8 accepted papers
Current methods for editing pre-trained models face significant challenges, primarily high computational costs and limited scalability. Task arithmetic has recently emerged as a promising solution, using simple arithmetic operations—addition and negation—based on task vectors which are the differenc
Sharpness-Aware Minimization (SAM) improves generalization by minimizing the worst-case loss within a fixed parameter-space radius neighborhood. SAM and its variants mainly rely on a first-order linearized surrogate, while flat minima are inherently a second-order (curvature) notion. We revisit this…
Loss reweighting is a widely used strategy for long-tailed classification, but existing reweighting strategies often rely on heuristics and rarely define a well-specified target. Inspired by Neural Collapse (NC), the ideal simplex Equiangular Tight Frame (ETF) terminal geometry suggests equal per-cl…
Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding o
Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and the classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe sample imbalance tends to prevent the emergence of the NC
Accurate ego-centric localization assumes a paramount significance in the domain of autonomous driving. However, traditional methods for camera-LiDAR map localization rely on perspective projection to create a unified representation, which often falls short due to challenges such as occlusion and th…
Existing LiDAR odometry strategies match a new scan iteratively with previous fixed-pose scans, gradually accumulating errors. Furthermore, as an effective joint optimization mechanism, bundle adjustment (BA) cannot be directly introduced into odometry due to the intensive computation of global land…
In this paper, a spectral-spatial symmetrical aggregation cross-linking network (SACLNet) is developed for multi-modal data classification, which contains three modules as follows. First, the Spectro-Spatial Feature Learning Module is proposed, using the involution operation sliding over the spectra…