10 papers · 1 filter
RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models
Feixiang Liu, Qiang Qiu, Qingyang Li +1
Vision-language models can answer spatial relation questions confidently even when the image supports an incompatible relation. We formulate relation-grounded selective prediction:…
SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification
Feixiang Liu, Likun Wang, Qiang Qiu +3
Spatial relation questions require a model to identify the queried subject and object before comparing their layout. Yet a VLM can recognize both entities and still answer from the…
Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference
Feixiang Liu, Qiang Qiu, Hao Zhang +1
Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this protocol can miss a distinct fail…
Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers
Fexiang Liu, Shiye Wang, Qiang Qiu +1
Reliable deployment of multimodal large language models (MLLMs) requires deciding whether a confident visual answer should be trusted, reviewed, or routed to a stronger system. Con…
Visual Credit Audit for Multimodal Spatial Reasoning
Feixiang Liu, Qiang Qiu, Lanbo Sun +3
Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts. Under a fixed forced-choice interface, Visual Credit…
Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification
Jeeyung Kim, Erfan Esmaeili, Qiang Qiu
When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful f…
Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps
Jeeyung Kim, Erfan Esmaeili, Qiang Qiu
In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens pr…
Conditional Text-to-Image Generation with Reference Guidance
Taewook Kim, Ze Wang, Zhengyuan Yang +4
Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating hig…
Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
Zichen Miao, Zhengyuan Yang, Kevin Lin +4
Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer infe…
Model-Agnostic Human Preference Inversion in Diffusion Models
Jeeyung Kim, Ze Wang, Qiang Qiu
Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation…