Search Results for author:
Found 65 papers, 29 papers with code
Continual Pre-Training is (not) What You Need in Domain Adaption
The recent advances in Legal Large Language Models (LLMs) have transformed the landscape of legal research and practice by automating tasks, enhancing research precision, and supporting complex decision-making processes.
Transforming Future Data Center Operations and Management via Physical AI
Our results demonstrate its superior performance over traditional time-consuming Computational Fluid Dynamics/Heat Transfer (CFD/HT) simulation, with a median absolute temperature prediction error of 0. 18 {\deg}C. This emerging approach would open doors to several potential research directions for advancing Physical AI in future DC operations.
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving
In this paper, we introduce M3Net, a novel multimodal and multi-task network that simultaneously tackles detection, segmentation, and 3D occupancy prediction for autonomous driving and achieves superior performance than single task model.
Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds
Quadrupeds have gained rapid advancement in their capability of traversing across complex terrains.
XAI4Extremes: An interpretable machine learning framework for understanding extreme-weather precursors under climate change
Extreme weather events are increasing in frequency and intensity due to climate change.
CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints
In this work, we find that water vapor oversaturation during condensation is a key factor compromising the stability of hybrid models.
LogiDynamics: Unraveling the Dynamics of Logical Inference in Large Language Model Reasoning
Modern large language models (LLMs) employ various forms of logical inference, both implicitly and explicitly, when addressing reasoning tasks.
Feature-based Graph Attention Networks Improve Online Continual Learning
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks.
Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning
Additionally, most AL methods seldom address multimodal data, highlighting a research gap in this field.
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has become a crucial method for acquiring 3D assets.
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
Single-view 3D reconstruction methods like Triplane Gaussian Splatting (TGS) have enabled high-quality 3D model generation from just a single image input within seconds.
On-Device LLMs for SMEs: Challenges and Opportunities
This paper presents a systematic review of the infrastructure requirements for deploying Large Language Models (LLMs) on-device within the context of small and medium-sized enterprises (SMEs), focusing on both hardware and software perspectives.
A Multimodal Vision Foundation Model for Clinical Dermatology
Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities.
Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
Debate is the process of exchanging viewpoints or convincing others on a particular issue.
GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields
While approaches like CopyRNeRF have been introduced to embed binary messages into NeRF models as digital signatures for copyright protection, the process of recolorization can remove these binary messages.
TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
However, this task faces limitations due to the scarcity of high-quality clinical datasets and the complex relationship between symptoms and herbs.
Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model
Neural Radiance Fields (NeRFs) have become a key method for 3D scene representation.
Nutrition Estimation for Dietary Management: A Transformer Approach with Depth Sensing
In this paper, we propose NuNet, a transformer-based network designed for nutrition estimation that utilizes both RGB and depth information from food images.
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
This framework integrates the policy evaluation steps and the policy improvement steps, resulting in a single objective training process.
Ranked #1 on
Omniverse Isaac Gym
on FrankaCabinet
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study.
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels.
Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference.
AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval
Automatic radiology report generation using deep learning models has been recently explored and found promising.
Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation
Next we extract background context from the query image to modulate the support foreground feature thus eliminating the foreground feature misalignment caused by the different backgrounds.
TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining
A main goal of Argument Mining (AM) is to analyze an author's stance.
Self-Consistent Narrative Prompts on Abductive Natural Language Inference
However, the inter-sentential coherence and the model consistency have not been well exploited in the previous works on this task.
Learning Gabor Texture Features for Fine-Grained Recognition
We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information.
CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
Neural Radiance Fields (NeRF) have the potential to be a major representation of media.
Towards Balanced Active Learning for Multimodal Classification
Our studies demonstrate that the proposed method achieves more balanced multimodal learning by avoiding greedy sample selection from the dominant modality.
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots.
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning
In fully cooperative multi-agent reinforcement learning (MARL) settings, environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of other agents.
Ranked #1 on
SMAC
on SMAC 26m_vs_30m
COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective
This paper proposes a new task to detect commonsense causation between two events in an event sequence (i. e., context), called contextualized commonsense causal reasoning.
Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport
In contrast to existing scoring functions motivated by local comparison or global transport, this work investigates the local and global trade-off with unbalanced optimal transport theory.
DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition
Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to recognize the discourse relations between the arguments with the absence of discourse connectives.
Continual Semantic Segmentation with Automatic Memory Sample Selection
Continual Semantic Segmentation (CSS) extends static semantic segmentation by incrementally introducing new classes for training.
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
We first propose a TRi-frame Optical Flow (TROF) module that estimates bi-directional optical flows for the center frame in a three-frame manner.
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance.
Logical Message Passing Networks with One-hop Inference on Atomic Formulas
On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning for complex query answering.
MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs
The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts.
Inductive Attention for Video Action Anticipation
Consequently, existing solutions based on the action recognition models are only suboptimal.
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i. e., subnet).
Ranked #26 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform
However, the performance of the hyperbolic KG embedding models for non-transitive relations is still unpromising, while the complex hyperbolic embeddings do not deal with multi-relations.
CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation
Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists.
PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population
We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from.
SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller
In this paper, we propose a new task of sub-event generation for an unseen process to evaluate the understanding of the coherence of sub-event actions and objects.
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
In this study, we propose a simple yet effective framework for video restoration.
Ranked #2 on
Deblurring
on GoPro
(using extra training data)
NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022
In this report, we describe the technical details of our submission for the EPIC-Kitchen-100 action anticipation challenge.
Unified Recurrence Modeling for Video Action Anticipation
To this end, we propose a unified recurrence modeling for video action anticipation via message passing framework.
Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning
It has been shown that an SSL pretraining model can achieve excellent performance in various downstream tasks of speech processing.
Self-Supervised Video Representation Learning by Video Incoherence Detection
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning.
Aligning Correlation Information for Domain Adaptation in Action Recognition
Yet correlation features of the same action would differ across domains due to domain shift.
Mathematical Vocoder Algorithm : Modified Spectral Inversion for Efficient Neural Speech Synthesis
The proposed method is expected to adapt for researching on neural network models capable of synthesizing speech at the studio recording level.
Effective Action Recognition with Embedded Key Point Shifts
Temporal feature extraction is an essential technique in video-based action recognition.
PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition
Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83. 09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.
ARID: A New Dataset for Recognizing Action in the Dark
We bridge the gap of the lack of data for this task by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset.
Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition
Temporal feature extraction is an important issue in video-based action recognition.
Dependently Typed Knowledge Graphs
Reasoning over knowledge graphs is traditionally built upon a hierarchy of languages in the Semantic Web Stack.
Understanding Top-k Sparsification in Distributed Deep Learning
Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes the new system bottleneck.
Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention
Secondly, in CT scans, the lesions are often indistinguishable from the background since the lesion and non-lesion areas may have very similar appearances.
Secure Deep Learning Engineering: A Software Quality Assurance Perspective
Over the past decades, deep learning (DL) systems have achieved tremendous success and gained great popularity in various applications, such as intelligent machines, image processing, speech processing, and medical diagnostics.
DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving.
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint).
CRNN: A Joint Neural Network for Redundancy Detection
We observe that MGU achieves the optimal runtime and comparable performance against GRU and LSTM.
Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images.
