27 accepted papers
Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of kilobases away. Our work first reveals th…
Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of ke
Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer from two critical limitations: a persistent misalignment betwee
Autonomous vehicle trajectory planning faces significant challenges in dynamic traffic environments due to the complex and mixed causal relationships between critical scene elements (e.g., pedestrians, vehicles, road markings) and safe decision-making. To identify the causal factors influencing plan
This paper focuses on the basic structure of Chinese characters: semantic-phonetic compound characters. This paper takes advantage of this feature of Chinese characters and innovatively proposes a Chinese speech-processing method based on character shape. We use the association between the character…
Accurate and high-fidelity driving scene reconstruction relies on fully leveraging scene information as conditioning. However, existing approaches, which primarily use 3D bounding boxes and binary maps for foreground and background control, fall short in capturing the complexity of the scene and int
Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet they often struggle with context-faithfulness generations that properly reflect contextual knowledge. While existing approaches focus on enhancing the decoding strategies, they ignore the fundamental mechani…
Neural network architectures have a large impact in machine learning. However, in the specific case of reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based mo…
Audio-visual speech recognition (AVSR) aims to enhance the robustness of an automatic speech recognition (ASR) systems by incorporating visual information from lip movements, especially in challenging noisy environments. Nevertheless, most current approaches either involve training from scratch or f…
The utilization of multimodal cues enhances the effectiveness of specific cognitive tasks in audio-visual learning. However, on the one hand, designing a unified model for multimodal learning poses challenges due to the presence of information redundancy and modality noise. On the other hand, existi…
$\textit{Cis}$-regulatory elements (CREs), such as promoters and enhancers, are relatively short DNA sequences that directly regulate gene expression. The fitness of CREs, measured by their ability to modulate gene expression, highly depends on the nucleotide sequences, especially specific motifs kn…
Inspired by the success of unsupervised pre-training paradigms, researchers have applied these approaches to DNA pre-training. However, we argue that these approaches alone yield suboptimal results because pure DNA sequences lack sufficient information, since their functions are regulated by genomic…
Recently, camera-based Bird's-Eye View (BEV) representation has gained significant traction in 3D object detection. However, training high-performance BEV 3D detectors typically requires a large number of annotated samples, which can be costly. Traditional semi-supervised methods for BEV 3D object d
Accurate localization using visual information is a critical yet challenging task, especially in urban environments where nearby buildings and construction sites significantly degrade GNSS (Global Navigation Satellite System) signal quality. This issue underscores the importance of visual localizati…
Chain-of-Thought (CoT) prompting combined with large language models (LLM) has shown great potential in improving performance on challenging reasoning tasks. While understanding why CoT prompting is effective is crucial for the application and improvement of CoT prompting, few studies have addressed…
Knowledge distillation (KD) possesses immense potential to accelerate the deep neural networks (DNNs) for LiDAR-based 3D detection. However in most of prevailing approaches the suboptimal teacher models and insufficient student architecture investigations limit the performance gains. To address thes…
This paper studies the spatio-temporal video grounding task, which aims to localize a spatio-temporal tube in an untrimmed video based on the given text description of an event. Existing one-stage approaches suffer from insufficient space-time interaction in two aspects: i) less precise prediction o…
Large language models (LLMs) internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a crucial dilemma known as knowledge conflicts, where the contextual knowledge…
Chain-of-thought Distillation (CoTD) aims at distilling Chain-of-thought (CoT) reasoning ability of large language models (LLMs) to much smaller student models. The core of CoTD is using a large teacher model to generate rationales and fine-tune smaller student models. However, current Chain-of-thou…
While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments. Current compression techniques, such as parameter pruning, often fail to effectively utilize the knowledge from pruned parameters. To address these challenges,…
Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a single source, which tends to do poorly when noise is present d…
Although In-Context Learning has proven effective across a broad array of tasks, its efficiency is noticeably influenced by the selection of demonstrations. Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scena…
Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine vision-language features. Despite their complexity, RNN-based me…
Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image. A para…
Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features on model predictions. As an explanation method, the evaluatio…
Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors. Existing explanation methods usually pick prominent features such as words or phrases from the input text. However, for NLI, alignments among w…
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow. Despite their complexity, these kinds of approach tend to favour short-term temporal dependencies and are thus prone to accumulating inaccuracies, which cause drift over time…