Related papers: Motion2Language, unsupervised learning of synchron…

Gloss-free Sign Language Translation (SLT) converts sign videos directly into spoken language sentences without relying on glosses. Recently, Large Language Models (LLMs) have shown remarkable translation performance in gloss-free methods…

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical…

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the…

In recent years, creative content generations like style transfer and neural photo editing have attracted more and more attention. Among these, cartoonization of real-world scenes has promising applications in entertainment and industry.…

We introduce a novel method for controlling a motion sequence using an arbitrary temporal control sequence using temporal alignment. Temporal alignment of motion has gained significant attention owing to its applications in motion control…

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the…

This paper studies the creation of textual descriptions of user activities and interactions on smartphones. Our approach of referring to encrypted mobile traffic exceeds traditional smartphone activity classification methods in terms of…

A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have…

We study architectural and optimization techniques for sample-efficient language modeling under the constraints of the BabyLM 2025 shared task. Our model, BLaLM, replaces self-attention with a linear-time mLSTM token mixer and explores…

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial…

Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect this embodied dimension, limiting their ability to capture…

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks…

We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Human action recognition and motion generation are two active research problems in human-centric computer vision, both aiming to align motion with textual semantics. However, most existing works study these two problems separately, without…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…

Spontaneous mouse behavior is composed from repeatedly-used modules of movement (e.g., rearing, running, grooming) that are flexibly placed into sequences whose content evolves over time. By identifying behavioral modules and the order in…

As wearable sensing becomes increasingly pervasive, a key challenge remains: how can we generate natural language summaries from raw physiological signals such as actigraphy - minute-level movement data collected via accelerometers? In this…

Self-attention is a useful mechanism to build generative models for language and images. It determines the importance of context elements by comparing each element to the current time step. In this paper, we show that a very lightweight…