12 papers
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
Jiyuan Liu, Liangwei Nathan Zheng, Wei Emma Zhang +2
Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality that is useful for one input…
Probing Routing-Conditional Calibration in Attention-Residual Transformers
Wenhao Liang, Lin Yue, Wei Emma Zhang +4
Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly accompany predictions with sampl…
Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
Liangwei Nathan Zheng, Wei Emma Zhang, Mingyu Guo +2
Effectively managing missing modalities is a fundamental challenge in real-world multimodal learning scenarios, where data incompleteness often results from systematic collection e…
Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers
Wenhao Liang, Wei Emma Zhang, Lin Yue +4
Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assu…
Neural Tractability via Structure: Learning-Augmented Algorithms for Graph Combinatorial Optimization
Jialiang Li, Weitong Chen, Mingyu Guo
Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions fo…
Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS
Liangwei Nathan Zheng, Wenhao Liang, Wei Emma Zhang +3
Pseudo-Alignment is a pervasive challenge in many large language models for time series (LLM4TS) models, often causing them to underperform compared to linear models or randomly in…