26 accepted papers
Sign Language Production (SLP) aims to translate spoken language into sign sequences, where the main challenge lies in generating coherent and natural poses from discrete glosses (G2P). Existing G2P methods typically treat each pose as an indivisible unit, limiting their ability to capture fine-grai
Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations, including the risk of test data contamination from textbook…
Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the transformer architecture's reliance on self-attention, particularly the large KV cache for long-sequence inference. Recent efforts to reduce KV cache si…
Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer’s Key-Value cache. To mitigate this, recent methods employ a scoring-aggregation framework to evict unimportant cache entries…
Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical cache elements during runtime while preserving generation quali…
Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding phases. Although several attempts have been made to accelerate de…
To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as an external resource to enhance LLM reasoning.However, existing KG-RAG approaches struggle with a…
In continuous sign language recognition (CSLR), 2D-CNN-based extractors are often insufficiently trained for spatial capture and struggle with temporal modeling. This leads to incomplete spatial discrimination, hindering the understanding actions across frames. To address these limitations, we propo…
Current continuous sign language recognition (CSLR) methods typically rely on single or adjacent frames for calculations, which can overlook broader contextual information and result in lower accuracy. To address this issue, we introduce CVSign, which constructs an extended contextual space frame by…
Sketches, probabilistic structures for estimating item frequencies in infinite data streams with limited space, are widely used across various domains. Recent studies have shifted the focus from handcrafted sketches to neural sketches, leveraging memory-augmented neural networks (MANNs) to enhance t…
The primary challenge in continuous sign language recognition (CSLR) mainly stems from the presence of multi-orientational and long-term motions. However, current research overlooks these crucial aspects, significantly impacting accuracy. To tackle these issues, we propose a novel CSLR framework: Or…
We prove that using global observables to train the matrix product state ansatz results in the vanishing of all partial derivatives, also known as barren plateaus, while using local observables avoids this. This ansatz is widely used in quantum machine learning for learning weakly entangled state ap…
This paper presents PCDreamer, a novel method for point cloud completion. Traditional methods typically extract features from partial point clouds to predict missing regions, but the large solution space often leads to unsatisfactory results. More recent approaches have started to use images as extr…
Large language models excel at many tasks but often incur high inference costs during deployment. To mitigate hallucination, many systems use a knowledge graph to enhance retrieval-augmented generation (KG-RAG). However, the large amount of retrieved knowledge contexts increase these inference costs
In the field of multi-variable long-term time series (MLTS) prediction, many deep learning models have been developed, and Transformer-based models have received widespread attention for their ability to capture the complex interactions between sequences. However, as the sequence length increases an…
Variational Quantum Algorithms (VQA) have been identified as a promising candidate for the demonstration of near-term quantum advantage in solving optimization tasks in chemical simulation, quantum information, and machine learning. The standard model of training requires a significant amount of qua…
Accurate human motion prediction is vital for diverse artificial intelligence applications, and recent research has yielded substantial advancements. Despite this, the prediction process often encounters abrupt discontinuities and accumulates errors over the long term due to insufficient modeling of…
A graph is a structure made up of vertices and edges used to represent complex relationships between entities, while a graph stream is a continuous flow of graph updates that convey evolving relationships between entities. The massive volume and high dynamism of graph streams promote research on dat…
This paper proposes an efficient and lightweight model called PoseHMR to address the interference of irrelevant image features and the issues of model inefficiency in 3D human body mesh reconstruction. PoseHMR uses a transformer-decoder architecture and obtains holistic and regional prior constraint…
Program verification is vital for ensuring software reliability, especially in the context of increasingly complex systems. Loop invariants, remaining true before and after each iteration of loops, are crucial for this verification process. Traditional provers and machine learning based methods for…
Variational quantum algorithms (VQAs) are the quantum analog of classical neural networks (NNs). A VQA consists of a parameterized quantum circuit (PQC) which is composed of multiple layers of ansatzes (simpler PQCs, which are an analogy of NN layers) that differ only in selections of parameters. Pr…
Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set. However, the extracted knowledge is insufficient to cope with the variable intra-class differences s…
To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain.…
In this paper, we provide two views of constrained differential private (DP) mechanisms. The first one is as belief revision. A constrained DP mechanism is obtained by standard probabilistic conditioning, and hence can be naturally implemented by Monte Carlo algorithms. The other is as belief upda…
In large-scale underground mines and mine-like deep urban canyons, intersections are crucial geometry structures. Accurate recognition of intersections is of great importance to improve localization precision for Unmanned Aerial Vehicles(UAVs) and Unmanned Ground Vehicles(UGVs). Currently, tradition
Closed-loop production lines with constant number of carriers are widely encountered in manufacturing systems. In this letter, we introduce an iteration method to study the key performance indicator (KPI) of closed-loop production lines with geometric reliability machines. First, analysis of two-mac