLM Evaluation Hallucination Detection in VLMs
Yonsei University
Test-Time Hallucination Control in Large Vision-Language Models
Aug 11, 2026Mehran Tamjidi, Hamidreza Dastmalchi, Ali Cheraghian +3Test-Time Adaptation of VLMs Large Vision-Language Models
University of Technology Sydney · York University, Canada · Australian National University +2
Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences
Aug 11, 2026Martina Ianaro, Guilherme Fernandes, Maurizio Gabbrielli +1VLM Evaluation Vision-Language Models
University of Bologna Bologna, Italy · NOVA School of Science and Technology NOVA Laboratory for Computer Science and Informatics Lisbon, Portugal
Where To Look? : Causal Tracing of Vision Encoders in VLM
Aug 11, 2026Naren Kumar S, Tirth Bhatt, Mayank SinghLarge Vision-Language Models VLM Interpretability
LINGO Research Group, Indian Institute of Technology Gandhinagar, India
When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs
Aug 11, 2026Congyang Ou, Ruike Song, Yang Zhou +3Efficient VLM Inference Large Vision-Language Models
Northwestern Polytechnical University · Chongqing University · MiLM Plus, Xiaomi Inc.
Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
Aug 10, 2026Shravan Venkatraman, Omkar Thawakar, Ritesh Thawkar +2VLM Distillation Large Vision-Language Models
1Mohamed bin Zayed University of Artificial Intelligence · 2Aalto University
Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs
Aug 10, 2026Ali Cheraghian, Hamidreza Dastmalchi, Hamed Barzamini +4Large Vision-Language Models Model Editing
Macquarie University, Australia · Australian National University, Australia · York University, Canada +4

Sep 26, 2026, cs.CVJ/K move · Enter open · S save

Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction

Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu+2

Shanghai Jiao Tong University · Xi’an Jiaotong University · University of Cambridge+1

Efficient VLM Inference VLM Distillation Large Vision-Language Models On-Policy Distillation Visual Token Compression

Open paper AskPDF arXiv

Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets. Existing work has explored both visual-token selection and training-based adaptation to reduced visual inputs. We take a step further by asking how a heavily compressed MLLM should learn from the states induced by its own generations. This setting naturally calls for on-policy self-distillation: a heavily compressed model is supervised on the states induced by its own generations, while its full-token counterpart serves as an information-rich teacher. Based on this insight, we propose LT-OPD, a training framework for extreme visual-token reduction. The student rolls out responses with only a small fraction of visual tokens, and a frozen full-token copy of the same MLLM provides distributional supervision along these student-generated trajectories. To stabilize on-policy learning when visual evidence is severely limited, we further introduce a budget-level curriculum that progressively decreases the token budget during training. Across nine benchmarks on Qwen3.5-4B, LT-OPD raises average retained performance under 5% visual-token retention from 68.6% to 82.3%, outperforming training-free, training-based, and reinforcement-learning baselines at the same budget. The gains transfer consistently to Qwen3.5-9B, GLM-4.6V-9B, and LLaVA-OV-1.5-4B. LT-OPD also reduces KV-cache usage by 85.2% and prefill FLOPs by 85.4% without additional inference overhead, demonstrating that on-policy learning can substantially recover capabilities lost to extreme visual-token reduction.

Momentum

Related topics

Latest papers 256