31 accepted papers
Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks, LVLMs remain vulnerable to adversarial attacks, which can re…
Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential Grounding), a novel proxy task framework where MLLMs learn
Autoregressive (AR) models have achieved remarkable success in natural language processing, yet their application to image generation faces significant challenges. When implementing VQ-based decoders for autoregressive image generation, the generated images typically preserve semantic information bu
Multimodal table understanding, which aims for a comprehensive grasp of table content by integrating cellular text, tabular structure, and visual presentation, remains a core yet challenging area of research. We identify that the structural complexity of a table, quantifiable by intrinsic properties
Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising progress in table reasoning from visual table inputs. Despite their ability to capture rich visual cues such as color and layout, MLLMs still underperform compared to text-only models.We argue that a major limitation
Denoising Diffusion Codebook Models (DDCM) have emerged as a promising framework for zero-shot image compression by replacing stochastic sampling with discrete selection from a reproducible Gaussian codebook. By greedily picking noise vectors that best match the target image, DDCM encodes the genera
While recent advancements in Vector Quantization (VQ) models have successfully achieved complete codebook utilization, a critical bottleneck remains largely unexplored: the effective dimensionality of the codebook embedding space. We observe that discrete codebook representations tend to degenerate …
Vector Quantization (VQ) is essential for discretizing continuous representations in unsupervised learning but suffers from representation collapse, causing low codebook utilization and limiting scalability. Existing solutions often rely on complex optimizations or reduce latent dimensionality, whic…
Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities makes the embeddings from the vision projector critical for…
The Incremental Named Entity Recognition (INER) task aims to update a model to extract entities from an expanding set of entity type candidates due to concerns related to data privacy and scarcity. However, conventional sequence labeling approaches to INER often suffer from the catastrophic forgetti…
The task of music-to-lyric generation aims to create lyrics that can be sung in harmony with the music while capturing the music’s intrinsic meaning. Previous efforts in this area have struggled to effectively handle both the structural and semantic alignments of music and lyrics, often relying on r…
Large vision-language models (LVLMs) have demonstrated remarkable image understanding and dialogue capabilities, allowing them to handle a variety of visual question answering tasks. However, their widespread availability raises concerns about unauthorized usage and copyright infringement, where use…
Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using categorical distributions, allowing for different diffusion pr…
People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative v…
To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recognition (ASR) and speech translation (ST). However, the commonly used FL approach (i.e., FEDAVG) in S2T tasks typically su…
Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the optimization challenges encountered with both the embedding s…
Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow…
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed fo…
Leveraging vast training data multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance across various tasks. However their performance in visual document understanding still leaves much room for improvement. T…
Latent-based image generative models, such as Latent Diffusion Models (LDMs) and Mask Image Models (MIMs), have achieved notable success in image generation tasks. These models typically leverage reconstructive autoencoders like VQGAN or VAE to encode pixels into a more compact latent space and lear…
Large Language Model (LLM)-enhanced agents become increasingly prevalent in Human-AI communication, offering vast potential from entertainment to professional domains. However, current multi-modal dialogue systems overlook the acoustic information present in speech, which is crucial for understandin…
Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and visual video signals. Although existing methods have demonstrated that the aligned visual input of lip movements ca…
While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically, due to the low information density of speech data, the transfo…
In this paper, we propose a novel multi-modal framework for Scene Text Visual Question Answering (STVQA), which requires models to read scene text in images for question answering. Apart from text or visual objects, which could exist independently, scene text naturally links text and visual modaliti…
In this paper, we propose a novel span-level model for Aspect-Based Sentiment Analysis (ABSA), which aims at identifying the sentiment polarity of the given aspect. In contrast to conventional ABSA models that focus on modeling the word-level dependencies between an aspect and its corresponding opin…
The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in lat…
We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based methods, SSPGAN is equipped with a siamese semantic-preserving discriminator, which ca…
The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and avoid over-correction, previous sequence-to-sequence (seq2se…
Hierarchical multi-label text classification (HMTC) deals with the challenging task where an instance can be assigned to multiple hierarchically structured categories at the same time. The majority of prior studies either focus on reducing the HMTC task into a flat multi-label problem ignoring the v…
Distributed parallel stochastic gradient descent algorithms are workhorses for large scale machine learning tasks. Among them, local stochastic gradient descent (Local SGD) has attracted significant attention due to its low communication complexity. Previous studies prove that the communication comp…
While large scale pre-trained language models such as BERT have achieved great success on various natural language understanding tasks, how to efficiently and effectively incorporate them into sequence-to-sequence models and the corresponding text generation tasks remains a non-trivial problem. In t…