Papers

New on arXiv

Sun 10 Mar 2024

120 papers

Attention is all you need for boosting graph convolutional neural networkKnowledge distillation → Graph neural network distillation
WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image InputsWorld models → Video-generation world models and simulators +1
From Instructions to Constraints: Language Model Alignment with Automatic Constraint VerificationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty EquivalentsDeep reinforcement learning methods → RL theory and sample complexity
Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation SchemesLLM reasoning → Clinical and biomedical applications +1
Fine-tuning of diffusion models via stochastic control: entropy regularization and beyondDiffusion models → Diffusion foundations and sampling
FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video EditingDiffusion models → Video generation
TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned DecisionLLM reasoning → Reasoning for agents, planning and code +1
VkD: Improving Knowledge Distillation using Orthogonal ProjectionsKnowledge distillation → General knowledge distillation methods
Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Decoupled Contrastive Learning for Long-Tailed RecognitionKnowledge distillation → General knowledge distillation methods
MACE: Mass Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local ExamplesLLM safety and security → Federated unlearning and poisoning
In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion ModelsDiffusion models → Video generation
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?Diffusion models → Image generation, text-to-image and editing
Knowledge Distillation of Convolutional Neural Networks through Feature Map Transformation using Decision TreesKnowledge distillation → General knowledge distillation methods
Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation ModelsSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingKnowledge distillation → General knowledge distillation methods
Reframe Anything: LLM Agent for Open World Video ReframingLLM agents and tool use → Multimodal and embodied agents
Test-time Distribution Learning Adapter for Cross-modal Visual ReasoningLLM reasoning → Multimodal reasoning +1
Decoupled Data Consistency with Diffusion Purification for Image RestorationDiffusion models → Inverse problems and image restoration
UCINet0: A Machine Learning based Receiver for 5G NR PUCCH Format 0
Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints
Few-shot Learning on Heterogeneous Graphs: Challenges, Progress, and Prospects
A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
Attacking Transformers with Feature Diversity Adversarial Perturbation
FWin transformer for dengue prediction under climate and ocean influence
Whiteness-based bilevel learning of regularization parameters in imaging
Enhancing Quantum Variational Algorithms with Zero Noise Extrapolation via Neural Networks
A Unified Model for Spatio-Temporal Prediction Queries with Arbitrary Modifiable Areal Units
Separable Physics-informed Neural Networks for Solving the BGK Model of the Boltzmann Equation
FOAA: Flattened Outer Arithmetic Attention For Multimodal Tumor Classification
Disentangling shared and private latent factors in multimodal Variational Autoencoders
Exploiting the Margin: How Capitalism Fuels AI at the Expense of Minoritized Groups
Distributional Successor Features Enable Zero-Shot Policy Optimization
Leveraging Computer Vision in the Intensive Care Unit (ICU) for Examining Visitation and Mobility
Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
An End-to-End Deep Learning Generative Framework for Refinable Shape Matching and Generation
A Study on Domain Generalization for Failure Detection through Human Reactions in HRI
How much data do you need? Part 2: Predicting DL class specific training dataset sizes
Nonparametric Automatic Differentiation Variational Inference with Spline Approximation
LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition
Analysis of Total Variation Minimization for Clustered Federated Learning
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
Transformer based Multitask Learning for Image Captioning and Object Detection
Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Probing Image Compression For Class-Incremental Learning
UNICORN: Ultrasound Nakagami Imaging via Score Matching and Adaptation
Physics-Guided Abnormal Trajectory Gap Detection
FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations
Editing Conceptual Knowledge for Large Language Models
Poly Kernel Inception Network for Remote Sensing Detection
Online Multi-spectral Neuron Tracing
No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks
Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering
COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System
Cooperative Classification and Rationalization for Graph Generalization
Probabilistic Neural Circuits
Finding Visual Saliency in Continuous Spike Stream
LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem
PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRI
MoST: Motion Style Transformer between Diverse Action Contents
Personalized LoRA for Human-Centered Text Understanding
Limit of the Maximum Random Permutation Set Entropy
S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes
Identifying and interpreting non-aligned human conceptual representations using language modeling
Are You Being Tracked? Discover the Power of Zero-Shot Trajectory Tracing with LLMs!
SuPRA: Surgical Phase Recognition and Anticipation for Intra-Operative Planning
DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
On depth prediction for autonomous driving using self-supervised learning
Harmonious Group Choreography with Trajectory-Controllable Diffusion
An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
Domain Adversarial Active Learning for Domain Generalization Classification
Speeding up 6-DoF Grasp Sampling with Quality-Diversity
DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation
Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation
Cracking the neural code for word recognition in convolutional neural networks
GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection
The ALℓ0CORE Tensor Decomposition for Sparse Count Data
Can Large Language Models Automatically Score Proficiency of Written Essays?
All-in-one platform for AI R&D in medical imaging, encompassing data collection, selection, annotation, and pre-processing
Fluent: Round-efficient Secure Aggregation for Private Federated Learning
Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification
RESTORE: Towards Feature Shift for Vision-Language Prompt Learning
ClickVOS: Click Video Object Segmentation
Low-dose CT Denoising with Language-engaged Dual-space Alignment
PSS-BA: LiDAR Bundle Adjustment with Progressive Spatial Smoothing
Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning
CLEAR: Cross-Transformers with Pre-trained Language Model is All you need for Person Attribute Recognition and Retrieval
FMPAF: How Do Fed Chairs Affect the Financial Market? A Fine-grained Monetary Policy Analysis Framework on Their Language
Large Language Models on Fine-grained Emotion Detection Dataset with Data Augmentation and Transfer Learning
Textureless Object Recognition: An Edge-based Approach

All 120