Related papers: The Rescue Effect: Spatio-Semantic Early Exit Bypa…

Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, reducing the precision to 2-bit usually triggers a catastrophic…

We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few. Though deep learning leads to groundbreaking performance in these domains, the…

Recent advancements in large-scale pretraining in natural language processing have enabled pretrained vision-language models such as CLIP to effectively align images and text, significantly improving performance in zero-shot image…

Due to the prevalence of scale variance in nature images, we propose to use image scale as a self-supervised signal for Masked Image Modeling (MIM). Our method involves selecting random patches from the input image and downsampling them to…

Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a…

Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive…

Low-rank adaptation (LoRA) has emerged as a powerful tool for parameter-efficient fine-tuning of large language models (LLMs). This paper studies LoRA under a federated learning setting, enabling collaborative fine-tuning across clients…

Retrieval augmented generation (RAG) has transformed text based question answering, yet its extension to visual domains remains hindered by fundamental challenges: bridging the modality gap between image queries and text heavy knowledge…

Model compression has become an important tool for making image super resolution models more efficient. However, the gap between the best compressed models and the full precision model still remains large and a need for deeper understanding…

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

The rapid advancement of generative models has made real and synthetic images increasingly indistinguishable. Although extensive efforts have been devoted to detecting AI-generated images, out-of-distribution generalization remains a…

We identify a core failure mode that occurs when using the usual linear interpolation on rotary positional embeddings (RoPE) for mixed-resolution denoising with Diffusion Transformers. When tokens from different spatial grids are mixed, the…

Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and…

Video Joint Embedding Predictive Architectures (V-JEPA) learn generalizable off-the-shelf video representation by predicting masked regions in latent space with an exponential moving average (EMA)-updated teacher. While EMA prevents…

A widely used method for mitigating errors in noisy quantum computers is Richardson extrapolation, a technique in which the overall effect of noise on the estimation of quantum expectation values is captured by a single parameter that,…

Uncertainty in timing information pertaining to the start time of microphone recordings and sources' emission time pose significant challenges in various applications, such as joint microphones and sources localization. Traditional…

Prior work suggests that neural networks tend to learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we derive a novel closed-form concept erasure method, QLEACE, which…

Object detection in hazy environments is challenging because degraded objects are nearly invisible and their semantics are weakened by environmental noise, making it difficult for detectors to identify. Common approaches involve image…