Search Results for author:
Found 62 papers, 25 papers with code
BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics
We introduce BCAT, a PDE foundation model designed for autoregressive prediction of solutions to two dimensional fluid dynamics problems.
Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Management
Clinical machine learning deployment across institutions faces significant challenges when patient populations and clinical practices differ substantially.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
Ranked #1 on
Mathematical Reasoning
on AIME24
Automatically Planning Optimal Parallel Strategy for Large Language Models
The number of parameters in large-scale language models based on transformers is gradually increasing, and the scale of computing clusters is also growing.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction
In-Context Operator Networks (ICONs) are models that learn operators across different types of PDEs using a few-shot, in-context approach.
Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization
Synthetic defect data generation is a popular approach for mitigating data challenges.
Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement
However, we have identified two key issues with existing parallel decoding frameworks: (1) decoding heads fail to balance prediction accuracy and the parallelism of execution, and (2) parallel decoding is not a universal solution, as it can bring unnecessary overheads at some challenging decoding steps.
Annotation-Free Curb Detection Leveraging Altitude Difference Image
This module utilizes a deterministic curb detection algorithm to automatically generate a vast quantity of training data.
TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition
In this paper, we propose TSCLIP, a robust fine-tuning approach with the contrastive language-image pre-training (CLIP) model for worldwide cross-regional traffic sign recognition.
FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera
We incorporate a fisheye camera model into the projection and reprojection stages during training to handle image distortions, thereby improving depth estimation accuracy and training stability.
Depth from Coupled Optical Differentiation
It is based on our discovery that per-pixel object distance can be rigorously determined by a coupled pair of optical derivatives of a defocused image using a simple, closed-form relationship.
PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics
We propose PROSE-FD, a zero-shot multimodal PDE foundational model for simultaneous prediction of heterogeneous two-dimensional physical systems related to distinct fluid dynamics settings.
HierLLM: Hierarchical Large Language Model for Question Recommendation
Question recommendation is a task that sequentially recommends questions for students to enhance their learning efficiency.
Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning
For DL training, we deployed the Fire-Flyer 2 with 10, 000 PCIe A100 GPUs, achieved performance approximating the DGX-A100 while reducing costs by half and energy consumption by 40%.
Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey
This paper explores the recent advancements in enhancing Computational Fluid Dynamics (CFD) tasks through Machine Learning (ML) techniques.
WorldScribe: Towards Context-Aware Live Visual Descriptions
In this work, we develop WorldScribe, a system that generates automated live real-world visual descriptions that are customizable and adaptive to users' contexts: (i) WorldScribe's descriptions are tailored to users' intents and prioritized based on semantic relevance.
EditScribe: Non-Visual Image Editing with Natural Language Verification Loops
To address this, we developed EditScribe, a prototype system that makes image editing accessible using natural language verification loops powered by large multimodal models.
Characterizing segregation in blast rock piles a deep-learning approach leveraging aerial image analysis
Blasted rock material serves a critical role in various engineering applications, yet the phenomenon of segregation-where particle sizes vary significantly along the gradient of a quarry pile-presents challenges for optimizing quarry material storage and handling.
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
Given a domain-specific object detection dataset, we first fine-tune a pre-trained diffusion model on both cropped foreground objects and entire images to fit target distributions.
ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval
Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifiers (IDs) based on search queries.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolation
More importantly, we provide three extrapolation studies to demonstrate that PROSE-PDE can generalize physical features through the robust training of multiple operators and that the proposed model can extrapolate to predict PDE solutions whose models or data were unseen during the training.
Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks
This review looks back and analyzes the current state of achievements in the field of 3D lane detection research.
Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models
P2G utilizes the tool-usage potential of MLLMs to employ expert agents for on-the-fly grounding of reasoning into critical visual and textual elements in images, thereby enabling deliberate reasoning through multimodal prompting.
CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation
Curb detection is a crucial function in intelligent driving, essential for determining drivable areas on the road.
Multiple Latent Space Mapping for Compressed Dark Image Enhancement
Since texture details intertwine with compression artifacts in compressed dark images, detail enhancement and blocking artifacts suppression contradict each other in image space.
Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering
Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems.
Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving
Collectively, these contributions lay a robust foundation for the widespread adoption of vision-based 3D perception technologies in autonomous driving applications.
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations.
Text Diffusion with Reinforced Conditioning
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio.
Disentangle Estimation of Causal Effects from Cross-Silo Data
Estimating causal effects among different events is of great importance to critical fields such as drug development.
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability.
Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training
Monocular 3D object detection plays a crucial role in autonomous driving.
PROSE: Predicting Operators and Symbolic Expressions using Multimodal Transformers
Approximating nonlinear differential equations using a neural network provides a robust and efficient tool for various scientific computing tasks, including real-time predictions, inverse problems, optimal controls, and surrogate modeling.
Calibrating LLM-Based Evaluator
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.
Self-Supervised Instance Segmentation by Grasping
Leveraging this insight, we learn a grasp segmentation model to segment the grasped object from before and after grasp images.
Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such can cause critical errors in high-performance applications.
FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving
Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving.
Nonlinear Intensity, Scale and Rotation Invariant Matching for Multimodal Images
We present an effective method for the matching of multimodal images.
Random Feature Models for Learning Interacting Dynamical Systems
Particle dynamics and multi-agent systems provide accurate dynamical models for studying and forecasting the behavior of complex interacting systems.
Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
3D bounding boxes are a widespread intermediate representation in many computer vision applications.
RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement
To annotate road network graphs effectively and efficiently, automatic algorithms for road network graph detection are demanded.
CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation
Due to the use of the DETR-like transformer network, CenterLineDet can handle complicated graph topology, such as lane intersections.
Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation
The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism).
Tackling Long-Tailed Category Distribution Under Domain Shifts
Two new datasets were proposed for this problem, named AWA2-LTS and ImageNet-LTS.
Integrating Dependency Tree Into Self-attention for Sentence Representation
Recent progress on parse tree encoder for sentence representation learning is notable.
RNGDet: Road Network Graph Detection by Transformer in Aerial Images
To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning in this paper.
csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps
To provide a solution to the aforementioned problems, in this letter, we propose a novel system termed csBoundary to automatically detect road boundaries at the city scale for HD map annotation.
Unified Group Fairness on Federated Learning
We validate the advantages of the FMDA-M algorithm with various kinds of distribution shift settings in experiments, and the results show that FMDA-M algorithm outperforms the existing fair FL algorithms on unified group fairness.
Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs.
YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs.
3D Object Detection From Stereo Images
Disparity Estimation
+3
Ground-aware Monocular 3D Object Detection for Autonomous Driving
We further verify the power of the proposed module with a neural network designed for monocular depth prediction.
Ranked #6 on
Monocular 3D Object Detection
on KITTI Cars Hard
Learning geometry-image representation for 3D point cloud generation
We study the problem of generating point clouds of 3D objects.
ATG-PVD: Ticketing Parking Violations on A Drone
In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD).
Difference Attention Based Error Correction LSTM Model for Time Series Prediction
In this paper, we propose a novel model for time series prediction in which difference-attention LSTM model and error-correction LSTM model are respectively employed and combined in a cascade way.
Learning to Drive from Simulation without Real World Labels
Simulation can be a powerful tool for understanding machine learning systems and designing methods to solve real-world problems.
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems.
Hierarchical Reinforcement Learning
reinforcement-learning
+3
Meta-Reinforcement Learning of Structured Exploration Strategies
Exploration is a fundamental challenge in reinforcement learning (RL).
Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures.
Building Program Vector Representations for Deep Learning
In this pioneering paper, we propose the "coding criterion" to build program vector representations, which are the premise of deep learning for program analysis.
