Search Results for author:
Found 37 papers, 21 papers with code
A Sample Efficient Conditional Independence Test in the Presence of Discretization
Motivated by this, this paper introduces a sample-efficient CI test that does not rely on the binarization process.
Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
However, we observe that such geometry-based couplings do not necessarily align with the model's preferred trajectories, making it difficult to learn the vector field induced by these couplings, which prevents the model from learning straight trajectories.
SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training
DONNs leverage light propagation for efficient analog AI and signal processing.
Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space
Experimental results on the Valence-Arousal (VA) Estimation task of the 8th competition on Affective Behavior Analysis in-the-wild (ABAW) demonstrate that the proposed model achieves valence and arousal scores of 0. 5362 (0. 5036) and 0. 4310 (0. 4119) on the validation (test) set, respectively, outperforming the baseline.
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
Traditional autonomous driving systems often struggle to connect high-level reasoning with low-level control, leading to suboptimal and sometimes unsafe behaviors.
Flow: Modularized Agentic Workflow Automation
In this paper, we define workflows as an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by LLM agents through dynamic subtask allocation adjustment based on historical performance and previous AOVs.
SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
On the other hand, directly aligning long captions with images can lead to the retention of entangled details, preventing the model from learning disentangled, atomic concepts -- ultimately limiting its generalization on certain downstream tasks involving short prompts.
Ranked from Within: Ranking Large Multimodal Models for Visual Question Answering Without Labels
As large multimodal models (LMMs) are increasingly deployed across diverse applications, the need for adaptable, real-world model ranking has become paramount.
Multi-Dimensional Reconfigurable, Physically Composable Hybrid Diffractive Optical Neural Network
To overcome this challenge, we introduce, for the first time, a multi-dimensional reconfigurable hybrid diffractive ONN system (MDR-HDONN), a physically composable architecture that unlocks a new degree of freedom and unprecedented versatility in DONNs.
Enhanced channel estimation for near-field IRS-aided multi-user MIMO system via a large deep residual network
In this paper, the channel estimation (CE) of intelligent reflecting surface-aided near-field (NF) multi-user communication is investigated.
MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting
A recent model, Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer, offering comparable performance with higher throughput and linear complexity related to sequence length.
A Conditional Independence Test in the Presence of Discretization
Applying existing test methods to the observations of $X_1$, $\tilde{X}_2$ and $X_3$ can lead to a false conclusion about the underlying conditional independence of variables $X_1$, $X_2$ and $X_3$.
MD-Dose: A diffusion model based on the Mamba for radiation dose prediction
To tackle these challenges, we introduce a novel diffusion model, MD-Dose, based on the Mamba architecture for predicting radiation therapy dose distribution in thoracic cancer patients.
BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification
Mainstream data augmentation (DA) methods are usually applied at the image level.
SP-DiffDose: A Conditional Diffusion Model for Radiation Dose Prediction Based on Multi-Scale Fusion of Anatomical Structures, Guided by SwinTransformer and Projector
To address these limitations, we propose a dose prediction diffusion model based on SwinTransformer and a projector, SP-DiffDose.
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation
First, FaceEncoder is used to obtain latent code by extracting features from the visual face information taken from the video source containing the face frame. Then, HyperConv, which weighting parameters are updated by HyperNet with the audio features as input, will modify the latent code to synchronize the lip movement with the audio.
Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving
In autonomous driving tasks, scene understanding is the first step towards predicting the future behavior of the surrounding traffic participants.
Energy-Guided Diffusion Model for CBCT-to-CT Synthesis
Cone Beam CT (CBCT) plays a crucial role in Adaptive Radiation Therapy (ART) by accurately providing radiation treatment when organ anatomy changes occur.
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels.
Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control
In this paper, Policy Constraint Q-Learning (PCQL), a data-driven reinforcement learning algorithm for solving the problem of learning anesthesia strategies on real clinical datasets, is proposed.
Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation
In this paper, we propose EnCo, a simple but efficient way to maintain the content by constraining the representational similarity in the latent space of patch-level features from the same stage of the \textbf{En}coder and de\textbf{Co}der of the generator.
A Many-ported and Shared Memory Architecture for High-Performance ADAS SoCs
A domain specific memory architecture is essential to achieve the above goals.
Multi-scale Cooperative Multimodal Transformers for Multimodal Sentiment Analysis in Videos
On the whole, the "multi-scale" mechanism is capable of exploiting the different levels of semantic information of each modality which are used for fine-grained crossmodal interactions.
Emulating Quantum Dynamics with Neural Networks via Knowledge Distillation
We focus on the question of how the emulator learns the rules of quantum dynamics from the curriculum of simple training examples and to which extent it can generalize the acquired knowledge to solve more challenging cases.
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels.
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?
Existing methods for learning with noisy labels can be generally divided into two categories: (1) sample selection and label correction based on the memorization effect of neural networks; (2) loss correction with the transition matrix.
Instance-dependent Label-noise Learning under a Structural Causal Model
In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier.
Coupling Intent and Action for Pedestrian Crossing Behavior Prediction
In this work, we follow the neuroscience and psychological literature to define pedestrian crossing behavior as a combination of an unobserved inner will (a probabilistic representation of binary intent of crossing vs. not crossing) and a set of multi-class actions (e. g., walking, standing, etc.).
Smart Black Box 2.0: Efficient High-bandwidth Driving Data Collection based on Video Anomalies
An updated SBB pipeline is proposed for the real-time capture of driving video data.
Markov chain Monte Carlo methods for hierarchical clustering of dynamic causal models
Specifically, we introduce a class of proposal distributions which aims to capture the interdependencies between the parameters of the clustering and subject-wise generative models and helps to reduce random walk behaviour of the MCMC scheme.
Unsupervised Regionalization of Particle-resolved Aerosol Mixing State Indices on the Global Scale
Here we developed a simple but effective unsupervised learning approach to regionalize predictions of global aerosol mixing state indices.
BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation
BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional decoder to improve longer-term trajectory prediction accuracy.
Ranked #2 on
Trajectory Prediction
on JAAD
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA.
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Hitherto, the distributional-assumption-free CPE methods rely on a critical assumption that the support of the positive data distribution cannot be contained in the support of the negative data distribution.
Unsupervised Traffic Accident Detection in First-Person Videos
Recognizing abnormal events such as traffic violations and accidents in natural driving scenes is essential for successful autonomous driving and advanced driver assistance systems.
Ranked #1 on
Traffic Accident Detection
on A3D
Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems
Predicting the future location of vehicles is essential for safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous driving.
