Related papers: Polymorph: Energy-Efficient Multi-Label Classifica…

Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie…

Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-depth and layer-skipping methods reduce this cost, but often…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in…

As Low-Rank Adaptation (LoRA) becomes the standard approach for efficiently fine-tuning large language models (LLMs), shared clusters increasingly execute many concurrent LoRA training jobs over the same frozen backbone. While recent…

Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet harmful or socially disruptive content. This challenge has spurred growing interest in…

A naive application of state-of-the-art bidirectional encoders for streaming sequence tagging would require encoding each token from scratch for each new token in an incremental streaming input (like transcribed speech). The lack of…

Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates. This paradigm presents challenges for systems that…

Scalable high-quality MAP inference in arbitrary-order Markov Random Fields (MRFs) remains challenging. Approximate message-passing methods are often efficient but can degrade on dense or high-order instances, while exact solvers such as…

A cross domain multistream classification is a challenging problem calling for fast domain adaptations to handle different but related streams in never-ending and rapidly changing environments. Notwithstanding that existing multistream…

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle when references exhibit severe stylistic domain gaps with the…

Visual analogy learning enables image manipulation through demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\{\mathbf{a}$, $\mathbf{a}'$,…

Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur high computational costs due to full-parameter fine-tuning…

Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, including newly emerging entities and culturally specific categories. We introduce…

The pretrain+fine-tune paradigm is foundational for deploying large language models (LLMs) across various downstream applications. Within this framework, Low-Rank Adaptation (LoRA) stands out for its parameter-efficient fine-tuning (PEFT),…

Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled,…

In today's fast-paced world, accurately monitoring stress levels is crucial. Sensor-based stress monitoring systems often need large datasets for training effective models. However, individual-specific models are necessary for personalized…

Recently,there has been a lot of interest in building compact models for video classification which have a small memory footprint (<1 GB). While these models are compact, they typically operate by repeated application of a small weight…