10 papers
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Wenxiao Fan, Jingling Fu, Lichen Ma +6
Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences with local objectives. This ove…
Is Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings
Wenxiao Fan, Jingling Fu, Luohang Liu +6
Reasoning-enhanced universal multimodal embeddings (UME) improve heterogeneous retrieval, but plausible rationales do not necessarily produce discriminative rankings. We study this…
iFAN: Inference-Aware Learning for Plain Mask Transformers
Fang Li, Yu He, Haoyang Tong +7
Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly…
Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection
Wenxiao Fan, Jingling Fu, Luohang Liu +8
One-to-one (O2O) matching enables Detection Transformers (DETRs) to perform end-to-end set prediction by assigning each object to a single positive query. However, the strongest cl…
Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning
Wenxiao Fan, Kan Li
Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches. Thi…
Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-Reflection
Wenxiao Fan, Jingling Fu, Fang Li +9
Vision-language models (VLMs) are expected to revise their reasoning when visual evidence changes. Failures to do so are often attributed to insufficient visual attention or contex…
Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
Wenxiao Fan, Kan Li
Deep learning models excel in visual recognition but suffer severe performance drops when training labels are corrupted by noise. Under label noise prior work cannot learn accurate…
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
Wenxiao Fan, Hang Yin, Kan Li
Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rathe…
Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
Hang Yin, Xiaomin He, PeiWen Yuan +5
Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that…
Combating Semantic Contamination in Learning with Label Noise
Wenxiao Fan, Kan Li
Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictio…