Related papers: BEAST: Efficient Tokenization of B-Splines Encoded…
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes…
Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding analytic surface structure and topological adjacency and thereby weakening consistent instance-level analysis. We present STEP-Parts,…
Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the…
Tactile sensing is essential for robotic manipulation, prosthetics and assistive technologies, yet neuromorphic tactile datasets remain limited compared to their visual counterparts. We introduce STEMNIST, a large-scale neuromorphic tactile…
Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It is challenging to…
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image…
With the development of robotics, skeleton-based action recognition has become increasingly important, as human-robot interaction requires understanding the actions of humans and humanoid robots. Due to different sources of human skeletons…
Meta-learning, i.e., "learning to learn", is a promising approach to enable efficient BCI classifier training with limited amounts of data. It can effectively use collections of in some way similar classification tasks, with rapid…
Dynamic scene understanding remains a persistent challenge in robotic applications. Early dynamic mapping methods focused on mitigating the negative influence of short-term dynamic objects on camera motion estimation by masking or tracking…
In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (BER) and block error…
Existing video coding for machines is often trained for a specific downstream task and model. As a result, the compressed representation becomes tightly coupled to the end task, making it difficult to scale across multiple tasks or adapt to…
Recent efforts target spoken language models (SLMs) that not only listen but also speak for more natural human-LLM interaction. Joint speech-text modeling is a promising direction to achieve this. However, the effectiveness of recent speech…
Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…
Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text has inspired scaling sequence…
The bee-identification problem, formally defined by Tandon, Tan and Varshney (2019), requires the receiver to identify "bees" using a set of unordered noisy measurements. In this previous work, Tandon, Tan, and Varshney studied error…
Behavior recognition is an important task in video representation learning. An essential aspect pertains to effective feature learning conducive to behavior recognition. Recently, researchers have started to study fine-grained behavior…
Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large networks pose significant computational challenges during…
Binary code similarity detection (BCSD) has various applications, including but not limited to vulnerability detection, plagiarism detection, and malware detection. Previous research efforts mainly focus on transforming binary code to…
As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training…