Papers

New on arXiv

Sun 7 Apr 2024

150 papers

X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained ClassificationLLM reasoning → Multimodal reasoning +1
How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model CollapseSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-ExpertsMixture-of-experts → MoE theory and gating functions
Percentile Criterion Optimization in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
FGAIF: Aligning Large Vision-Language Models with Fine-grained AI FeedbackMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
Shortcut-connected Expert Parallelism for Accelerating Mixture-of-ExpertsMixture-of-experts → Efficient MoE training and inference systems
Adapting LLMs for Efficient Context Processing through Soft Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?Multimodal LLMs / vision-language models → Medical vision-language models
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Towards Understanding the Influence of Reward Margin on Preference Model PerformanceLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
Multilingual Large Language Model: A Survey of Resources, Taxonomy and FrontiersLLM reasoning → Reasoning benchmarks and evaluation
Regularized Conditional Diffusion Model for Multi-Task Preference AlignmentDiffusion models → Diffusion and flow policies for robotics +1
Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End DecoderDiffusion models → Diffusion for compression and wireless
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
Convergence Analysis of Stochastic Saddle Point Mirror Descent Algorithm -- A Projected Dynamical View PointDeep reinforcement learning methods → RL theory and sample complexity
AI2Apps: A Visual IDE for Building LLM-based AI Agent ApplicationsLLM agents and tool use → Software engineering coding agents
Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMsEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies +1
ByteEdit: Boost, Comply and Accelerate Generative Image EditingDiffusion models → Image generation, text-to-image and editing
Demonstration-Enhanced Adaptable Multi-Objective Robot NavigationDeep reinforcement learning methods → RL for games and combinatorial optimization
Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain InjectionLLM safety and security → Jailbreaking
LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road AheadLLM agents and tool use → Software engineering coding agents
ShoeModel: Learning to Wear on the User-specified Shoes via Diffusion ModelDiffusion models → 3D, point cloud and scene generation
Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai LanguageRetrieval-augmented generation → Generation and context integration
Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal BudgetEfficient LLM inference and serving → KV cache optimization
Rethinking Diffusion Model for Multi-Contrast MRI Super-ResolutionDiffusion models → Medical imaging and segmentation
Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking LearningDeep reinforcement learning methods → RL for energy, networks and operations
Some variation of COBRA in sequential learning setup
A geometric framework for interstellar discourse on fundamental physical structures
Anchor Pair Selection in TDOA Positioning Systems by Door Transition Error Minimization
Simulation-Free Determination of Microstructure Representative Volume Element Size via Fisher Scores
Quantifying AI Vulnerabilities: A Synthesis of Complexity, Dynamical Systems, and Game Theory
Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
PMG : Personalized Multimodal Generation with Large Language Models
A Multi-Level Framework for Accelerating Training Transformer Models
LLM-aided explanations of EDA synthesis errors
Dynamic Quality-Diversity Search
Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach
CSA-Trans: Code Structure Aware Transformer for AST
Efficient Gradient Estimation for Parameterized Quantum Systems with Lie Algebraic Symmetries
Reconstructing Retinal Visual Images from 3T fMRI Data Enhanced by Unsupervised Learning
VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module
LHU-Net: a Lean Hybrid U-Net for Cost-efficient, High-performance Volumetric Segmentation
StockGPT: A GenAI Model for Stock Prediction and Trading
Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?
A Note on LoRA
DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models
On the Uniqueness of Solution for the Bellman Equation of LTL Objectives
QRscript: Embedding a Programming Language in QR codes to support Decision and Management
Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind
Test-Time Training for Depression Detection
AirShot: Efficient Few-Shot Detection for Autonomous Exploration
A Structure-Guided Gauss-Newton Method for Shallow ReLU Neural Network
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
New methods to compute the generalized chi-square distribution
Automated Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy from DWI Data
A robust assessment for invariant representations
TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis
Facial Affective Behavior Analysis with Instruction Tuning
Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint
PlateSegFL: A Privacy-Preserving License Plate Detection Using Federated Segmentation Learning
Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
PathFinder: Attention-Driven Dynamic Non-Line-of-Sight Tracking with a Mobile Robot
Scalable and Efficient Hierarchical Visual Topological Mapping
DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
Hyperbolic Learning with Synthetic Captions for Open-World Detection
MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
Towards Reliable and Empathetic Depression-Diagnosis-Oriented Chats
Camera-Based Remote Physiology Sensing for Hundreds of Subjects Across Skin Tones
Dual-Scale Transformer for Large-Scale Single-Pixel Imaging
Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM
Efficient Surgical Tool Recognition via HMM-Stabilized Deep Learning
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detection
Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning
CAVIAR: Categorical-Variable Embeddings for Accurate and Robust Inference
Neural Network Modeling for Forecasting Tourism Demand in Stopi'ca Cave: A Serbian Cave Tourism Study
FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation
How to characterize imprecision in multi-view clustering?
Temporal Generalization Estimation in Evolving Graphs
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
A Two Dimensional Feature Engineering Method for Relation Extraction
High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning
SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning
Gull: A Generative Multifunctional Audio Codec
AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment
Chiplet Placement Order Exploration Based on Learning to Rank with Graph Representation
Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring
Fuzzy K-Means Clustering without Cluster Centroids
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models
Anomaly Detection in Electrocardiograms: Advancing Clinical Diagnosis Through Self-Supervised Learning
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
GvT: A Graph-based Vision Transformer with Talking-Heads Utilizing Sparsity, Trained from Scratch on Small Datasets

All 150