Related papers: Merge Mode for Template-based Intra Mode Derivatio…

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

Software engineers who collaborate to develop software in teams often have to manually merge changes they made to a module (e.g. a class), because the change conflicts with one that has just been made by another engineer to the same or…

This paper proposes a novel maximum-likelihood (ML) soft-decision decoding framework for linear block codes, termed error-building decoding (EBD). The complete decoding process can be performed using only the parity-check matrix, without…

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and…

Cross-modal image-recipe retrieval has gained significant attention in recent years. Most work focuses on improving cross-modal embeddings using unimodal encoders, that allow for efficient retrieval in large-scale databases, leaving aside…

Conventional turbo codes (CTCs) usually employ a block-oriented interleaving so that each block is separately encoded and decoded. As interleaving and de-interleaving are performed within a block, the message-passing process associated with…

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on…

This paper presents a three-tier modality alignment approach to learning text-image joint embedding, coined as JEMA, for cross-modal retrieval of cooking recipes and food images. The first tier improves recipe text embedding by optimizing…

Infrared imaging offers resilience against changing lighting conditions by capturing object temperatures. Yet, in few scenarios, its lack of visual details compared to daytime visible images, poses a significant challenge for human and…

In video coding, it is expected that the encoder could adaptively select the encoding parameters (e.g., quantization parameter) to optimize the bit allocation to different sources under the given constraint. However, in hybrid video coding,…

We are developing code-division multiplexing (CDM) systems for transition-edge sensor arrays with the goal of reaching multiplexing factors in the hundreds. We report on x-ray measurements made with a four-channel prototype CDM system that…

We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…

Intra prediction is an essential component in the image coding. This paper gives an intra prediction framework completely based on neural network modes (NM). Each NM can be regarded as a regression from the neighboring reference blocks to…

Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for training and final-layer representations for predictions, potentially overlooking the predictive power embedded in intermediate layers. Surprisingly,…

With the fast-growing GUI development workload in the Internet industry, some work on intelligent methods attempted to generate maintainable front-end code from UI screenshots. It can be more suitable for utilizing UI design drafts that…

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information.…

Existing deep image watermarking methods follow a fixed embedding-distortion-extraction pipeline, where the embedder and extractor are weakly coupled through a final loss and optimized in isolation. This design lacks explicit collaboration,…

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on…

In this paper, we investigate the feasibility of leveraging large language models (LLMs) for integrating general knowledge and incorporating pseudo-events as priors for temporal content distribution in video moment retrieval (VMR) models.…