Papers
Sun 1 Oct 2023
133 papers
- Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of DiffusionDiffusion models → Diffusion foundations and sampling
- Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model ReasoningLLM reasoning → Test-time compute and efficient thinking
- Adapting LLM Agents with Universal Feedback in CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
- Parameter-Efficient Tuning Helps Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Sparse Backpropagation for MoE TrainingMixture-of-experts → MoE theory and gating functions
- Pre-training with Synthetic Data Helps Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Analyzing and Mitigating Object Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- A General Offline Reinforcement Learning Framework for Interactive RecommendationOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal AssistantsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- PETA: Parameter-Efficient Trojan AttacksLLM safety and security → Backdoor and data poisoning attacks
- Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Source Attribution for Large Language Model-Generated DataSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis +1
- GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised LearningLLM safety and security → Backdoor and data poisoning attacks
- Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and RealisationDiffusion models → Discrete and text diffusion
- A Comparison of Bounding Box and Landmark Detection Methods for Video-Based Heart Rate Estimation
- LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts
- My Machine and I: ChatGPT and the Future of Human-Machine Collaboration in Africa
- A Framework for Inference Inspired by Human Memory Mechanisms
- Facilitating Battery Swapping Services for Freight Trucks with Spatial-Temporal Demand Prediction
- A quantum moving target segmentation algorithm for grayscale video
- Quantum image edge detection based on eight-direction Sobel operator for NEQR
- A Stable and Efficient Covariate-Balancing Estimator for Causal Survival Effects
- Meta Semantic Template for Evaluation of Large Language Models
- Quantum-Based Feature Selection for Multi-classification Problem in Complex Systems with Edge Computing
- Determining the Optimal Number of Clusters for Time Series Datasets with Symbolic Pattern Forest
- ECG-SL: Electrocardiogram(ECG) Segment Learning, a deep learning method for ECG signal
- Learning to Make Adherence-Aware Advice
- Sharingan: A Transformer-based Architecture for Gaze Following
- OceanNet: A principled neural operator-based digital twin for regional oceans
- Towards Causal Foundation Model: on Duality between Causal Inference and Attention
- Completing Visual Objects via Bridging Generation and Segmentation
- Bayesian Design Principles for Frequentist Sequential Learning
- Knowledge Engineering for Wind Energy
- GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
- Don't Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection
- SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation
- Recent Advances in Generative AI for Healthcare Applications
- Revisiting Link Prediction: A Data Perspective
- Towards a Universal Understanding of Color Harmony: Fuzzy Approach
- Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs
- Propagating Semantic Labels in Video Data
- Mining Java Memory Errors using Subjective Interesting Subgroups with Hierarchical Targets
- Categorizing Flight Paths using Data Visualization and Clustering Methodologies
- SMOOT: Saliency Guided Mask Optimized Online Training
- Data-Efficient Strategies for Probabilistic Voltage Envelopes under Network Contingencies
- Counterfactual Image Generation for adversarially robust and interpretable Classifiers
- Data-driven adaptive building thermal controller tuning with constraints: A primal-dual contextual Bayesian optimization approach
- Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI Models
- TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
- Identifying Copeland Winners in Dueling Bandits with Indifferences
- SEED: Domain-Specific Data Curation With Large Language Models
- NoxTrader: LSTM-Based Stock Return Momentum Prediction for Quantitative Trading
- RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
- Deterministic Langevin Unconstrained Optimization with Normalizing Flows
- FELM: Benchmarking Factuality Evaluation of Large Language Models
- Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology
- GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models
- Robust Sentiment Analysis for Low Resource languages Using Data Augmentation Approaches: A Case Study in Marathi
- Spectral Neural Networks: Approximation Theory and Optimization Landscape
- Physics-Informed Graph Neural Network for Dynamic Reconfiguration of Power Systems
- Review of deep learning in healthcare
- Improving Length-Generalization in Transformers via Task Hinting
- Subtractive Mixture Models via Squaring: Representation and Learning
- HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
- Logical Bias Learning for Object Relation Prediction
- A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
- Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech
- You Do Not Need Additional Priors in Camouflage Object Detection
- Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips
- Learning How to Propagate Messages in Graph Neural Networks
- Do the Benefits of Joint Models for Relation Extraction Extend to Document-level Tasks?
- A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent
- Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange
- PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling
- CebuaNER: A New Baseline Cebuano Named Entity Recognition Model
- Optimization or Architecture: How to Hack Kalman Filtering
- Learning Type Inference for Enhanced Dataflow Analysis
- GeRA: Label-Efficient Geometrically Regularized Alignment
- A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos
- Balancing Efficiency vs. Effectiveness and Providing Missing Label Robustness in Multi-Label Stream Classification
- Twin Neural Network Improved k-Nearest Neighbor Regression
- Liveness Detection Competition -- Noncontact-based Fingerprint Algorithms and Systems (LivDet-2023 Noncontact Fingerprint)
- The Robots are Here: Navigating the Generative AI Revolution in Computing Education
- LEGO-Prover: Neural Theorem Proving with Growing Libraries
- PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
- From Bandits Model to Deep Deterministic Policy Gradient, Reinforcement Learning with Contextual Information
- RegBN: Batch Normalization of Multimodal Data with Regularization
- Segmentation-based Assessment of Tumor-Vessel Involvement for Surgical Resectability Prediction of Pancreatic Ductal Adenocarcinoma
- A primal-dual perspective for distributed TD-learning
- Knowledge Engineering using Large Language Models
- A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks
- Win-Win: Training High-Resolution Vision Transformers from Two Windows
- Finger-UNet: A U-Net based Multi-Task Architecture for Deep Fingerprint Enhancement
- Intelligent Client Selection for Federated Learning using Cellular Automata
- GNRK: Graph Neural Runge-Kutta method for solving partial differential equations
- Towards Understanding Adversarial Transferability in Federated Learning
- Scene-aware Human Motion Forecasting via Mutual Distance Prediction
- PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
All 133
- Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning
- Understanding Robust Overfitting from the Feature Generalization Perspective
- Path Structured Multimarginal Schr"odinger Bridge for Probabilistic Learning of Hardware Resource Usage by Control Software
- Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
- Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification
- A Novel Computational and Modeling Foundation for Automatic Coherence Assessment
- A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training
- Quantum generative adversarial learning in photonics
- City Foundation Models for Learning General Purpose Representations from OpenStreetMap
- Nine-year-old children outperformed ChatGPT in emotion: Evidence from Chinese writing
- GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length
- YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs
- Colloquial Persian POS (CPPOS) Corpus: A Novel Corpus for Colloquial Persian Part of Speech Tagging
- LaPLACE: Probabilistic Local Model-Agnostic Causal Explanations
- TDCGL: Two-Level Debiased Contrastive Graph Learning for Recommendation
- Image Data Hiding in Neural Compressed Latent Representations
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
- Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models
- DYNAP-SE2: a scalable multi-core dynamic neuromorphic asynchronous spiking neural network processor
- Discrete Choice Multi-Armed Bandits
- CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression
- Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
- Siamese Representation Learning for Unsupervised Relation Extraction
- Implicit Neural Representations and the Algebra of Complex Wavelets
- Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
- Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
- Thompson Exploration with Best Challenger Rule in Best Arm Identification
- JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
- SELF: Self-Evolution with Language Feedback
- Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
- Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets
- Self-supervised Learning of Contextualized Local Visual Embeddings
- Are Graph Neural Networks Optimal Approximation Algorithms?