Papers
Mon 15 Jan 2024
184 papers
- Binding-Adaptive Diffusion Models for Structure-Based Drug DesignDiffusion models → Flow matching, time series and science
- Constrained Multi-objective Optimization with Deep Reinforcement Learning Assisted Operator SelectionDeep reinforcement learning methods → RL for games and combinatorial optimization
- The Chronicles of RAG: The Retriever, the Chunk and the GeneratorRetrieval-augmented generation → RAG pipeline design and evaluation
- Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative DecodingEfficient LLM inference and serving → Speculative decoding
- The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian NoiseDeep reinforcement learning methods → RL theory and sample complexity
- Question Translation Training for Better Multilingual ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Flexibly Scaling Large Language Models Contexts Through Extensible TokenizationRetrieval-augmented generation → Generation and context integration
- When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and AlignmentMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
- Combining Machine Learning and Ontology: A Systematic Literature ReviewLLM reasoning → Reasoning benchmarks and evaluation
- Go-Explore for Residential Energy ManagementDeep reinforcement learning methods → RL for energy, networks and operations
- Towards Efficient Diffusion-Based Image Editing with Instant Attention MasksDiffusion models → Image generation, text-to-image and editing
- Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated ApplicationsLLM safety and security → Prompt injection and agent security
- Multi-task real-robot data with gaze attention for dual-arm fine manipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
- MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in PerceptionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- InstantID: Zero-shot Identity-Preserving Generation in SecondsDiffusion models → Image generation, text-to-image and editing
- Concept-Guided Prompt Learning for Generalization in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Discriminative Consensus Mining with A Thousand Groups for More Accurate Co-Salient Object Detection
- TP-Aware Dequantization
- Determining the Difficulties of Students With Dyslexia via Virtual Reality and Artificial Intelligence: An Exploratory Analysis
- Knowledge-Driven Deep Learning Paradigms for Wireless Network Optimization in 6G
- Graph Representation Learning for Contention and Interference Management in Wireless Networks
- Challenge design roadmap
- The Effect of Human v/s Synthetic Test Data and Round-tripping on Assessment of Sentiment Analysis Systems for Bias
- A VR Serious Game to Increase Empathy towards Students with Phonological Dyslexia
- Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
- Push- and Pull-based Effective Communication in Cyber-Physical Systems
- Analyzing Brain Activity During Learning Tasks with EEG and Machine Learning
- DISTINQT: A Distributed Privacy Aware Learning Framework for QoS Prediction for Future Mobile and Wireless Networks
- Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning
- Training program on sign language: social inclusion through Virtual Reality in ISENSE project
- Survival Analysis of Young Triple-Negative Breast Cancer Patients
- Assistant, Parrot, or Colonizing Loudspeaker? ChatGPT Metaphors for Developing Critical AI Literacies
- Decoupled Prototype Learning for Reliable Test-Time Adaptation
- Contextual Bandits with Stage-wise Constraints
- Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning
- Analysing the Needs of Homeless People Using Feature Selection and Mining Association Rules
- Jewelry Recognition via Encoder-Decoder Models
- Discovery of Generalizable TBI Phenotypes Using Multivariate Time-Series Clustering
- Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation
- Carrying over algorithm in transformers
- Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes
- How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?
- Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings
- Simulated Autopoiesis in Liquid Automata
- MCMChaos: Improvising Rap Music with MCMC Methods and Chaos Theory
- AI-as-exploration: Navigating intelligence space
- Cesium Tiles for High-realism Simulation and Comparing SLAM Results in Corresponding Virtual and Real-world Environments
- Solution of the Probabilistic Lambert Problem: Connections with Optimal Mass Transport, Schr"odinger Bridge and Reaction-Diffusion PDEs
- Graph Dual-stream Convolutional Attention Fusion for Precipitation Nowcasting
- Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models
- A Study on Large Language Models' Limitations in Multiple-Choice Question Answering
- Image Similarity using An Ensemble of Context-Sensitive Models
- SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
- SemEval-2017 Task 4: Sentiment Analysis in Twitter using BERT
- Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding
- Integrate Any Omics: Towards genome-wide data integration for patient stratification
- A Globally Convergent Algorithm for Neural Network Parameter Optimization Based on Difference-of-Convex Functions
- Vertical Federated Image Segmentation
- Machine Learning Based Object Tracking
- A Lexicon for Studying Radicalization in Incel Communities
- Are self-explanations from Large Language Models faithful?
- Word Boundary Information Isn't Useful for Encoder Language Models
- The Pitfalls of Defining Hallucination
- A Strategy for Implementing description Temporal Dynamic Algorithms in Dynamic Knowledge Graphs by SPIN
- Machine Learning Techniques to Identify Hand Gestures amidst Forearm Muscle Signals
- Multifidelity domain decomposition-based physics-informed neural networks and operators for time-dependent problems
- Learned Best-Effort LLM Serving
- EMBRE: Entity-aware Masking for Biomedical Relation Extraction
- Do stable neural networks exist for classification problems? -- A new view on stability in AI
- The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
- Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities
- JumpCoder: Go Beyond Autoregressive Coder via Online Modification
- Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability
- Authorship Obfuscation in Multilingual Machine-Generated Text Detection
- Adaptive Neural-Operator Backstepping Control of a Benchmark Hyperbolic PDE
- Information hiding cameras: optical concealment of object information into ordinary images
- M2Fusion: Bayesian-based Multimodal Multi-level Fusion on Colorectal Cancer Microsatellite Instability Prediction
- VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
- Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions
- Two Types of AI Existential Risk: Decisive and Accumulative
- Phenotyping calcification in vascular tissues using artificial intelligence
- Wikidata as a seed for Web Extraction
- Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues
- Optimal Data Splitting in Distributed Optimization for Machine Learning
- Uncovering the Full Potential of Visual Grounding Methods in VQA
- Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey
- Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification
- Activations and Gradients Compression for Model-Parallel Training
- Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach
- Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing
- Towards A Better Metric for Text-to-Video Generation
- Quantum Transfer Learning for Acceptability Judgements
- Seeing the Unseen: Visual Common Sense for Semantic Placement
- Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation
- On the importance of Data Scale in Pretraining Arabic Language Models
- Joint Probability Selection and Power Allocation for Federated Learning
- Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space
- DeepThalamus: A novel deep learning method for automatic segmentation of brain thalamic nuclei from multimodal ultra-high resolution MRI
- Sparsity-based background removal for STORM super-resolution images
All 184
- MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation
- Conformal Approach To Gaussian Process Surrogate Evaluation With Coverage Guarantees
- SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction
- HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation
- Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management
- Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation
- Efficient Nonparametric Tensor Decomposition for Binary and Count Data
- Prompting open-source and commercial language models for grammatical error correction of English learner text
- Data vs. Model Machine Learning Fairness Testing: An Empirical Study
- Stochastic optimization with arbitrary recurrent data sampling
- Assisted Knowledge Graph Authoring: Human-Supervised Knowledge Graph Construction from Natural Language
- CLSA-CIM: A Cross-Layer Scheduling Approach for Computing-in-Memory Architectures
- SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels
- Empirical Evidence for the Fragment level Understanding on Drug Molecular Structure of LLMs
- Learning Explainable and Better Performing Representations of POMDP Strategies
- MLAD: A Unified Model for Multi-system Log Anomaly Detection
- Foundation Models for Biomedical Image Segmentation: A Survey
- Multifractal-spectral features enhance classification of anomalous diffusion
- SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting
- Compute-Efficient Active Learning
- Fine-Grained Prototypes Distillation for Few-Shot Object Detection
- Cost-sensitive Feature Selection for Support Vector Machines
- RedEx: Beyond Fixed Representation Methods via Convex Optimization
- Data Assimilation using ERA5, ASOS, and the U-STN model for Weather Forecasting over the UK
- MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models
- E3x: E(3)-Equivariant Deep Learning Made Easy
- Multimodal Crowd Counting with Pix2Pix GANs
- Curriculum for Crowd Counting -- Is it Worthy?
- Collaboratively Self-supervised Video Representation Learning for Action Recognition
- Geo-locating Road Objects using Inverse Haversine Formula with NVIDIA Driveworks
- PMFSNet: Polarized Multi-scale Feature Self-attention Network For Lightweight Medical Image Segmentation
- Confounded Budgeted Causal Bandits
- Cascaded Cross-Modal Transformer for Audio-Textual Classification
- Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding
- A Bi-Pyramid Multimodal Fusion Method for the Diagnosis of Bipolar Disorders
- Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
- FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality
- Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models
- Robust Semi-Supervised Learning for Self-learning Open-World Classes
- See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
- Must: Maximizing Latent Capacity of Spatial Transcriptomics Data
- Combining Image- and Geometric-based Deep Learning for Shape Regression: A Comparison to Pixel-level Methods for Segmentation in Chest X-Ray
- Study Features via Exploring Distribution Structure
- Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation
- Automatic characterization of boulders on planetary surfaces from high-resolution satellite images
- One for All: Toward Unified Foundation Models for Earth Vision
- Editing Arbitrary Propositions in LLMs without Subject Labels
- TAROT: A Hierarchical Framework with Multitask Co-Pretraining on Semi-Structured Data towards Effective Person-Job Fit
- Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends
- Temporal Link Prediction Using Graph Embedding Dynamics
- Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering
- SeMaScore : a new evaluation metric for automatic speech recognition tasks
- PolMERLIN: Self-Supervised Polarimetric Complex SAR Image Despeckling with Masked Networks
- Compositional Oil Spill Detection Based on Object Detector and Adapted Segment Anything Model from SAR Images
- Harnessing Deep Learning and Satellite Imagery for Post-Buyout Land Cover Mapping
- Efficient Wireless Federated Learning via Low-Rank Gradient Factorization
- Input Convex Lipschitz Recurrent Neural Networks for Robust and Efficient Process Modeling and Optimization
- The Principle of Minimum Pressure Gradient: An Alternative Basis for Physics-Informed Learning of Incompressible Fluid Mechanics
- Feature Selection via Maximizing Distances between Class Conditional Distributions
- Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation
- A Contrast Based Feature Selection Algorithm for High-dimensional Data set in Machine Learning
- CascadeV-Det: Cascade Point Voting for 3D Object Detection
- GWPT: A Green Word-Embedding-based POS Tagger
- Utilizing deep learning models for the identification of enhancers and super-enhancers based on genomic and epigenomic features
- A Deep Hierarchical Feature Sparse Framework for Occluded Person Re-Identification
- Learning-Based Speed Estimation from Accelerometer-Only Inertial Sensing
- Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection
- Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids
- Quantum Privacy Aggregation of Teacher Ensembles (QPATE) for Privacy-preserving Quantum Machine Learning
- Consistency of semi-supervised learning, stochastic tug-of-war games, and the p-Laplacian
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
- Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
- Model Editing at Scale leads to Gradual and Catastrophic Forgetting
- Formal Logic Enabled Personalized Federated Learning Through Property Inference
- Taec: a Manually annotated text dataset for trait and phenotype extraction and entity linking in wheat breeding literature
- GACE: Learning Graph-Based Cross-Page Ads Embedding For Click-Through Rate Prediction
- Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance
- Mask-adaptive Gated Convolution and Bi-directional Progressive Fusion Network for Depth Completion
- BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels
- Generalized Planning for the Abstraction and Reasoning Corpus
- Leveraging the power of transformers for guilt detection in text
- Improved Implicit Neural Representation with Fourier Reparameterized Training
- Cross Domain Early Crop Mapping using CropSTGAN
- Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification