Related papers: SIEVE: Sample-Efficient Parametric Learning from N…

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

Complex narrative contexts often challenge language models' ability to follow instructions, and existing benchmarks fail to capture these difficulties. To address this, we propose Concise-SAE, a training-free framework that improves…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…

This paper addresses the problem of key phrase extraction from sentences. Existing state-of-the-art supervised methods require large amounts of annotated data to achieve good performance and generalization. Collecting labeled data is,…

We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that guide natural interactions. Hence we introduce EventWeave, a framework that explicitly models…

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

As a fundamental task in Information Retrieval and Computational Linguistics, sentence representation has profound implications for a wide range of practical applications such as text clustering, content analysis, question-answering…

Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR…

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to…

We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex…

We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we…

Learning representative embeddings for different types of speaking styles, such as emotion, age, and gender, is critical for both recognition tasks (e.g., cognitive computing and human-computer interaction) and generative tasks (e.g.,…

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence…