Yibing Liu

Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabilities. However, under lossy context compression in a compressor–decoder setup, we find a \textbf\textitSize-Fidelity Paradox: increasing compressor size can lessen the faithfulness of reconstructed contexts though reconstruction error decreases. Across 27 compressor setups spanning model families, scales, and compression rates, we coin this paradox arising from two dominant factors: 1) \textitknowledge overwriting: larger models increasingly replace source facts with their own prior beliefs, \textite.g., “the white strawberry“ → “the red strawberry“; and 2) \textitsemantic drift: larger models tend to paraphrase or restructure content instead of reproducing it verbatim, \textite.g., “Alice hit Bob“ → “Bob hit Alice“. Interestingly, this paradox persists across varied settings, with mid-sized compressors often outperforming larger ones in faithful recovery. By analyzing the compressed memory via embedding geometry and reconstruction determinacy, we further reveal that compressors tend to organize memory across broader semantic subspaces, yielding more ambiguous representations prone to overwriting, drift, and weakened recovery. These findings complement existing evaluations of context compression and expose a breakdown of scaling laws when the objective shifts from plausible generation to faithful preservation.

Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often overlook the evaluation of authenticity and recovery quality of user privacy. To this end, this work uniquely focuses on the critical challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios. We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset, which includes a wide range of privacy categories and user instructions to simulate real MLLM applications. This dataset offers protected surrogates alongside their various MLLM-edited versions, thus enabling the direct assessment of privacy recovery quality. By formulating privacy recovery as a guided generation task conditioned on complementary multimodal signals, we further introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits. The experiments on both SPPE and InstructPix2Pix further show that our approach generalizes well across diverse visual content and editing tasks, achieving a strong balance between privacy protection and MLLM usability.

The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the neuron activation coverage (NAC) – a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.

Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicators. However, in this paper, we find one critical limitation in attention explanations: weakness in identifying the polarity of feature impact. This would be somehow misleading – features with higher attention weights may not faithfully contribute to model predictions; instead, they can impose suppression effects. With this finding, we reflect on the explainability of current attention-based techniques, such as Attention \bigodot Gradient and LRP-based attention explanations. We first propose an actionable diagnostic methodology (henceforth faithfulness violation test) to measure the consistency between explanation weights and the impact polarity. Through the extensive experiments, we then show that most tested explanation methods are unexpectedly hindered by the faithfulness violation issue, especially the raw attention. Empirical analyses on the factors affecting violation issues further provide useful observations for adopting explanation methods in attention models.