相关论文: UT-ACA: Uncertainty-Triggered Adaptive Context All…

As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now…

A striking property of transformers is their ability to perform in-context learning (ICL), a machine learning framework in which the learner is presented with a novel context during inference implicitly through some data, and tasked with…

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…

Aspect-based sentiment analysis (ABSA) and Targeted ASBA (TABSA) allow finer-grained inferences about sentiment to be drawn from the same text, depending on context. For example, a given text can have different targets (e.g., neighborhoods)…

In long-context question answering, selecting the appropriate scope of context for a query remains a key and unresolved challenge. Insufficient context can lead to missing essential information, whereas excessive context often introduces…

Large language models spend most of their inference cost on attention over long contexts, yet empirical behavior suggests that only a small subset of tokens meaningfully contributes to each query. We formalize this phenomenon by modeling…

Time series domain adaptation aims to transfer the complex temporal dependence from the labeled source domain to the unlabeled target domain. Recent advances leverage the stable causal mechanism over observed variables to model the…

Recently, leveraging pre-trained Large Language Models (LLMs) for time series (TS) tasks has gained increasing attention, which involves activating and enhancing LLMs' capabilities. Many methods aim to activate LLMs' capabilities based on…

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Managing long texts is challenging for large language models (LLMs) due to limited context window sizes. This study introduces UIO-LLMs, an unbiased incremental optimization approach for memory-enhanced transformers under long-context…

Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability…

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental limitation of the softmax function emerges:…

We leverage different context windows when predicting the emotion of different utterances. New modules are included to realize variable-length context: 1) two speaker-aware units, which explicitly model inner- and inter-speaker dependencies…

Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. Previous research shows that using test-time learning to encode context directly into model parameters can effectively enable…

Cloud cover can significantly hinder the use of remote sensing images for Earth observation, prompting urgent advancements in cloud removal technology. Recently, deep learning strategies have shown strong potential in restoring…

Prior study has shown that pretrained language models (PLM) can boost the performance of text-based recommendation. In contrast to previous works that either use PLM to encode user history as a whole input text, or impose an additional…

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

Short-term precipitation forecasting remains challenging due to the difficulty in capturing long-term spatiotemporal dependencies. Current deep learning methods fall short in establishing effective dependencies between conditions and…

Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as…