Papers

New on arXiv

Wed 10 Apr 2024

225 papers

Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel DecodingEfficient LLM inference and serving → Speculative decoding
Apollonion: Profile-centric Dialog AgentLLM agents and tool use → General LLM agent frameworks and benchmarks
Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Structured Reinforcement Learning for Media Streaming at the Wireless EdgeDeep reinforcement learning methods → RL for energy, networks and operations
GoodDrag: Towards Good Practices for Drag Editing with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
BRAVE: Broadening the visual encoding of vision-language modelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth DiffusionDiffusion models → 3D, point cloud and scene generation
Reward Learning from Suboptimal Demonstrations with Applications in Surgical ElectrocauteryOffline RL and imitation learning from data → Robot learning from demonstration
Move Anything with Layered Scene DiffusionDiffusion models → Image generation, text-to-image and editing
Scaling Laws for Data Filtering -- Data Curation cannot be Compute AgnosticMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
How Consistent are Clinicians? Evaluating the Predictability of Sepsis Disease Progression with Dynamics ModelsDeep reinforcement learning methods → RL for clinical treatment and surgery
Towards a Game-theoretic Understanding of Explanation-based Membership Inference AttacksLLM safety and security → Membership inference attacks
3DMambaComplete: Exploring Structured State Space Model for Point Cloud CompletionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and DetectionDeep reinforcement learning methods → Deep RL algorithms and representations
VLLMs Provide Better Context for Emotion Understanding Through Common Sense ReasoningLLM reasoning → Audio-language model reasoning
LaPlaSS: Latent Space Planning for Stochastic SystemsLLM agents and tool use → Agent threats, guardrails and governance
Groundedness in Retrieval-augmented Long-form Generation: An Empirical StudyRetrieval-augmented generation → RAG robustness and adaptive retrieval
ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain ModelingMultimodal LLMs / vision-language models → Medical vision-language models
Generative inpainting of incomplete Euclidean distance matrices of trajectories generated by a fractional Brownian motionDiffusion models → 3D, point cloud and scene generation
Improving Language Model Reasoning with Self-motivated LearningLLM reasoning → Test-time compute and efficient thinking
Deep Reinforcement Learning for Mobile Robot Path PlanningDeep reinforcement learning methods → RL for robot navigation and UAV control
HRVDA: High-Resolution Visual Document AssistantMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Superposition Prompting: Improving and Accelerating Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
Vision-Language Model-based Physical Reasoning for Robot Liquid PerceptionLLM reasoning → Spatial and embodied reasoning +1
SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
Fine color guidance in diffusion models and its application to image compression at extremely low bitratesDiffusion models → Image generation, text-to-image and editing
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet DiffusionDiffusion models → 3D, point cloud and scene generation
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style TransferDiffusion models → Image generation, text-to-image and editing
ComPC: Completing a 3D Point Cloud with 2D Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
Not All Contexts Are Equal: Teaching LLMs Credibility-aware GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Uncertainty-aware Medical Diagnostic Phrase Identification and GroundingMultimodal LLMs / vision-language models → Medical vision-language models
Urban Architect: Steerable 3D Urban Scene Generation with Layout PriorDiffusion models → 3D, point cloud and scene generation
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent SpaceDiffusion models → Discrete and text diffusion
Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Disguised Copyright Infringement of Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural KnowledgeLLM safety and security → Prompt injection and agent security
Efficient Denoising using Score Embedding in Score-based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
A Robust Power Model Training Framework for Cloud Native Runtime Energy Metric Exporter
Benchmarking Semantic Communications for Image Transmission Over MIMO Interference Channels
"Sora is Incredible and Scary": Emerging Governance Challenges of Text-to-Video Generative AI Models
Automating Patch Set Generation from Code Review Comments Using Large Language Models
Fairness Evolution in Continual Learning for Medical Imaging
PROflow: An iterative refinement model for PROTAC-induced structure prediction
Unveiling Nonlinear Dynamics in Catastrophe Bond Pricing: A Machine Learning Perspective
NeuroNet: A Novel Hybrid Self-Supervised Learning Framework for Sleep Stage Classification Using Single-Channel EEG
RSSI Estimation for Constrained Indoor Wireless Networks using ANN
Reducing Human-Robot Goal State Divergence with Environment Design
A Strategy Transfer and Decision Support Approach for Epidemic Control in Experience Shortage Scenarios
DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models
Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models
Analyzing the Performance of Large Language Models on Code Summarization
AI-Guided Feature Segmentation Techniques to Model Features from Single Crystal Diamond Growth
ONNXPruner: ONNX-Based General Model Pruning Adapter
Enhanced Cooperative Perception for Autonomous Vehicles Using Imperfect Communication
An inclusive review on deep learning techniques and their scope in handwriting recognition
Differentiable Search for Finding Optimal Quantization Strategy
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks
Incorporating Explanations into Human-Machine Interfaces for Trust and Situation Awareness in Autonomous Vehicles
Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI
LLMs in Biomedicine: A study on clinical Named Entity Recognition
Improving Multi-Center Generalizability of GAN-Based Fat Suppression using Federated Learning
Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees
Differentially Private GANs for Generating Synthetic Indoor Location Data
Gradient Networks
A solution for the mean parametrization of the von Mises-Fisher distribution
GANsemble for Small and Imbalanced Data Sets: A Baseline for Synthetic Microplastics Data
FairEM360: A Suite for Responsible Entity Matching
Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos
Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention
Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements
Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping
PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores
A Modified Depolarization Approach for Efficient Quantum Machine Learning
Rethinking Perceptual Metrics for Medical Image Translation
Spatial Transfer Learning for Estimating PM2.5 in Data-poor Regions
AI-Guided Defect Detection Techniques to Model Single Crystal Diamond Growth
We're Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text
A Deep Learning Method for Predicting Mergers and Acquisitions: Temporal Dynamic Industry Networks
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers
Certifying almost all quantum states with few single-qubit measurements
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition
UMBRAE: Unified Multimodal Brain Decoding
Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective
A Foundation Model for Zero-shot Logical Query Reasoning
VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA
A predictive machine learning force field framework for liquid electrolyte development
Self-supervised Monocular Depth Estimation on Water Scenes via Specular Reflection Prior
A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks
Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory
Using Neural Networks to Model Hysteretic Kinematics in Tendon-Actuated Continuum Robots
PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System

All 225