相关论文: Knowing When to Answer: Adaptive Confidence Refine…

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…

Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different…

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external documents at inference time, enabling up-to-date knowledge access without costly retraining. However, conventional RAG methods retrieve…

Reliable set-valued prediction provides a principled way to mitigate hallucinations in open-ended question answering (QA), yet existing conformal approaches typically rely on a fragile premise: finite sampling must already produce at least…

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in…

Visual Question Answering (VQA) is a core task for evaluating the capabilities of Vision-Language Models (VLMs). Existing VQA benchmarks primarily feature clear and unambiguous image-question pairs, whereas real-world scenarios often…

Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability patches. However, questions remain about their ability to repair unseen vulnerabilities.…

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which is computationally expensive and yields overly conservative…

Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…

Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge,…

Visual autoregressive (VAR) models have recently emerged as a promising alternative for image generation, offering stable training, non-iterative inference, and high-fidelity synthesis through next-scale prediction. This encourages the…

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual…

Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance,…

Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering). Current debiasing methods…

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent,…

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously struggling with the patch overfitting issue due to the weak…

Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to…

Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the…