Search Results for author:
Found 302 papers, 147 papers with code
Info-Coevolution: An Efficient Framework for Data Model Coevolution
It can further reduce the annotation ratio to 50\% with semi-supervised learning.
Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
Within the domain of Massively Multiplayer Online (MMO) economy research, Agent-Based Modeling (ABM) has emerged as a robust tool for analyzing game economics, evolving from rule-based agents to decision-making agents enhanced by reinforcement learning.
When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans.
MVP-Shapley: Feature-based Modeling for Evaluating the Most Valuable Player in Basketball
The burgeoning growth of the esports and multiplayer online gaming community has highlighted the critical importance of evaluating the Most Valuable Player (MVP).
Solving Euler equations with Multiple Discontinuities via Separation-Transfer Physics-Informed Neural Networks
Despite the remarkable progress of physics-informed neural networks (PINNs) in scientific computing, they continue to face challenges when solving hydrodynamic problems with multiple discontinuities.
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Phase II then performs one-shot termination that deactivates the alignment loss, once a simple trigger such as a fixed iteration is hit, freeing the DiT to focus on denoising and exploit its generative capacity.
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model.
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets.
Unsupervised Learning for Class Distribution Mismatch
Specifically, with a 60% mismatch proportion on Tiny-ImageNet dataset, our approach, without relying on labeled data, surpasses OpenMatch (with 40 labels per class) by 35. 1%, 63. 7%, and 72. 5% in classifying known, unknown, and new classes.
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications
To address this challenge, we introduce MINT (Multimodal Integrated kNowledge Transfer), a framework that aligns unimodal large decoder models with domain-specific decision patterns from multimodal biomedical data through preference optimization.
FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting
Multivariate time series forecasting is crucial across various industries, where accurate extraction of complex periodic and trend components can significantly enhance prediction performance.
Computational Efficiency
Multivariate Time Series Forecasting
+1
STRGCN: Capturing Asynchronous Spatio-Temporal Dependencies for Irregular Multivariate Time Series Forecasting
Irregular multivariate time series (IMTS) are prevalent in real-world applications across many fields, where varying sensor frequencies and asynchronous measurements pose significant modeling challenges.
Quantitative Analysis of Performance Drop in DeepSeek Model Quantization
Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
Landmark-Free Preoperative-to-Intraoperative Registration in Laparoscopic Liver Resection
Further, a structure-regularized deformation network is designed to adjust the preoperative model to align with the intraoperative liver surface.
Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing
However, existing editing techniques designed for diffusion models fail to translate directly to AR models due to fundamental differences in structural control.
DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation
Our investigations reveal that these costs primarily stem from the \emph{static} inference paradigm, which inevitably introduces redundant computation in certain \emph{diffusion timesteps} and \emph{spatial regions}.
Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
Large language models (LLMs) struggle with the factual error during inference due to the lack of sufficient training data and the most updated knowledge, leading to the hallucination problem.
MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate.
Dynamic Vision Mamba
For block redundancy, we allow each image to select SSM blocks dynamically based on an empirical observation that the inference speed of Mamba-based vision models is largely affected by the number of SSM blocks.
Slow-Fast Architecture for Video Multi-Modal Large Language Models
Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs).
ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
Parameter generation has emerged as a novel paradigm for neural network development, offering an alternative to traditional neural network training by synthesizing high-quality model weights directly.
Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation, addressing the need for independently controlled style elements for the Disentangled Stylized Image Generation (DisIG) problem.
Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
The objective is to assess the safety capabilities of these models in Chinese contexts both before and after distillation, and to further elucidate the adverse effects of distillation on model safety.
AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
Novel view synthesis (NVS) is a cornerstone for image-to-3d creation.
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability.
PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
In recent years, Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in tasks such as visual question answering, visual understanding, and reasoning.
Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes
We also showed that RAG-driven CoT and CoT-driven RAG both outperform foundation models in candidate gene prioritization from clinical notes; in particular, both methods with DeepSeek backbone resulted in a top-10 gene accuracy of over 40% on Phenopacket-derived clinical notes.
Make Optimization Once and for All with Fine-grained Guidance
Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks.
X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction
X-ray imaging is indispensable in medical diagnostics, yet its use is tightly regulated due to potential health risks.
A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis
We demonstrate the utility of the dataset by finetuning state-of-the-art multimodal models, showcasing significant improvements in crop disease diagnosis.
Learning Object Placement Programs for Indoor Scene Synthesis with Iterative Self Training
Empirical observations show that current systems tend to produce incomplete next object location distributions.
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
Recent advancements in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks.
Optimizing for the Shortest Path in Denoising Diffusion Model
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error.
Digital Player: Evaluating Large Language Models based Human-like Agent in Games
With the rapid advancement of Large Language Models (LLMs), LLM-based autonomous agents have shown the potential to function as digital employees, such as digital analysts, teachers, and programmers.
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system.
What's in a Query: Polarity-Aware Distribution-Based Fair Ranking
Unlike prior methods that operate on expected amortized attention for each individual, we define new divergence-based measures for attention distribution-based fairness in ranking (DistFaiR), characterizing unfairness as the divergence between the distribution of attention and relevance corresponding to an individual over time.
Safety Evaluation of DeepSeek Models in Chinese Contexts
In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark.
Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis
DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks.
Enhance-A-Video: Better Generated Video for Free
DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored.
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
Diffusion priors have been used for blind face restoration (BFR) by fine-tuning diffusion models (DMs) on restoration datasets to recover low-quality images.
One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Drawing inspiration from the inherent context consistency, we propose a novel training-free method for consistent text-to-image (T2I) generation, termed "One-Prompt-One-Story" (1Prompt1Story).
Recurrent Diffusion for Large-Scale Parameter Generation
The recurrent model's outputs, as conditions, are then fed into a diffusion model to generate the neural network parameters.
Matching Free Depth Recovery from Structured Light
We present a novel approach for depth estimation from images captured by structured light systems.
MedCT: A Clinical Terminology Graph for Generative AI Applications in Healthcare
We introduce the world's first clinical terminology for the Chinese healthcare community, namely MedCT, accompanied by a clinical foundation model MedBERT and an entity linking model MedLink.
InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models
Balancing the diffusion model's stochastic sampling with edge supervision of tampered image regions mitigates the risk of incorrect predictions from overconfidence and prevents the loss of subtle boundaries that can result from overly stochastic processes.
On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing
Missing data imputation, which aims to impute the missing values in the raw datasets to achieve the completeness of datasets, is crucial for modern data-driven models like large language models (LLMs) and has attracted increasing interest over the past decades.
One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models
Our findings suggest that, for T2I diffusion models, decoders are more adept at capturing richer and more explicit semantic information, while encoders can be effectively shared across decoders from diverse time steps. Based on these observations, we introduce the first Time-independent Unified Encoder (TiUE) for the student model UNet architecture, which is a loop-free image generation approach for distilling T2I diffusion models.
PowerRadio: Manipulate Sensor Measurementvia Power GND Radiation
Sensors are key components enabling various applications, e. g., home intrusion detection and environmental monitoring.
CALLIC: Content Adaptive Learning for Lossless Image Compression
To address this challenge, we explore the connection between the Minimum Description Length (MDL) principle and Parameter-Efficient Transfer Learning (PETL), leading to the development of a novel content-adaptive approach for learned lossless image compression, dubbed CALLIC.
TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction
We present TAR3D, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT) to generate high-quality 3D assets.
Covariances for Free: Exploiting Mean Distributions for Federated Learning with Pre-Trained Models
Our method, which only uses first-order statistics in the form of class means communicated by clients to the server, incurs only a fraction of the communication costs required by methods based on communicating second-order statistics.
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Re-training the token-reduced model enhances the performance of Mamba, by effectively rebuilding the key knowledge.
The Art of Deception: Color Visual Illusions and Diffusion Models
We use this fact to demonstrate that diffusion models can predict visual illusions.
Single-View Graph Contrastive Learning with Soft Neighborhood Awareness
Most graph contrastive learning (GCL) methods heavily rely on cross-view contrast, thus facing several concomitant challenges, such as the complexity of designing effective augmentations, the potential for information loss between views, and increased computational costs.
Multi-Modal Environmental Sensing Based Path Loss Prediction for V2I Communications
The stability and reliability of wireless data transmission in vehicular networks face significant challenges due to the high dynamics of path loss caused by the complexity of rapidly changing environments.
A multimodal ensemble approach for clear cell renal cell carcinoma treatment outcome prediction
Using predicted risk medians to stratify high- and low-risk groups, log-rank tests showed improved performance in both OS and DFS compared to single-modality models.
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous visual tokens.
Ranked #19 on
Visual Question Answering
on MM-Vet
HunyuanVideo: A Systematic Framework For Large Video Generative Models
In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
Deep Sparse Latent Feature Models for Knowledge Graph Completion
Recent progress in knowledge graph completion (KGC) has focused on text-based approaches to address the challenges of large-scale knowledge graphs (KGs).
InterFormer: Towards Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction.
Computational metaoptics for imaging
Advanced applications enabled by computational metaoptics are highlighted, including phase imaging and quantum state measurement, which benefit from the metasurfaces' ability to manipulate complex light fields and the computational algorithms' capacity to reconstruct high-dimensional information.
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
In this paper, we define semantic binding as the task of associating a given object with its attribute, termed attribute binding, or linking it to other related sub-objects, referred to as object binding.
Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier
However, in many realistic scenarios, we only have access to few samples and knowledge of the class names (e. g., when considering instances of classes).
Primal-Dual Spectral Representation for Off-policy Evaluation
We highlight that our algorithm, SpectralDICE, is the first to leverage the linear representation of primal-dual variables that is both computation and sample efficient, the performance of which is supported by a rigorous theoretical sample complexity guarantee and a thorough empirical evaluation on various benchmarks.
Learning Lossless Compression for High Bit-Depth Volumetric Medical Image
The BD-LVIC framework skillfully divides the high bit-depth volume into two lower bit-depth segments: the Most Significant Bit-Volume (MSBV) and the Least Significant Bit-Volume (LSBV).
Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios
Hopefully, more researchers will be inspired and encouraged to improve the practicality and efficacy of DD.
Assessing Open-world Forgetting in Generative Image Model Customization
Our work presents the first systematic investigation into open-world forgetting in diffusion models, focusing on semantic and appearance drift of representations.
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands.
Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs
In this paper, we introduce SCR, a unified graph reasoning framework designed to train on knowledge graphs and effectively generalize across a wide range of graph tasks and domains.
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
We evaluate a wide variety of frontier vision-language models on MEGA-Bench to understand their capabilities across these dimensions.
ERCache: An Efficient and Reliable Caching Framework for Large-Scale User Representations in Meta's Ads System
The increasing complexity of deep learning models used for calculating user representations presents significant challenges, particularly with limited computational resources and strict service-level agreements (SLAs).
Dynamic Diffusion Transformer
In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations.
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process.
What is the Right Notion of Distance between Predict-then-Optimize Tasks?
Comparing datasets is a fundamental task in machine learning, essential for various learning paradigms; from evaluating train and test datasets for model generalization to using dataset similarity for detecting data drift.
Distilling Long-tailed Datasets
It reduces the distance between the student and the biased expert trajectories and prevents the tail class bias from being distilled to the synthetic dataset.
Real-Time Video Generation with Pyramid Attention Broadcast
We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free approach for DiT-based video generation.
GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
In this paper, we introduce a diffusion-based method, termed \ourmethod, to generate fonts that vividly embody specific impressions, utilizing an input consisting of a single letter and a set of descriptive impression keywords.
The Dial-a-Ride Problem with Limited Pickups per Trip
This results in the Dial-a-Ride Problem with Limited Pickups per Trip (DARP-LPT).
LipidBERT: A Lipid Language Model Pre-trained on METiS de novo Lipid Library
To the best of our knowledge, this is the first successful demonstration of the capability of a pre-trained language model on virtual lipids and its effectiveness in downstream tasks using web-lab data.
Prioritize Alignment in Dataset Distillation
To achieve this, existing methods use the agent model to extract information from the target dataset and embed it into the distilled dataset.
More Than Positive and Negative: Communicating Fine Granularity in Medical Diagnosis
Specifically, we devise a division rule based on medical knowledge to divide positive cases into two subcategories, namely atypical positive and typical positive.
TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks
Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks.
Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models
Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities.
MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability
Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are incapable of generalizing to unseen view points, MVPbev simultaneously generates cross-view consistent images of different perspective views with a two-stage design, allowing object-level control and novel view generation at test-time.
Exemplar-free Continual Representation Learning via Learnable Drift Compensation
Prototype-based approaches, when continually updated, face the critical issue of semantic drift due to which the old class prototypes drift to different positions in the new feature space.
ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement
To overcome this, we generate several basic geometric objects in the target color, allowing for color and shape disentanglement during the color prompt learning.
CUPID: Improving Battle Fairness and Position Satisfaction in Online MOBA Games with a Re-matchmaking System
Enhancing the gaming experience requires a deep understanding of player behavior, and a crucial aspect of MOBA games is matchmaking, which aims to assemble teams of comparable skill levels.
Methodology of Adapting Large English Language Models for Specific Cultural Contexts
The rapid growth of large language models(LLMs) has emerged as a prominent trend in the field of artificial intelligence.
OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser
Recent research has shown that combining Mamba with Transformer architecture, which has selective state space and quadratic self-attention mechanism, outperforms using Mamba or Transformer architecture alone in language modeling tasks.
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
The main barrier is the lack of large-scale human-annotated dataset.
First-Order Methods for Linearly Constrained Bilevel Optimization
For linear equality constraints, we attain $\epsilon$-stationarity in $\widetilde{O}(\epsilon^{-2})$ gradient oracle calls, which is nearly-optimal.
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling.
CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models
With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention.
Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality
To address these challenges, this paper introduces the Text-to-Video Human Evaluation (T2VHE) protocol, a comprehensive and standardized protocol for T2V models.
AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation
This shared backbone facilitates both audio and video generation.
Aligning Large Language Models with Representation Editing: A Control Perspective
To achieve alignment for specific objectives, we introduce external control signals into the state space of this language dynamical system.
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in language comprehension and reasoning across diverse domains.
SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs
We aim to predict future links within the dynamic graph while simultaneously providing causal explanations for these predictions.
Dataset Growth
To tackle this challenge, we propose InfoGrowth, an efficient online algorithm for data cleaning and selection, resulting in a growing dataset that keeps up to date with awareness of cleanliness and diversity.
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
Training diffusion models is always a computation-intensive task.
FAITH: Frequency-domain Attention In Two Horizons for Time Series Forecasting
Time Series Forecasting plays a crucial role in various fields such as industrial equipment maintenance, meteorology, energy consumption, traffic flow and financial investment.
Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation
We also present Grad-TEAM, a Gradient-weighted Time-Event Activation Mapping approach specifically developed for deep survival model visual explanation, to generate patient-specific time-to-event activation maps.
TransAnaNet: Transformer-based Anatomy Change Prediction Network for Head and Neck Cancer Patient Radiotherapy
The predicted image from the proposed method yielded the best similarity to the real image (CBCT21) over pCT, CBCT01, and predicted CBCTs from other comparison models.
Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.
ATOM: Attention Mixer for Efficient Dataset Distillation
To address these challenges in dataset distillation, we propose the ATtentiOn Mixer (ATOM) module to efficiently distill large datasets using a mixture of channel and spatial-wise attention in the feature matching process.
GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
To further expedite the network inference, we introduce context cache optimization to GroupedMixer, which caches attention activation values in cross-group token-mixers and avoids complex and duplicated computation.
LocInv: Localization-aware Inversion for Text-Guided Image Editing
Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts.
$ν$-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction
The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving.
SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
Optical flow estimation is crucial to a variety of vision tasks.
EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker
Most of 3D single object trackers (SOT) in point clouds follow the two-stream multi-stage 3D Siamese or motion tracking paradigms, which process the template and search area point clouds with two parallel branches, built on supervised point cloud backbones.
A dataset of primary nasopharyngeal carcinoma MRI with multi-modalities segmentation
Multi-modality magnetic resonance imaging data with various sequences facilitate the early diagnosis, tumor segmentation, and disease staging in the management of nasopharyngeal carcinoma (NPC).
GNSS Spoofing Detection by Crowdsourcing Double Differential Pseudorange Spatial Distribution
It is widely known that spoofing is a major threat that adversely impacts the reliability and accuracy of GNSS applications.
Assessing the Utility of Large Language Models for Phenotype-Driven Gene Prioritization in Rare Genetic Disorder Diagnosis
A similar increasing trend was observed for the task completion rate, with complicated prompts more likely to increase task completeness in models smaller than GPT-4.
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency.
Difference Learning for Air Quality Forecasting Transport Emulation
Due to a recent increase in extreme air quality events, both globally and locally in the United States, finer resolution air quality forecasting guidance is needed to effectively adapt to these events.
Neural Network Diffusion
The autoencoder extracts latent representations of a subset of the trained neural network parameters.
LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs
Knowledge Graph (KG) inductive reasoning, which aims to infer missing facts from new KGs that are not seen during training, has been widely adopted in various applications.
Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
Specifically, we employ a curriculum learning strategy to train expert trajectories with more diverse supervision signals from the original graph, and then effectively transfer the information into the condensed graph with expanding window matching.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns.
AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant
After training, ThyGPT could automatically evaluate thyroid nodule and engage in effective communication with physicians through human-computer interaction.
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
Specifically, GST initially constructs a topology & semantic anchor at a low training cost, followed by performing dynamic sparse training to align the sparse graph with the anchor.
Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements.
Machine learning for industrial sensing and control: A survey and practical perspective
Soft sensing contains a wealth of industrial applications of statistical and machine learning methods.
Sequential Model for Predicting Patient Adherence in Subcutaneous Immunotherapy for Allergic Rhinitis
How to enhance the adherence of patients to maximize the benefit of allergen immunotherapy (AIT) plays a crucial role in the management of AIT.
Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation
The increasing demand for intelligent systems capable of interpreting and reasoning about visual content requires the development of large Vision-and-Language Models (VLMs) that are not only accurate but also have explicit reasoning capabilities.
Must: Maximizing Latent Capacity of Spatial Transcriptomics Data
MuST integrates the multi-modality information contained in the ST data effectively into a uniform latent space to provide a foundation for all the downstream tasks.
Understanding YTHDF2-mediated mRNA Degradation By m6A-BERT-Deg
N6-methyladenosine (m6A) is the most abundant mRNA modification within mammalian cells, holding pivotal significance in the regulation of mRNA stability, translation, and splicing.
GestaltMML: Enhancing Rare Genetic Disease Diagnosis through Multimodal Machine Learning Combining Facial Images and Clinical Texts
Many rare genetic diseases have distinctive facial features, which can be used by artificial intelligence algorithms to facilitate clinical diagnosis, in prioritizing candidate diseases to be further examined by lab tests or genetic assays, or in helping the phenotype-driven reinterpretation of genome/exome sequencing data.
Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling
The emergence of on-demand ride pooling services allows each vehicle to serve multiple passengers at a time, thus increasing drivers' income and enabling passengers to travel at lower prices than taxi/car on-demand services (only one passenger can be assigned to a car at a time like UberX and Lyft).
Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models
The term "Reversal Curse" refers to the scenario where auto-regressive decoder large language models (LLMs), such as ChatGPT, trained on "A is B" fail to learn "B is A," assuming that B and A are distinct and can be uniquely identified from each other, demonstrating a basic failure of logical deduction.
MLLMs-Augmented Visual-Language Representation Learning
Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets.
Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta
To address these challenges, we present Scaling User Modeling (SUM), a framework widely deployed in Meta's ads ranking system, designed to facilitate efficient and scalable sharing of online user representation across hundreds of ads models.
Towards Long-term Annotators: A Supervised Label Aggregation Baseline
These annotators could leave substantial historical annotation records on the crowdsourcing platforms, which can benefit label aggregation, but are ignored by previous works.
LiPar: A Lightweight Parallel Learning Model for Practical In-Vehicle Network Intrusion Detection
As the main network of in-vehicle networks, the controller area network (CAN) has many potential security hazards, resulting in higher generalization capability and lighter security requirements for intrusion detection systems to ensure safety.
STATGRAPH: Effective In-vehicle Intrusion Detection via Multi-view Statistical Graph Learning
In-vehicle network (IVN) is facing complex external cyber-attacks, especially the emerging masquerade attacks with extremely high difficulty of detection while serious damaging effects.
AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking
Specifically, in the proposed encoder AViT encoder, we introduce a tracking-tailored Adaptor module for vanilla ViT and a joint target state embedding to enrich the target-prior embedding paradigm.
IterInv: Iterative Inversion for Pixel-Level T2I Models
Based on this observation, we develop an iterative inversion (IterInv) technique for this category of T2I models and verify IterInv with the open-source DeepFloyd-IF model. Specifically, IterInv employ NTI as the inversion and reconstruction of low-resolution image generation.
DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching
Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones.
Does Graph Distillation See Like Vision Dataset Counterpart?
We validate the proposed SGDD across 9 datasets and achieve state-of-the-art results on all of them: for example, on the YelpChi dataset, our approach maintains 98. 6% test accuracy of training on the original graph dataset with 1, 000 times saving on the scale of the graph.
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning
Personalized FL (PFL) addresses this by synthesizing personalized models from a global model via training on local data.
Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset.
Can pre-trained models assist in dataset distillation?
Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training.
Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt.
KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation
Knowledge graph completion (KGC) revolves around populating missing triples in a knowledge graph using available information.
Ranked #2 on
Link Prediction
on WN18RR
When Large Language Models Meet Citation: A Survey
Such information could be incorporated into LLMs pre-training and improve the text representation in LLMs.
Multi-user passive beamforming in RIS-aided communications and experimental validations
To generate the reflection coefficients with the aim of maximizing the spectral efficiency, we propose a quadratic transform-based low-rank multi-user beamforming (QTLM) algorithm.
Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning
In the second phase, we combine this new knowledge with the previous network in an adaptation-retrospection phase to avoid forgetting and initialize a new expert with the knowledge of the old network.
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
With the help of iterative training of the semantic encoder and diffusion model, DiffAug improves the representation ability in an uninterrupted and unsupervised manner.
Ranked #1 on
Data Augmentation
on GA1457
Region Generation and Assessment Network for Occluded Person Re-Identification
Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.
Recurrence-Free Survival Prediction for Anal Squamous Cell Carcinoma Chemoradiotherapy using Planning CT-based Radiomics Model
Conclusions: A treatment planning CT based radiomics and clinical combined model had improved prognostic performance in predicting RFS for ASCC patients treated with CRT as compared to a model using clinical features only.
ScrollNet: Dynamic Weight Importance for Continual Learning
The importance of weights for each task can be determined either explicitly through learning a task-specific mask during training (e. g., parameter isolation-based approaches) or implicitly by introducing a regularization term (e. g., regularization-based approaches).
Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification
In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
Dataset Quantization
Extensive experiments demonstrate that DQ is able to generate condensed small datasets for training unseen network architectures with state-of-the-art compression ratios for lossless model training.
The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field
Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoothing as they go deeper as models of computer vision realm.
Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT
We hypothesize that large language models (LLMs) based on the transformer architecture can enable automated detection of clinical phenotype terms, including terms not documented in the HPO.
DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis
Firstly, the frozen features are transformed by an lightweight bottleneck layer to learn the domain-specific distribution of downstream medical tasks, and then a few learnable visual prompts are used as dynamic queries and then conduct cross-attention with the transformed features, attempting to acquire sample-specific knowledge that are suitable for each sample.
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude
Whole-body biometric recognition is an important area of research due to its vast applications in law enforcement, border security, and surveillance.
Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System
Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i. e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance).
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain.
Generating Driving Scenes with Diffusion
In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car.
Summarizing Stream Data for Memory-Constrained Online Continual Learning
Through maintaining the consistency of training gradients and relationship to the past tasks, the summarized samples are more representative for the stream data compared to the original images.
SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation
Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness.
River of No Return: Graph Percolation Embeddings for Efficient Knowledge Graph Reasoning
We study Graph Neural Networks (GNNs)-based embedding techniques for knowledge graph (KG) reasoning.
The 3rd Anti-UAV Workshop & Challenge: Methods and Results
Second, we set up two tracks for the first time, i. e., Anti-UAV Tracking and Anti-UAV Detection & Tracking.
A Soft Coordination Method of Heterogeneous Devices in Distribution System Voltage Control
The proposed method achieves the soft coordination by establishing a modified actor-critic algorithm to train a proxy model of inverters.
Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain.
Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking
In this paper, we follow a data-centric philosophy and propose a novel motion annotation method based on the inherent representativeness of motion data in a given dataset.
Classification of integers based on residue classes via modern deep learning algorithms
Judging whether an integer can be divided by prime numbers such as 2 or 3 may appear trivial to human beings, but can be less straightforward for computers.
Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models
The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry.
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
Cross-modal retrieval with noisy correspondence
Image-text matching
+1
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition
In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition.
Continual Self-Supervised Learning
Handwritten Text Recognition
+1
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance.
Ranked #8 on
Vehicle Re-Identification
on VehicleID Large
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
To address this challenge, we propose a novel method ZSCL to prevent zero-shot transfer degradation in the continual learning of vision-language models in both feature and parameter space.
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
To solve this problem, we propose \textbf{InfoBatch}, a novel framework aiming to achieve lossless training acceleration by unbiased dynamic data pruning.
DiM: Distilling Dataset into Generative Model
To the best of our knowledge, we are the first to achieve higher accuracy on complex architectures than simple ones, such as 75. 1\% with ResNet-18 and 72. 6\% with ConvNet-3 on ten images per class of CIFAR-10.
DREAM: Efficient Dataset Distillation by Representative Matching
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
Bioformer: an efficient transformer language model for biomedical text mining
We thoroughly evaluated the performance of Bioformer as well as existing biomedical BERT models including BioBERT and PubMedBERT on 15 benchmark datasets of four different biomedical NLP tasks: named entity recognition, relation extraction, question answering and document classification.
Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style
Diffusion models have demonstrated impressive capability of text-conditioned image synthesis, and broader application horizons are emerging by personalizing those pretrained diffusion models toward generating some specialized target object or style.
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision
Meanwhile, SANE easily establishes multi-task learning with CORE loss functions on both depth and surface normal estimation, leading to the whole performance leap.
FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting
However, use of FT is problematic due to Gibbs phenomenon.
Expanding Small-Scale Datasets with Guided Imagination
Specifically, GIF conducts data imagination by optimizing the latent features of the seed data in the semantically meaningful space of the prior model, resulting in the creation of photo-realistic images with new content.
Self adaptive global-local feature enhancement for radiology report generation
Automated radiology report generation aims at automatically generating a detailed description of medical images, which can greatly alleviate the workload of radiologists and provide better medical services to remote areas.
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
In this work, we expand the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image-to-text, and variations in one unified model.
Dataset Factorization for Condensation
In this paper, we study dataset distillation (DD), from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
Dataset Distillation via Factorization
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
MV-HAN: A Hybrid Attentive Networks based Multi-View Learning Model for Large-scale Contents Recommendation
In this paper, we introduce a novel Multi-View Approach with Hybrid Attentive Networks (MV-HAN) for contents retrieval at the matching stage of recommender systems.
Vision-Based Defect Classification and Weight Estimation of Rice Kernels
To compensate for the imbalance of different kernel numbers and classify kernels with multiple flaws accurately, we propose a multi-stage workflow which is able to locate the kernels in the captured image and classify their properties.
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Lifelong object re-identification incrementally learns from a stream of re-identification tasks.
Attention Distillation: self-supervised vision transformer students need more guidance
In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model).
Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
Especially for smaller, single institutional datasets, it may be important to evaluate multiple estimations techniques before incorporating a model into clinical practice.
Long-Term Person Re-identification with Dramatic Appearance Change: Algorithm and Benchmark
In addition, we propose a network named M2Net, which integrates multi-modality features from the RGB images, contour images and human parsing images.
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.
Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients.
Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals.
Prompt Vision Transformer for Domain Generalization
In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction.
QuickSkill: Novice Skill Estimation in Online Multiplayer Games
However, the skill rating of a novice is usually inaccurate, as current matchmaking rating algorithms require considerable amount of games for learning the true skill of a new player.
