Search Results for author:
Found 158 papers, 79 papers with code
Effective Fine-Tuning Methods for Cross-lingual Adaptation
In this work, we propose a novel fine-tuning method based on co-training that aims to learn more generalized semantic equivalences as a complementary to multilingual language modeling using the unlabeled data in the target language.
An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD Camera
To enable robust tracking, we embrace both the initial model and the various visual cues into a novel performance capture scheme with hybrid motion optimization and semantic volumetric fusion, which can successfully capture challenging human motions under the monocular setting without pre-scanned detailed template and owns the reinitialization ability to recover from tracking failures and the disappear-reoccur scenarios.
View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness.
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
This work underscores the potential of guided replay with web tutorials as a viable strategy for large-scale GUI agent training, paving the way for more capable and autonomous digital agents.
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Graphical User Interfaces (GUIs) are critical to human-computer interaction, yet automating GUI tasks remains challenging due to the complexity and variability of visual environments.
Ranked #2 on
Natural Language Visual Grounding
on ScreenSpot
IREE Oriented Active RIS-Assisted Green communication System with Outdated CSI
Given the non-convex nature of the problem, we propose an Alternating Optimization Successive Approximation (AOSO) algorithm.
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics.
Ranked #1 on
Text-To-SQL
on Spider 2.0
Attacking Vision-Language Computer Agents via Pop-ups
Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces.
Can Uncertainty Quantification Enable Better Learning-based Index Tuning?
Index tuning is crucial for optimizing database performance by selecting optimal indexes based on workload.
Augmented Intelligence in Smart Intersections: Local Digital Twins-Assisted Hybrid Autonomous Driving
Vehicle-road collaboration is a promising approach for enhancing the safety and efficiency of autonomous driving by extending the intelligence of onboard systems to smart roadside infrastructures.
PNR: Physics-informed Neural Representation for high-resolution LFM reconstruction
Existing approaches often do not adequately address issues such as the loss of high-frequency information due to defocus and sample aberration, resulting in suboptimal performance.
PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion
Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress.
Neural Octahedral Field: Octahedral prior for simultaneous smoothing and sharp edge regularization
Neural implicit representation, the parameterization of distance function as a coordinate neural field, has emerged as a promising lead in tackling surface reconstruction from unoriented point clouds.
Non-Overlapping Placement of Macro Cells based on Reinforcement Learning in Chip Design
Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency.
CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation
Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results.
Rethinking Domain Adaptation and Generalization in the Era of CLIP
In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain.
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
To better benchmark retrieval on such challenging queries, we introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
These tasks, derived from real-world use cases, evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems.
HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models
In this paper, we extend the ability of controllable generative models for a more comprehensive hand mesh recovery task: direct hand mesh generation, inpainting, reconstruction, and fitting in a single framework, which we name as Holistic Hand Mesh Recovery (HHMR).
Ranked #7 on
3D Hand Pose Estimation
on FreiHAND
Roadside Units Assisted Localized Automated Vehicle Maneuvering: An Offline Reinforcement Learning Approach
Traffic intersections present significant challenges for the safe and efficient maneuvering of connected and automated vehicles (CAVs).
Collage: Light-Weight Low-Precision Strategy for LLM Training
Large models training is plagued by the intense compute cost and limited hardware memory.
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity.
MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors
To validate the dataset, we propose an RGBD-P SMPL fitting method and also a monocular-video-based baseline framework, VP-MoCap, for human motion capture.
Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios.
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited.
Yi: Open Foundation Models by 01.AI
The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models.
Ranked #1 on
Chatbot
on AlpacaEval
YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5
Additionally, we have incorporated a global attention mechanism into the backbone network.
Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning
Furthermore, the proposed method achieves superior performance when designing complex or rapidly evolving DFCs, highlighting the substantial potential of RL in circuit design automation.
Smart Mobility Digital Twin Based Automated Vehicle Navigation System: A Proof of Concept
The performance of SMDT is evaluated from two standpoints: (i) the rewards of the proposed navigation system on traffic efficiency and safety and, (ii) the latency and reliability of the SMDT platform.
EVOR: Evolving Retrieval for Code Generation
Recently the retrieval-augmented generation (RAG) has been successfully applied in code generation.
Generative Representational Instruction Tuning
Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss.
Momentum Approximation in Asynchronous Private Federated Learning
Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients.
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerated progress in building digital agents.
Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement Learning
To fill these gaps, a novel contextual meta graph reinforcement learning (Meta-GRL) for a highly generalized multi-stage optimal dispatch policy is proposed.
DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation
In this paper we propose a novel framework DiffPerformer to synthesize high-fidelity and temporally consistent human video.
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Retraining-free is important for LLMs' pruning methods.
Internet of Federated Digital Twins (IoFDT): Connecting Twins Beyond Borders for Society 5.0
The concept of digital twin (DT), which enables the creation of a programmable, digital representation of physical systems, is expected to revolutionize future industries and will lie at the heart of the vision of a future smart society, namely, Society 5. 0, in which high integration between cyber (digital) and physical spaces is exploited to bring economic and societal advancements.
DisControlFace: Adding Disentangled Control to Diffusion Autoencoder for One-shot Explicit Facial Image Editing
We identify the key challenge as the exploration of disentangled conditional control between high-level semantics and explicit parameters (e. g., 3DMM) in the generation process, and accordingly propose a novel diffusion-based editing framework, named DisControlFace.
OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure.
OpenAgents: An Open Platform for Language Agents in the Wild
Language agents show potential in being capable of utilizing natural language for varied and intricate tasks in diverse environments, particularly when built upon large language models (LLMs).
Lemur: Harmonizing Natural Language and Code for Language Agents
We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents.
PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis
This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality.
Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Unlike inverse RL and recent work that uses LLMs to write sparse reward codes or unshaped dense rewards with a constant function across timesteps, Text2Reward produces interpretable, free-form dense reward codes that cover a wide range of tasks, utilize existing packages, and allow iterative refinement with human feedback.
Dynamic Spectrum Mixer for Visual Recognition
Recently, MLP-based vision backbones have achieved promising performance in several visual recognition tasks.
ImmersiveNeRF: Hybrid Radiance Fields for Unbounded Immersive Light Field Reconstruction
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation.
AutoDroid: LLM-powered Task Automation in Android
Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones.
Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?
The capabilities of pretrained language models have opened opportunities to explore new application areas, but applications involving human-human interaction are limited by the fact that most data is protected from public release for privacy reasons.
Fast Segment Anything
In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
Ranked #4 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learning
Therefore, we propose the first data-driven study to detect epileptic waves in a real-world SEEG dataset.
Coneheads: Hierarchy Aware Attention
These networks rely heavily on the dot product attention operator, which computes the similarity between two points by taking their inner product.
Shadow Cones: A Generalized Framework for Partial Order Embeddings
Specifically, we model partial orders as subset relations between shadows formed by a light source and opaque objects in hyperbolic space.
Generating Data for Symbolic Language with Large Language Models
However, such an approach has primarily been applied to natural language tasks and has not yet been explored for symbolic language tasks with complex structured outputs (e. g., semantic parsing and code generation).
Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression
During offline training, a pre-processed signal obtained from the Kalman filter and an ideal microphone signal generated via teacher-forced training strategy are used to train the deep neural network (DNN).
StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video
Results and experiments demonstrate the superiority of our method in terms of image quality, full portrait video generation, and real-time re-animation compared to existing facial reenactment methods.
Super-NeRF: View-consistent Detail Generation for NeRF super-resolution
Given multi-view low-resolution images, Super-NeRF constructs a consistency-controlling super-resolution module to generate view-consistent high-resolution details for NeRF.
Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting
Detailed 3D reconstruction and photo-realistic relighting of digital humans are essential for various applications.
The Seven Worlds and Experiences of the Wireless Metaverse: Challenges and Opportunities
We then articulate how these experiences bring forth interactions between diverse metaverse constituents, namely, a) humans and avatars and b) connected intelligence systems and their digital twins (DTs).
Inpaint Anything: Segment Anything Meets Image Inpainting
We are also very willing to help everyone share and promote new projects based on our Inpaint Anything (IA).
Hi Sheldon! Creating Deep Personalized Characters from TV Shows
To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.
TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge
This paper introduces the Unbeatable Team's submission to the ICASSP 2023 Deep Noise Suppression (DNS) Challenge.
Automated Self-Supervised Learning for Recommendation
This does not generalize across different datasets and downstream recommendation tasks, which is difficult to be adaptive for data augmentation and robust to noise perturbation.
Compositional Exemplars for In-context Learning
The performance of ICL is highly dominated by the quality of the selected in-context examples.
Batch Prompting: Efficient Inference with Large Language Model APIs
We extensively validate the effectiveness of batch prompting on ten datasets across commonsense QA, arithmetic reasoning, and NLI/NLU: batch prompting significantly~(up to 5x with six samples in batch) reduces the LLM (Codex) inference token and time costs while achieving better or comparable performance.
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Our analysis suggests that INSTRUCTOR is robust to changes in instructions, and that instruction finetuning mitigates the challenge of training a single model on diverse datasets.
Realization Scheme for Visual Cryptography with Computer-generated Holograms
This method can expand the application range of visual cryptography and further increase the security of visual cryptography.
Coder Reviewer Reranking for Code Generation
Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions.
Ranked #30 on
Code Generation
on MBPP
Task Residual for Tuning Vision-Language Models
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts.
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas.
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback
To improve the quality of dataset synthesis, we propose a progressive zero-shot dataset generation framework, ProGen, which leverages the feedback from the task-specific model to guide the generation of new training data via in-context examples.
Ranked #3 on
Data-free Knowledge Distillation
on QNLI
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user's intent, that then converses with a text-to-SQL semantic parser to generate new interactions.
Binding Language Models in Symbolic Languages
We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) allows binding a unified API of language model (LM) functionalities to a programming language (e. g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemplar annotations.
Ranked #5 on
Table-based Fact Verification
on TabFact
NL2INTERFACE: Interactive Visualization Interface Generation from Natural Language Queries
We develop NL2INTERFACE to explore the potential of generating usable interactive multi-visualization interfaces from natural language queries.
Selective Annotation Makes Language Models Better Few-Shot Learners
Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time.
FOLIO: Natural Language Reasoning with First-Order Logic
We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations.
MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point
In this paper, we introduce MCTensor, a library based on PyTorch for providing general-purpose and high-precision arithmetic for DL training.
Geometry-aware Single-image Full-body Human Relighting
For the relighting, we introduce a ray tracing-based per-pixel lighting representation that explicitly models high-frequency shadows and propose a learning-based shading refinement module to restore realistic shadows (including hard cast shadows) from the ray-traced shading maps.
Design and Analysis of Robust Resilient Diffusion over Multi-Task Networks Against Byzantine Attacks
This paper studies distributed diffusion adaptation over clustered multi-task networks in the presence of impulsive interferences and Byzantine attacks.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment
In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space.
Compressed Image Quality Assessment
Full-Reference Image Quality Assessment
+1
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications.
GIMO: Gaze-Informed Human Motion Prediction in Context
We perform an extensive study of the benefits of leveraging the eye gaze for ego-centric human motion prediction with various state-of-the-art architectures.
ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling
Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency.
Structured Local Radiance Fields for Human Avatar Modeling
These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field.
FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset
In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc.
Interacting Attention Graph for Single Image Two-Hand Reconstruction
To solve occlusion and interaction challenges of two-hand reconstruction, we introduce two novel attention based modules in each upsampling step of the original GCN.
Ranked #4 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
3D Interacting Hand Pose Estimation
Vocal Bursts Valence Prediction
In-Context Learning for Few-Shot Dialogue State Tracking
In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates.
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Light field disparity estimation is an essential task in computer vision with various applications.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
Ranked #2 on
Data-free Knowledge Distillation
on QNLI
Random Laplacian Features for Learning with Hyperbolic Space
Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been developed.
Understanding Hyperdimensional Computing for Parallel Single-Pass Learning
Using representation theory, we characterize which similarity matrices can be "expressed" by finite group VSA hypervectors, and we show how these VSAs can be constructed.
Mask-based Latent Reconstruction for Reinforcement Learning
For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance.
HDhuman: High-quality Human Novel-view Rendering from Sparse Views
To this end, we propose HDhuman, which uses a human reconstruction network with a pixel-aligned spatial transformer and a rendering network with geometry-guided pixel-wise feature integration to achieve high-quality human reconstruction and rendering.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Ranked #1 on
Task-Oriented Dialogue Systems
on KVRET
HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars
To handle complicated motions (e. g., self-occlusions), we then leverage the encoded information on the UV manifold to construct a 3D volumetric representation based on a dynamic pose-conditioned neural radiance field.
Representing Hyperbolic Space Accurately using Multi-Component Floats
Hyperbolic space is particularly useful for embedding data with hierarchical structure; however, representing hyperbolic space with ordinary floating-point numbers greatly affects the performance due to its \emph{ineluctable} numerical errors.
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
Transformer-based models have achieved state-of-the-art performance on short-input summarization.
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
Existing text-to-SQL research only considers complete questions as the input, but lay-users might strive to formulate a complete question.
An Exploratory Study on Long Dialogue Summarization: What Works and What's Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
SummerTime: Text Summarization Toolkit for Non-experts
We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.
Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras
Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance.
Ranked #2 on
3D Multi-Person Pose Estimation
on Shelf
Logic-Consistency Text Generation from Semantic Parses
Text generation from semantic parses is to generate textual descriptions for formal representation inputs such as logic forms and SQL queries.
End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task
Furthermore, we propose two value filling methods to build the bridge from the existing zero-shot semantic parsers to real-world applications, considering most of the existing parsers ignore the values filling in the synthesized SQL.
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning.
Continuous Control (100k environment steps)
Continuous Control (500k environment steps)
+4
DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering
We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering.
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors
Human volumetric capture is a long-standing topic in computer vision and computer graphics.
DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras
We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed.
INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing.
POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture
By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions.
Local Patch AutoAugment with Multi-Agent Collaboration
We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image.
Nematicity Arising from a Chiral Superconducting Ground State in Magic-Angle Twisted Bilayer Graphene under In-Plane Magnetic Fields
Recent measurements of the resistivity in magic-angle twisted bilayer graphene near the superconducting transition temperature show two-fold anisotropy, or nematicity, when changing the direction of an in-plane magnetic field [Cao \textit{et al.}, Science \textbf{372}, 264 (2021)].
Superconductivity
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e. g., SQL, SPARQL) that can be executed against a structured ontology (e. g. databases, knowledge bases).
Ranked #3 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i. e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations.
Deep Implicit Templates for 3D Shape Representation
Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power.
DeepCloth: Neural Garment Representation for Shape and Style Editing
In this work, we introduce, DeepCloth, a unified framework for garment representation, reconstruction, animation and editing.
Vehicle Reconstruction and Texture Estimation Using Deep Implicit Semantic Template Mapping
We introduce VERTEX, an effective solution to recover 3D shape and intrinsic texture of vehicles from uncalibrated monocular input in real-world street environments.
Spin-Wave Doppler Shift by Magnon Drag in Magnetic Insulators
The Doppler shift of the quasiparticle dispersion by charge currents is responsible for the critical supercurrents in superconductors and instabilities of the magnetic ground state of metallic ferromagnets.
Mesoscale and Nanoscale Physics
Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text-to-SQL
Neural models have achieved significant results on the text-to-SQL task, in which most current work assumes all the input questions are legal and generates a SQL query for any input.
Online Conversation Disentanglement with Pointer Networks
We also introduce a joint-learning objective to better capture contextual information.
Semantic Evaluation for Text-to-SQL with Distilled Test Suites
We propose test suite accuracy to approximate semantic accuracy for Text-to-SQL models.
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data.
Ranked #8 on
Semantic Parsing
on spider
NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image
We propose NormalGAN, a fast adversarial learning-based method to reconstruct the complete and detailed 3D human from a single RGB-D image.
Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions.
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction
To overcome the limitations of regular 3D representations, we propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function.
Ranked #2 on
3D Human Reconstruction
on CAPE
DART: Open-Domain Structured Data Record to Text Generation
Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of structured data and contain nontrivial structures.