Related papers: SWIFT: Prompt-Adaptive Memory for Efficient Intera…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…
The exponential growth of user-generated movie reviews on digital platforms has made accurate text sentiment classification a cornerstone task in natural language processing. Traditional models, including standard BERT and recurrent…
Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while preserving behavior on benign prompts. We study this tension relative to the frozen generator,…
Video captioning, i.e. the task of generating captions from video sequences creates a bridge between the Natural Language Processing and Computer Vision domains of computer science. The task of generating a semantically accurate description…
Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…
Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…
Web platforms, mobile applications, and connected sensing systems generate multivariate time series with states at multiple levels of granularity, from coarse regimes to fine-grained events. Effective segmentation in these settings requires…
In recent work on time-series prediction, Transformers and even large language models have garnered significant attention due to their strong capabilities in sequence modeling. However, in practical deployments, time-series prediction often…
Continual Semantic Segmentation (CSS) seeks to incrementally learn to segment novel classes while preserving knowledge of previously encountered ones. Recent advancements in CSS have been largely driven by the adoption of Pre-trained Vision…
This paper introduces a novel approach for generating videos called Synchronized Deep Recurrent Attentive Writer (Sync-DRAW). Sync-DRAW can also perform text-to-video generation which, to the best of our knowledge, makes it the first…
Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…
The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature…
Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of…
Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due to computational inefficiency, memory limitations, and…
Large-scale multilingual ASR models like Whisper excel in high-resource settings but face challenges in low-resource scenarios, such as rare languages and code-switching (CS), due to computational costs and catastrophic forgetting. We…
Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…
Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables…
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…
Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We observe that optimized workflows converge to a small family of…