相关论文: HEED: Density-Weighted Residual Alignment for Hybr…

We introduce a simple yet effective distillation framework that is able to boost the vanilla ResNet-50 to 80%+ Top-1 accuracy on ImageNet without tricks. We construct such a framework through analyzing the problems in the existing…

Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of…

Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…

Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. However, the unprecedented detection performance of these vision…

The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models depend on complex feature transformations,…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed…

Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble…

Large language models having hundreds of millions, and even billions, of parameters have performed extremely well on a variety of natural language processing (NLP) tasks. Their widespread use and adoption, however, is hindered by the lack…

We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an…

Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of…

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability…

Knowledge-based Visual Question Answering (KBVQA) necessitates external knowledge incorporation beyond cross-modal understanding. Existing KBVQA methods either utilize implicit knowledge in multimodal large language models (MLLMs) via…

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, learn powerful representations from unlabeled data but are typically pretrained in isolation, overlooking complementary insights and…

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

Mainstream object detectors are commonly constituted of two sub-tasks, including classification and regression tasks, implemented by two parallel heads. This classic design paradigm inevitably leads to inconsistent spatial distributions…

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption…

Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will…