43 accepted papers
Scaling large models requires optimization strategies that ensure rapid convergence grounded in stability. Maximal Update Parametrization ($\boldsymbol{\mu}$P) provides a theoretical safeguard for width-invariant $\Theta(1)$ activation control, whereas emerging optimizers like Muon are only "half-al…
Machine learning promises to revolutionize drug discovery, but its "black-box" nature and narrow focus limit adoption by experts. While Large Language Models (LLMs) offer a path forward with their broad knowledge and interactivity, existing methods remain data-intensive and lack transparent reasonin…
Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals th…
Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition molecule generation on empty binding pockets from holo complexes, overlooking informative components such as the filler (ligands and solvent). Here, we…
Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This paper formulate two fundamental desiderata for DFCMM: transparency, avoiding interference with earlier tasks, and fidelity,…
Modern optical flow estimation, though empowered by recent deep neural architectures, remains rooted in the discrete correspondence paradigm inherited from classical vision. Most networks infer frame-to-frame displacements, capturing where pixels move but not how motion evolves continuously through
Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on weighted summation, which is costly to tune and insufficient for …
Remote sensing image segmentation is critical for a range of applications, including natural disaster monitoring and precision agriculture. Open-vocabulary segmentation enhances flexibility by removing fixed category constraints, enabling more fine-grained and adaptive scene understanding. Unlike CL
An event sequence generated by a temporal point process is often associated with a hidden and structured event branching process that captures the triggering relations between its historical and current events. In this study, we design a new plug-and-play module based on the Bregman ADMM (BADMM) al…
Denoising learning of 3D molecules learns molecular representations by imposing noises into the equilibrium conformation and predicting the added noises to recover the equilibrium conformation, which essentially captures the information of molecular force fields. Due to the specificity of Potential…
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human preference reward models fine-tuned based on CLIP and BLIP arch…
Accurately predicting 3D structures and dynamics of physical systems is crucial in scientific applications. Existing approaches that rely on geometric Graph Neural Networks (GNNs) effectively enforce $\mathrm{E}(3)$-equivariance, but they often fail in leveraging extensive broader information. While…
$\textit{Cis}$-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their ability to modulate gene expression, highly depends on the nucleotide sequences, especially specific motifs kn…
Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these mo…
Inspired by the success of unsupervised pre-training paradigms, researchers have applied these approaches to DNA pre-training. However, we argue that these approaches alone yield suboptimal results because pure DNA sequences lack sufficient information, since their functions are regulated by genomic…
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Rec…
Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among joints in human motion. However, existing GCN-based methods ten…
Exploring the bridge between historical and future motion behaviors remains a central challenge in human motion prediction. While most existing methods incorporate a reconstruction task as an auxiliary task into the decoder, thereby improving the modeling of spatio-temporal dependencies, they overlo…
Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i.e., the prediction confidences cannot truly reflect the accuracy. Post-hoc calibration tackles this problem by calibrating the predicti…
Text-to-image generative models specifically those based on diffusion models like Imagen and Stable Diffusion have made substantial advancements. Recently there has been a surge of interest in the delicate refinement of text prompts. Users assign weights or alter the injection time steps of certain…
Multi-Modal Entity Alignment (MMEA) aims to identify equivalent entities across different knowledge graphs by utilizing auxiliary modalities such as images. While MMEA has made significant progress, prevailing methods still heavily rely on abundant annotated entity pairs. Active learning seeks to al…
Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in off-the-shelf multi-modal medical datasets, most existing methods h…
Prior contrast-based methods for video representation learning mainly focus on clip discrimination while ignoring the context and relationship of clips from the same video in the temporal dimension. As a consequence, the learned spatiotemporal representations for successive clips are inconsistent an…
Paired video and language data is naturally temporal concurrency, which requires the modeling of the temporal dynamics within each modality and the temporal alignment across modalities simultaneously. However, most existing video-language representation learning methods only focus on discrete semant…
A meaningful video is semantically coherent and changes smoothly. However, most existing fine-grained video representation learning methods learn frame-wise features by aligning frames across videos or exploring relevance between multiple views, neglecting the inherent dynamic process of each video.…
In long-term time series forecasting, most Transformer-based methods adopt the standard point-wise attention mechanism, which not only has high complexity but also cannot explicitly capture the predictive dependencies from contexts since the corresponding key and value are transformed from the same…
Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton sequence for contrastive learning. However, due to the rich…
Auto-evaluation aims to automatically evaluate a trained model on any test dataset without human annotations. Most existing methods utilize global statistics of features extracted by the model as the representation of a dataset. This ignores the influence of the classification head and loses categor…
How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ignore the fact that real-world data often follows a long-tailed distribution. In t…
Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When the CL model is trained with full images, the performance tes…
Convolutional neural networks use regular quadrilateral convolution kernels to extract features. Since the number of parameters increases quadratically with the size of the convolution kernel, many popular models use small convolution kernels, resulting in small local receptive fields in lower layer…
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or “hard” (positive or negative) features. Early works include more informative features by applying complex data augmentations and large batch size or memory bank, and recent works desi…
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy and architecture design, it still remains two persistent de…
One typical approach to long-form document matching is first conducting alignment between cross-document sentence pairs, and then aggregating all of the sentence-level matching signals. However, this approach could be problematic because the alignment between documents is partial — despite two docum…
Recently, significant progress has been made in masked image modeling to catch up to masked language modeling. However, unlike words in NLP, the lack of semantic decomposition of images still makes masked autoencoding (MAE) different between vision and language. In this paper, we explore a potential…
Explainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances. Most sequence alignment methods infer the optimal alignment by solving an optimization problem under pre-defined feasible alignment constraints, which not only is time…
Person Re-IDentification (P-RID), as an instance-level recognition problem, still remains challenging in computer vision community. Many P-RID works aim to learn faithful and discriminative features/metrics from offline training data and directly use them for the unseen online testing data. However,…
Learning distances that operate directly on multi-dimensional sequences is challenging because such distances are structural by nature and the vectors in sequences are not independent. Generally, distances for sequences heavily depend on the ground metric between the vectors in sequences. We propose…
Supervised dimensionality reduction for sequence data projects the observations in sequences onto a low-dimensional subspace to better separate different sequence classes. It is typically more challenging than conventional dimensionality reduction for static data, because measuring the separability…
Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification. Considering the fact that motion information may not be discriminative nor reliable enough for MsP-RID, this paper is focused on handling the large variations in the visual appea…
Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace. Most DR methods require data to be i.i.d., however, in some doma…
We present a new distance measure between sequences that can tackle local temporal distortion and periodic sequences with arbitrary starting points. Through viewing the instances of sequences as empirical samples of an unknown distribution, we cast the calculation of the distance between sequences a…
Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem. Max-min distance analysis (MMDA) addresses this problem by maximizing the minimum pairwise distance in the latent subspace, but i…