Search Results for author:
Found 14 papers, 6 papers with code
Generalized Trajectory Scoring for End-to-end Multimodal Planning
GTRS consists of three complementary innovations: (1) a diffusion-based trajectory generator that produces diverse fine-grained proposals; (2) a vocabulary generalization technique that trains a scorer on super-dense trajectory sets with dropout regularization, enabling its robust inference on smaller subsets; and (3) a sensor augmentation strategy that enhances out-of-domain generalization while incorporating refinement training for critical trajectory discrimination.
DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
In complex driving environments, autonomous vehicles must navigate safely.
MDP: Multidimensional Vision Model Pruning with Latency Constraint
Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP reduction, with existing latency-aware methods frequently relying on simplistic, suboptimal linear models that fail to generalize well to transformers, where multiple interacting dimensions impact latency.
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge.
Target-aware Bidirectional Fusion Transformer for Aerial Object Tracking
The trackers based on lightweight neural networks have achieved great success in the field of aerial remote sensing, most of which aggregate multi-stage deep features to lift the tracking quality.
Enhancing Autonomous Driving Safety with Collision Scenario Integration
In this paper, we propose SafeFusion, a training framework to learn from collision data.
Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint
We develop a latency modeling technique that accurately captures model-wide latency variations during pruning, which is crucial for achieving an optimal latency-accuracy trade-offs at high pruning ratio.
Multi-attention Associate Prediction Network for Visual Tracking
They are capable of fully capturing the category-related semantics for classification and the local spatial contexts for regression, respectively.
Refining Pre-Trained Motion Models
In the first stage, we use the pre-trained model to estimate motion in a video, and then select the subset of motion estimates which we can verify with cycle-consistency.
Revisiting Deformable Convolution for Depth Completion
Our study reveals that, different from prior work, deformable convolution needs to be applied on an estimated depth map with a relatively high density for better performance.
Pruning for Better Domain Generalizability
On DomainBed benchmark and state-of-the-art MIRO, we can further boost its performance by 1 point only by introducing 10% sparsity into the model.
DiSparse: Disentangled Sparsification for Multitask Model Compression
We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts.
Updatable Siamese Tracker with Two-stage One-shot Learning
Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency.
Select Good Regions for Deblurring based on Convolutional Neural Networks
The goal of blind image deblurring is to recover sharp image from one input blurred image with an unknown blur kernel.
