Related papers: Efficient and Asymptotically Unbiased Constrained …

Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et…

Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as…

Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention. Although methods based on parameter efficient tuning like…

Brain-inspired deep predictive coding networks (DPCNs) effectively model and capture video features through a bi-directional information flow, even without labels. They are based on an overcomplete description of video scenes, and one of…

Domain adaptive semantic segmentation aims to generate accurate and dense predictions for an unlabeled target domain by leveraging a supervised model trained on a labeled source domain. The prevalent self-training approach involves…

Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms…

Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods suffer the drawbacks of lacking universality or highly relying on the auxiliary decoder. To remedy these…

Grammar-based compression is a popular and powerful approach to compressing repetitive texts but until recently its relatively poor time-space trade-offs during real-life construction made it impractical for truly massive datasets such as…

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial…

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

In the field of video analytics, particularly traffic surveillance, there is a growing need for efficient and effective methods for processing and understanding video data. Traditional full video decoding techniques can be computationally…

Semantic segmentation is essential for comprehending images, but the process necessitates a substantial amount of detailed annotations at the pixel level. Acquiring such annotations can be costly in the real-world. Unsupervised domain…

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, and vision-language…

The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implicit knowledge editing and controlled text generation by…

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have…

Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression…

Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the key-value (KV) cache during autoregressive decoding. Existing…

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…