Search Results for author:
Found 426 papers, 167 papers with code
PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting
In this work, we propose Patient and Confident Early Exiting BERT (PCEE-BERT), an off-the-shelf sample-dependent early exiting method that can work with different PLMs and can also work along with popular model compression methods.
Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link Prediction
Existing embedding methods are mostly built on Euclidean space, which are difficult to handle hierarchical structures.
A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model
In this paper, we focus on the problem of exactly recovering the communities in a binary symmetric SBM, where a graph of $n$ vertices is partitioned into two equal-sized communities and the vertices are connected with probability $p = \alpha\log(n)/n$ within communities and $q = \beta\log(n)/n$ across communities for some $\alpha>\beta>0$.
Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection
However, prior ICL-based Transformer models rely on deep architectures with many layers to achieve satisfactory performance, resulting in substantial storage and computational costs.
A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization
In this work, we aim to fill this gap by conducting a comprehensive study of the loss landscape of the regularized DMF problem.
Analyzing the Impact of Strategic Bidding on the Reserve Capacity via a Bi-Level Model
The growing integration of renewable energy sources necessitates adequate reserve capacity to maintain power balance.
Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning
Specifically, inspired by large language models (LLMs), we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space through tokenization and LLM processing, enabling zero-shot prediction across different hardware platforms for the first time.
SeedEdit 3.0: Fast and High-Quality Generative Image Editing
We introduce SeedEdit 3. 0, in companion with our T2I model Seedream 3. 0, which significantly improves over our previous SeedEdit versions in both aspects of edit instruction following and image content (e. g., ID/IP) preservation on real image inputs.
MiMo-VL Technical Report
We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning.
ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
To address this gap, we introduce ByteMorph, a comprehensive framework for instruction-based image editing with an emphasis on non-rigid motions.
Understanding Generalization in Diffusion Models via Probability Flow Distance
Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality samples that generalize beyond the training data.
Experimental robustness benchmark of quantum neural network on a superconducting quantum processor
Our benchmarking framework features an efficient adversarial attack algorithm designed for QNNs, enabling quantitative characterization of adversarial robustness and robustness bounds.
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
To tackle this, we model the sequential editing as a constrained stochastic programming.
Reward Is Enough: LLMs Are In-Context Reinforcement Learners
At the next round, we prompt the LLM again with the same task and a context consisting of all previous responses and rewards.
X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System
To fill this gap, we introduce X-WebAgentBench, a novel multilingual agent benchmark in an interactive web environment, which evaluates the planning and interaction performance of language agents across multiple languages, thereby contributing to the advancement of global agent intelligence.
A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
Instruction following evaluates large language models (LLMs) on their ability to generate outputs that adhere to user-defined constraints.
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages.
Drug classification based on X-ray spectroscopy combined with machine learning
X-ray absorption spectroscopy, a non-destructive detection technique, offers advantages such as ease of operation, penetrative observation, and strong substance differentiation capabilities, making it well-suited for application in the field of drug detection and identification.
RayZer: A Self-supervised Large View Synthesis Model
The emerging 3D awareness of RayZer is attributed to two key factors.
Cross-Frequency Collaborative Training Network and Dataset for Semi-supervised First Molar Root Canal Segmentation
Additionally, to alleviate the workload of manual annotation for dentists and fully leverage the unlabeled data, we designed a Cross-Frequency Collaborative training semi-supervised learning (SSL) Network called CFC-Net.
Channel-Adaptive Robust Resource Allocation for Highly Reliable IRS-Assisted V2X Communications
We formulate a joint optimization problem for vehicular transmit power, Multi-User Detection (MUD) matrices, V2V link spectrum reuse, and IRS reflection coefficients in IRS-aided V2X communication with imperfect CSI.
Seedream 3.0 Technical Report
At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework.
SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model
Extensive experiments on four benchmarks demonstrate that SlowFastVAD effectively combines the strengths of both fast and slow detectors, and achieves remarkable detection accuracy and interpretability with significantly reduced computational overhead, making it well-suited for real-world VAD applications with high reliability requirements.
A Survey of Scaling in Large Language Model Reasoning
The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration.
An Overview of Low-Rank Structures in the Training and Adaptation of Large Models
In this paper, we present a comprehensive review of recent advances in exploiting low-rank structures for deep learning and shed light on their mathematical foundations.
A Shared Low-Rank Adaptation Approach to Personalized RLHF
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models.
MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning
Compared to single-turn dialogue, multi-turn dialogue involving multiple images better aligns with the needs of real-world human-AI interactions.
Unlocking Generalization Power in LiDAR Point Cloud Registration
In real-world environments, a LiDAR point cloud registration method with robust generalization capabilities (across varying distances and datasets) is crucial for ensuring safety in autonomous driving and other LiDAR-based applications.
Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion
Generative models are widely used in visual content creation.
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
This survey seeks to fill this gap by offering a unified perspective on Long CoT.
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
To address these limitations, we present Seedream 2. 0, a native Chinese-English bilingual image generation foundation model that excels across diverse dimensions, which adeptly manages text prompt in both Chinese and English, supporting bilingual image generation and text rendering.
SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks
To address this issue, previous methods attempt to reduce the differences between viewpoints by critical attributes and decoupling the viewpoints.
ColorDynamic: Generalizable, Scalable, Real-time, End-to-end Local Planner for Unstructured and Dynamic Environments
Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments.
MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue
To fill this gap, we propose the MIND (Multi-agent INner Dialogue), a novel paradigm that provides more immersive psychological healing environments.
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
To address fine-grained compositional REC, we propose novel methods based on a Specialist-MLLM collaboration framework, leveraging the complementary strengths of them: Specialist Models handle simpler tasks efficiently, while MLLMs are better suited for complex reasoning.
Brain-inspired analogical mixture prototypes for few-shot class-incremental learning
Inspired by the brain's mechanisms for categorization and analogical learning, we propose a novel approach called Brain-inspired Analogical Mixture Prototypes (BAMP).
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Detecting Long QT Syndrome and First-Degree Atrioventricular Block using Single-Lead AI-ECG: A Multi-Center Real-World Study
Home-based single-lead AI-ECG devices have enabled continuous, real-world cardiac monitoring.
Constructing a Norm for Children's Scientific Drawing: Distribution Features Based on Semantic Similarity of Large Language Models
The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1.
Qwen2.5-VL Technical Report
We introduce Qwen2. 5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities.
Ranked #2 on
Visual Question Answering (VQA)
on VLM2-Bench
Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks
The optimization foundations of deep linear networks have received significant attention lately.
SeWA: Selective Weight Average via Probabilistic Masking
Weight averaging has become a standard technique for enhancing model performance.
Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities.
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD).
GP-GS: Gaussian Processes for Enhanced Gaussian Splatting
3D Gaussian Splatting has emerged as an efficient photorealistic novel view synthesis method.
Analyzing the Role of the DSO in Electricity Trading of VPPs via a Stackelberg Game Model
In order to study the role of DSO as a stakeholder, a Stackelberg game is represented via a bi-level model: the DSO maximizes profits at the upper level, while the VPPs minimize operating costs at the lower level.
SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild
), the text in natural scene images needs to meet the following four key criteria: (1) Fidelity: the generated text should appear as realistic as a photograph and be completely accurate, with no errors in any of the strokes.
A New Underdetermined Framework for Sparse Estimation of Fault Location for Transmission Lines Using Limited Current Measurements
This letter proposes an alternative underdetermined framework for fault location that utilizes current measurements along with the branch-bus matrix, providing another option besides the traditional voltage-based methods.
Understanding How Nonlinear Layers Create Linearly Separable Features for Low-Dimensional Data
In this work, we address this gap by examining the linear separation capabilities of shallow nonlinear networks.
Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
Large Vision-Language Models (LVLMs) have obtained impressive performance in visual content understanding and multi-modal reasoning.
Dual Diffusion for Unified Image Generation and Understanding
Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models.
LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context
While Large Language Models (LLMs) have demonstrated remarkable capabilities in scientific tasks, existing evaluation frameworks primarily assess their performance using rich contextual inputs, overlooking their ability to generate novel ideas from minimal information.
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with external environments, a critical step toward generalized AI.
Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
Models such as Contrastive Language-Image Pretraining (CLIP) are designed to bridge different modalities, such as images and text, by learning a shared representation space through contrastive learning.
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models
Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational cost poses a significant barrier to wider application.
Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud
Specializing LLMs in various domain-specific tasks has emerged as a critical step towards achieving high performance.
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy
The current landscape lacks a comprehensive benchmark to effectively measure the literate capabilities of LMMs.
Sustainable Self-evolution Adversarial Training
With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security.
Multi-Functional RIS Integrated Sensing and Communications for 6G Networks
We propose a MF-RIS-enabled multi-user and multi-target ISAC system, and formulate an optimization problem to maximize the signal-to-interference-plus-noise ratio (SINR) of sensing targets.
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities.
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation.
A Unified Analysis for Finite Weight Averaging
In this work, we first generalize SGD and LAWA as Finite Weight Averaging (FWA) and explain their advantages compared to SGD from the perspective of optimization and generalization.
Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution
In this work, we emphasize the infrared spectral distribution fidelity and propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion
Recent advancements in text-to-3D generation, building on the success of high-performance text-to-image generative models, have made it possible to create imaginative and richly textured 3D objects from textual descriptions.
MDHP-Net: Detecting an Emerging Time-exciting Threat in IVN
We systematically analyze the characteristics of the threat: dynamism, time-exciting impact, and low prior knowledge dependency.
MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation
In our experiments, we demonstrate that MBA-SLAM surpasses previous state-of-the-art methods in both camera localization and map reconstruction, showcasing superior performance across a range of datasets, including synthetic and real datasets featuring sharp images as well as those affected by motion blur, highlighting the versatility and robustness of our approach.
World Models: The Safety Perspective
With the proliferation of the Large Language Model (LLM), the concept of World Models (WM) has recently attracted a great deal of attention in the AI research community, especially in the context of AI agents.
SeedEdit: Align Image Re-Generation to Image Editing
We introduce SeedEdit, a diffusion model that is able to revise a given image with any text prompt.
Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation
Existing smart contract vulnerability detection methods face three main issues: (1) Insufficient quality of datasets, lacking detailed explanations and precise vulnerability locations.
Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification
By leveraging this shared textual space as an anchor, we can prompt the ReID model to embed images from various domains into a unified semantic space, thereby alleviating catastrophic forgetting caused by domain shifts.
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain.
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix.
Two Birds With One Stone: Enhancing Communication and Sensing via Multi-Functional RIS
Furthermore, we present two schemes that utilize MF-RISs to enhance the performance of integrated sensing and communication (ISAC).
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
To address these challenges, we propose Wrong-of-Thought (WoT), which includes two core modules: (1) Multi-Perspective Verification: A multi-perspective verification method for accurately refining the reasoning process and result, and (2) Wrong Information Utilization: Utilizing wrong information to alert LLMs and reduce the probability of LLMs making same mistakes.
60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task.
FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension
Referring Expression Comprehension (REC) is a crucial cross-modal task that objectively evaluates the capabilities of language understanding, image comprehension, and language-to-image grounding.
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing.
Ranked #3 on
Temporal Relation Extraction
on Vinoground
Natural Language Visual Grounding
Temporal Relation Extraction
+2
VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer
Text recognition is an inherent integration of vision and language, encompassing the visual texture in stroke patterns and the semantic context among the character sequences.
VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding
In particular, we propose to incorporate different views of a 3D shape into a permutation-invariant set, referred to as \emph{View Set}, which removes rigid relation assumptions and facilitates adequate information exchange and fusion among views.
MCDGLN: Masked Connection-based Dynamic Graph Learning Network for Autism Spectrum Disorder
We then employ a specialized weighted edge aggregation (WEA) module, which uses the cross convolution with channel-wise element-wise convolutional kernel, to integrate dynamic functional connectivity and to isolating task-relevant connections.
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Knowledge representation has been a central aim of AI since its inception.
Deep Learning for Video Anomaly Detection: A Review
Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos.
Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance
To achieve our goal, we propose a novel subgoal guidance learning strategy.
Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing
In this work, we improve the understanding of their semantic spaces from intriguing observations: among a certain range of noise levels, (1) the learned posterior mean predictor (PMP) in the diffusion model is locally linear, and (2) the singular vectors of its Jacobian lie in low-dimensional semantic subspaces.
Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering
Remarkably, these models can achieve this even with a small number of training samples despite a large image dimension, circumventing the curse of dimensionality.
Platypus: A Generalized Specialist Model for Reading Text in Various Forms
Recently, generalist models (such as GPT-4V), trained on tremendous data in a unified way, have shown enormous potential in reading text in various scenarios, but with the drawbacks of limited accuracy and low efficiency.
Sequential-Scanning Dual-Energy CT Imaging Using High Temporal Resolution Image Reconstruction and Error-Compensated Material Basis Image Generation
As existing material basis image reconstruction approaches assume that the data sets acquired at two tube potentials are temporally consistent, the violation of this assumption results in inaccurate quantification of material concentration.
Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision Fusion
Based on this observation, we introduce the Collaborative Decision Making (CDM) module, which fuses the multiple classifier heads to enhance the inference performance of adaptive deep networks.
Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts
Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension.
Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process
In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances.
A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap
On one hand, considering the crucial role of human-object pairs information in HOI tasks, the feature alignment module aligns the human-object pairs by aggregating instance information.
Diffusion Models as Optimizers for Efficient Planning in Offline RL
To evaluate the effectiveness and efficiency of the Trajectory Diffuser, we conduct experiments on the D4RL benchmarks.
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI.
Visual Text Generation in the Wild
However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (e. g., text detection and recognition).
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #3 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Visual Prompt Selection for In-Context Learning Segmentation
As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level.
Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification
The main challenge is how to transfer the unstructured semantic space in PLMs to the downstream domain hierarchy.
DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects
Finally, both the refined feature embeddings and the predicted positions are integrated to enhance the object association.
Ranked #1 on
Multi-Object Tracking
on VisDrone2019
CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model
This paper introduces Camera-free Diffusion (CamFreeDiff) model for 360-degree image outpainting from a single camera-free image and text description.
Fast and Continual Knowledge Graph Embedding via Incremental LoRA
To address this issue, we propose a fast CKGE framework (\model), incorporating an incremental low-rank adapter (\mec) mechanism to efficiently acquire new knowledge while preserving old knowledge.
Quantum Dynamics of Machine Learning
This equation reformulates the iterative process of machine learning into a time-dependent partial differential equation with a clear mathematical structure, offering a theoretical framework for investigating machine learning iterations through quantum and mathematical theories.
CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models
To address these limitations, we collect a variety of datasets designed for the bias evaluation of LLMs, and further propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream
Our method can jointly learn both the implicit neural scene representation and recover the camera motion by minimizing the differences between the synthesized data and the real measurements without pre-computed camera poses from COLMAP.
LLM Granularity for On-the-Fly Robot Control
Assistive robots have attracted significant attention due to their potential to enhance the quality of life for vulnerable individuals like the elderly.
Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning
In this model, we have designed a series of modality-specific prompts, which could enable our model to adapt to and make use of the specific information inherent in different modality inputs, thereby reducing the interference caused by the modality gap and achieving better identification.
Autoregressive Pretraining with Mamba in Vision
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks.
Symmetric Matrix Completion with ReLU Sampling
We study the problem of symmetric positive semi-definite low-rank matrix completion (MC) with deterministic entry-dependent sampling.
Visual Prompt Tuning in Null Space for Continual Learning
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models.
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
In practice, we demonstrate the effectiveness of this approach for deep low-rank matrix completion as well as fine-tuning language models.
A Global Geometric Analysis of Maximal Coding Rate Reduction
The maximal coding rate reduction (MCR$^2$) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in the derivation of fully explainable and highly effective deep network architectures.
MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors
In this paper, we propose MoDGS, a new pipeline to render novel views of dy namic scenes from a casually captured monocular video.
A Full-duplex Speech Dialogue Scheme Based On Large Language Models
It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function module, and the concept of a simple finite state machine (called neural FSM) with two states.
RaFe: Ranking Feedback Improves Query Rewriting for RAG
As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA.
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
In WISE, we design a dual parametric memory scheme, which consists of the main memory for the pretrained knowledge and a side memory for the edited knowledge.
Multi-Objective Optimization-Based Waveform Design for Multi-User and Multi-Target MIMO-ISAC Systems
In this paper, we investigate the waveform design problem in a downlink multi-user and multi-target ISAC system under different C&S performance preferences.
Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning
In addition, by incorporating curriculum planning, our approach systematically escalates the difficulty levels of tasks, progressively enhancing the student LLM's capabilities.
C3L: Content Correlated Vision-Language Instruction Tuning Data Generation via Contrastive Learning
Vision-Language Instruction Tuning (VLIT) is a critical training phase for Large Vision-Language Models (LVLMs).
Learning Social Graph for Inactive User Recommendation
In this paper, we propose a novel social recommendation method called LSIR (\textbf{L}earning \textbf{S}ocial Graph for \textbf{I}nactive User \textbf{R}ecommendation) that learns an optimal social graph structure for social recommendation, especially for inactive users.
Towards Continual Knowledge Graph Embedding via Incremental Distillation
On the one hand, existing methods usually learn new triples in a random order, destroying the inner structure of new KGs.
Depth Priors in Removal Neural Radiance Fields
This paper proposes a new pipeline that leverages SpinNeRF and monocular depth estimation models like ZoeDepth to enhance NeRF's performance in complex object removal with improved efficiency.
Dual-Modal Prompting for Sketch-Based Image Retrieval
In this study, we aim to tackle two major challenges of this task simultaneously: i) zero-shot, dealing with unseen categories, and ii) fine-grained, referring to intra-category instance-level retrieval.
Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations.
Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors
To this end, we introduce \textsc{Micre} (\textbf{M}eta \textbf{I}n-\textbf{C}ontext learning of LLMs for \textbf{R}elation \textbf{E}xtraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i. e., learning to learn in context for RE).
Multi-view Image Prompted Multi-view Diffusion for Improved 3D Generation
Using image as prompts for 3D generation demonstrate particularly strong performances compared to using text prompts alone, for images provide a more intuitive guidance for the 3D generation process.
Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion
Meanwhile, a network, dubbed as Masked ControlNet, is designed to utilize these object masks for object generation in the misaligned visual control region.
CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences
Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e. g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models.
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200, 000 edits.
COCONut: Modernizing COCO Segmentation
By enhancing the annotation quality and expanding the dataset to encompass 383K images with more than 5. 18M panoptic masks, we introduce COCONut, the COCO Next Universal segmenTation dataset.
Self-Explainable Affordance Learning with Embodied Caption
In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks.
Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.
BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
In this paper, we introduce a novel approach, named BAD-Gaussians (Bundle Adjusted Deblur Gaussian Splatting), which leverages explicit Gaussian representation and handles severe motion-blurred images with inaccurate camera poses to achieve high-quality scene reconstruction.
CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset.
Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning
Aligning these distributions between corresponding regions from different tasks imparts higher flexibility and capacity to capture intra-region structures, accommodating a broader range of tasks.
SAM-Lightening: A Lightweight Segment Anything Model with Dilated Flash Attention to Achieve 30 times Acceleration
Moreover, it takes only 244MB memory, which is 3. 5\% of the vanilla SAM.
Dcl-Net: Dual Contrastive Learning Network for Semi-Supervised Multi-Organ Segmentation
Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation .
Vision-Language Navigation with Embodied Intelligence: A Survey
As a long-term vision in the field of artificial intelligence, the core goal of embodied intelligence is to improve the perception, understanding, and interaction capabilities of agents and the environment.
Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations.
GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks.
TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation
TransGPT-MM is finetuned on a multi-modal Transportation dataset (MTD) that we manually collected from three areas of the transportation domain: driving tests, traffic signs, and landmarks.
Image Fusion via Vision-Language Model
Therefore, we introduce a novel fusion paradigm named image Fusion via vIsion-Language Model (FILM), for the first time, utilizing explicit textual information from source images to guide the fusion process.
Traffic Flow and Speed Monitoring Based On Optical Fiber Distributed Acoustic Sensor
In the realm of intelligent transportation systems, accurate and reliable traffic monitoring is crucial.
A Comprehensive Study of Knowledge Editing for Large Language Models
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on
knowledge editing
on zsRE
(using extra training data)
LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics
This research focuses on how Large Language Models (LLMs) can help with (path) planning for mobile embodied agents such as robots, in a human-in-the-loop and interactive manner.
ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
We introduce "ImageDream," an innovative image-prompt, multi-view diffusion model for 3D object generation.
Matching Weak Informative Ontologies
In this paper, these ontologies are named as weak informative ontologies (WIOs) and it is challenging for existing methods to matching WIOs.
Continual Referring Expression Comprehension via Dual Modular Memorization
In this paper, we propose Continual Referring Expression Comprehension (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks.
Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval
Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i. e., the same sub-category labels) highest based on the fine-grained details in the query.
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1. 3 seconds on a single A100 GPU.
FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models
In pursuit of this goal, various benchmarks have been constructed to evaluate the instruction-following capacity of these models.
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion.
Open-Vocabulary Video Anomaly Detection
Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task.
SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects
Current unsupervised models struggle to strike a balance between detecting texture and object defects, lacking the capacity to discern latent representations and intricate features.
Ranked #86 on
Anomaly Detection
on MVTec AD
GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps
Detecting unusual patterns in graph data is a crucial task in data mining.
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.
PERF: Panoramic Neural Radiance Field from a Single Panorama
In this paper, we present PERF, a 360-degree novel view synthesis framework that trains a panoramic neural radiance field from a single panorama.
Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction.
Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing
Consequently, effectively adapting large pre-trained models to downstream tasks in an efficient manner has become a prominent research area.
Generalized Neural Collapse for a Large Number of Classes
However, most of the existing empirical and theoretical studies in neural collapse focus on the case that the number of classes is small relative to the dimension of the feature space.
The Emergence of Reproducibility and Generalizability in Diffusion Models
In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.
Revisiting Large Language Models as Zero-shot Relation Extractors
On the one hand, we analyze the drawbacks of existing RE prompts and attempt to incorporate recent prompt techniques such as chain-of-thought (CoT) to improve zero-shot RE.
Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions.
Human-centric Behavior Description in Videos: New Benchmark and Model
To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7, 820 individuals.
USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
USB-NeRF is able to correct rolling shutter distortions and recover accurate camera motion trajectory simultaneously under the framework of NeRF, by modeling the physical image formation process of a RS camera.
Selective Feature Adapter for Dense Vision Transformers
Specifically, SFA consists of external adapters and internal adapters which are sequentially operated over a transformer model.
MMPI: a Flexible Radiance Field Representation by Multiple Multi-plane Images Blending
In this paper, we explore the potential of MPI and show that MPI can synthesize high-quality novel views of complex scenes with diverse camera distributions and view directions, which are not only limited to simple forward-facing scenes.
Qwen Technical Report
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans.
Ranked #3 on
Multi-Label Text Classification
on CC3M-TagMask
Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer
Despite advancements of end-to-end (E2E) models in speech recognition, named entity recognition (NER) is still challenging but critical for semantic understanding.
S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning
VQA Natural Language Explanation (VQA-NLE) task aims to explain the decision-making process of VQA models in natural language.
MVDream: Multi-view Diffusion for 3D Generation
We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt.
TouchStone: Evaluating Vision-Language Models by Language Models
Large vision-language models (LVLMs) have recently witnessed rapid advancements, exhibiting a remarkable capacity for perceiving, understanding, and processing visual information by connecting visual receptor with large language models (LLMs).
LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition
The diversity in length constitutes a significant characteristic of text.
Ground-to-Aerial Person Search: Benchmark Dataset and Approach
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31, 770 images of 260, 559 annotated bounding boxes for 2, 644 identities appearing in both of the UAVs and ground surveillance cameras.
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images.
Ranked #2 on
Spatial Reasoning
on EmbSpatial-Bench
VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection
With the benefit of dual branch, VadCLIP achieves both coarse-grained and fine-grained video anomaly detection by transferring pre-trained knowledge from CLIP to WSVAD task.
Polymerized Feature-based Domain Adaptation for Cervical Cancer Dose Map Prediction
Recently, deep learning (DL) has automated and accelerated the clinical radiation therapy (RT) planning significantly by predicting accurate dose maps.
Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
To obtain high-quality positron emission tomography (PET) scans while reducing radiation exposure to the human body, various approaches have been proposed to reconstruct standard-dose PET (SPET) images from low-dose PET (LPET) images.
Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval
Concretely, we leverage the capabilities of LLMs for document expansion, i. e. query generation, and effectively transfer expanded knowledge to retrievers using pre-training strategies tailored for passage retrieval.
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data.
AerialVLN: Vision-and-Language Navigation for UAVs
Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning.
Wireless Edge Content Broadcast via Integrated Terrestrial and Non-terrestrial Networks
In this paper, we introduce a novel approach to optimize wireless edge content placement using NTN, positioning NTN as a complement to TN for achieving optimal content broadcasting.
TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
Specifically, the TriDo-Former consists of two cascaded networks, i. e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms.
A Survey on Deep Learning-based Spatio-temporal Action Detection
Spatio-temporal action detection (STAD) aims to classify the actions present in a video and localize them in space and time.
Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition
Specifically, MGP-STR achieves an average recognition accuracy of $94\%$ on standard benchmarks for scene text recognition.
Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model
In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e. g., language descriptions and synchronous audios.
Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection
Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task.
Watch out Venomous Snake Species: A Solution to SnakeCLEF2023
The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata.
6G Network Business Support System
6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network security, etc.
Sparsified Simultaneous Confidence Intervals for High-Dimensional Linear Models
A critical question remains unsettled; that is, is it possible and how to embed the inference of the model into the simultaneous inference of the coefficients?
FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networks
Federated Learning (FL), as a privacy-preserving machine learning paradigm, trains a global model across devices without exposing local data.
MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e. g., perspective crops from a panorama or multi-view images given depth maps and poses).
Fast and Automatic 3D Modeling of Antenna Structure Using CNN-LSTM Network for Efficient Data Generation
In this study, we proposed a deep learning-assisted and image-based intelligent modeling approach for accelerating the data acquisition of antenna samples with different physical structures.
A Dynamic Feature Interaction Framework for Multi-task Visual Perception
In particular, one feature merge branch is designed for instance-level recognition the other for dense predictions.
The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
Second, it allows us to better understand deep representation learning by elucidating the linear progressive separation and concentration of representations from shallow to deep layers.
Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental Learning
Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data.
Learning Conditional Attributes for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations.
Ranked #1 on
Compositional Zero-Shot Learning
on MIT-States
Continuous and Noninvasive Measurement of Arterial Pulse Pressure and Pressure Waveform using an Image-free Ultrasound System
In in vitro cardiovascular phantom experiments, the results demonstrated high accuracy in the measurement of PP (error < 3 mmHg) and blood pressure waveform (root-mean-square-errors (RMSE) < 2 mmHg, correlation coefficient (r) > textgreater 0. 99).
NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment.
A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
At present, it is the largest semi-supervised VAD dataset with the largest number of scenes and classes of anomalies, the longest duration, and the only one considering the scene-dependent anomaly.
Editing Large Language Models: Problems, Methods, and Opportunities
Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.
