Related papers: DAM: Dynamic Adapter Merging for Continual Video Q…
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory…
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…
Unsupervised Domain Adaptation (UDA) has emerged as a key solution in data-driven fault diagnosis, addressing domain shift where models underperform in changing environments. However, under the realm of continually changing environments,…
Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple…
Adaptive representations are increasingly indispensable for reducing the in-memory and on-disk footprints of large-scale data. Usual solutions are designed broadly along two themes: reducing data precision, e.g., through compression, or…
Video question answering (VideoQA) is designed to answer a given question based on a relevant video clip. The current available large-scale datasets have made it possible to formulate VideoQA as the joint understanding of visual and…
Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues.…
Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges…
An important problem in multiview representation learning is finding the optimal combination of views with respect to the specific task at hand. To this end, we introduce NAM: a Neural Attentive Multiview machine that learns multiview item…
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is…
Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has…
Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality…
Modern recommendation systems frequently employ online learning to dynamically update their models with freshly collected data. The most commonly used optimizer for updating neural networks in these contexts is the Adam optimizer, which…
Recent works in dataset distillation seek to minimize training expenses by generating a condensed synthetic dataset that encapsulates the information present in a larger real dataset. These approaches ultimately aim to attain test accuracy…
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps…
The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam. Here, we study its…
Vision-language foundation models (VLMs), such as CLIP, exhibit remarkable performance across a wide range of tasks. However, deploying these models can be unreliable when significant distribution gaps exist between training and test data,…
Dense Associative Memory (DAM) models have been attracting renewed attention since they were shown to be robust to adversarial examples and closely related to cutting edge machine learning paradigms, such as the attention mechanism and…
Long-context LLMs and Retrieval-Augmented Generation (RAG) systems process information passively, deferring state tracking, contradiction resolution, and evidence aggregation to query time, which becomes brittle under ultra long streams…