Search Results for author:
Found 25 papers, 14 papers with code
Bursting Filter Bubble: Enhancing Serendipity Recommendations with Aligned Large Language Models
Recommender systems (RSs) often suffer from the feedback loop phenomenon, e. g., RSs are trained on data biased by their recommendations.
Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
Our method uses raymap conditioning to both augment visual features with spatial information from different viewpoints, as well as to guide the generation of images and depth maps from novel views.
Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
It enables users to conveniently specify the desired editing region and the desired dragging direction through the input of 3D masks and pairs of control points, thereby enabling precise control over the extent of editing.
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning.
Learning to Drive via Asymmetric Self-Play
Large-scale data is crucial for learning realistic and capable driving policies.
SusFL: Energy-Aware Federated Learning-based Monitoring for Sustainable Smart Farms
We propose a novel energy-aware federated learning (FL)-based system, namely SusFL, for sustainable smart farming to address the challenge of inconsistent health monitoring due to fluctuating energy levels of solar sensors.
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind occlusions.
FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects
In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data.
MotionLM: Multi-Agent Motion Forecasting as Language Modeling
Here, we represent continuous trajectories as sequences of discrete motion tokens and cast multi-agent motion prediction as a language modeling task over this domain.
Towards Zero-Shot Scale-Aware Monocular Depth Estimation
Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions.
Viewpoint Equivariance for Multi-View 3D Object Detection
We design view-conditioned queries at the output level, which enables the generation of multiple virtual frames during training to learn viewpoint equivariance by enforcing multi-view consistency.
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects.
Depth Is All You Need for Monocular 3D Detection
Our methods leverage commonly available LiDAR or RGB videos during training time to fine-tune the depth representation, which leads to improved 3D detectors.
COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles
To evaluate our model, we develop AutoCastSim, a network-augmented driving simulation framework with example accident-prone scenarios.
Contrastive Test-Time Adaptation
We propose a novel way to leverage self-supervised contrastive learning to facilitate target feature learning, along with an online pseudo labeling scheme with refinement that significantly denoises pseudo labels.
Multi-Frame Self-Supervised Depth with Transformers
Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures.
Learning from All Vehicles
In this paper, we present a system to train driving policies from experiences collected not just from the ego-vehicle, but all vehicles that it observes.
Ranked #5 on
Autonomous Driving
on CARLA Leaderboard
Region-level Active Detector Learning
Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level selection criteria.
CARTL: Cooperative Adversarially-Robust Transfer Learning
In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain.
Learning to drive from a world on rails
This assumption greatly simplifies the learning problem, factorizing the dynamics into a nonreactive world model and a low-dimensional and compact forward model of the ego-vehicle.
Ranked #13 on
Autonomous Driving
on CARLA Leaderboard
Minimax Active Learning
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator.
Learning by Cheating
We first train an agent that has access to privileged information.
Ranked #17 on
Autonomous Driving
on CARLA Leaderboard
Learning Instance Segmentation by Interaction
The agent uses its current segmentation model to infer pixels that constitute objects and refines the segmentation model by interacting with these pixels.
Zero-Shot Visual Imitation
In our framework, the role of the expert is only to communicate the goals (i. e., what to imitate) during inference.
Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
Manipulation of deformable objects, such as ropes and cloth, is an important but challenging problem in robotics.
