相关论文: SynRES: Towards Referring Expression Segmentation …

Recently reported state-of-the-art results in visual speech recognition (VSR) often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are limited in size. In this paper, for the first…

Dialogue-Based Generalized Referring Expression Comprehension (GREC) requires models to ground the expression and unlimited targets in complex visual scenes while resolving coreference across a long dialogue context. However, existing…

Evaluating text-to-SQL systems remains largely fragile: correctness is typically judged by executing predicted and gold SQL queries on a single static database, even though the same queries may behave differently under alternative database…

Current synthetic data pipelines for computer vision generate images without diagnosing what the downstream model actually needs. This open-loop paradigm treats synthetic data as cheap real data, randomly sampling the generator's output…

We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method constitutes a two-stage…

Evaluating student responses, from long essays to short factual answers, is a key challenge in educational NLP. Automated Essay Scoring (AES) focuses on holistic writing qualities such as coherence and argumentation, while Automatic Short…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to "adapt" a model trained on simulated images so that it performs well on…

Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker…

The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, tackles this by inserting reasoning steps only during natural…

Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover,…

Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance, and material science. Existing Large (Multimodal) Language…

Recent strides in multimodal large language models (MLLMs) have significantly advanced their performance in many reasoning tasks. However, Abstract Visual Reasoning (AVR) remains a critical challenge, primarily due to limitations in…

Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent video streams remains poorly understood. Existing multi-video benchmarks rely largely…

Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics. This stems from a lack of data for both modeling and evaluating rare senses in existing WSD…

We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity…

Generative models have gained significant attention for their ability to produce realistic synthetic data that supplements the quantity of real-world datasets. While recent studies show performance improvements in wireless sensing tasks by…

Semi-supervised learning has received considerable attention for its potential to leverage abundant unlabeled data to enhance model robustness. Pseudo labeling is a widely used strategy in semi supervised learning. However, existing methods…

Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improvements through simulating those degradations and leveraging…

Reinforcement learning (RL) post-training has enabled newer capabilities in models, such as agentic tool-use for search. However, these models struggle primarily due to limitations with sparse outcome-based rewards and a lack of training…