Papers

New on arXiv

Sat 8 Jun 2024

122 papers

QCQA: Quality and Capacity-aware grouped Query AttentionEfficient LLM inference and serving → KV cache optimization
Benchmarking Neural Decoding Backbones towards Enhanced On-edge iBCI ApplicationsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Creativity Has Left the Chat: The Price of Debiasing Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Enhanced Flight Envelope Protection: A Novel Reinforcement Learning ApproachDeep reinforcement learning methods → Safe and constrained RL
A Survey on Hybrid Motion Planning Methods for Automated Driving SystemsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
Autoregressive Diffusion Transformer for Text-to-Speech SynthesisDiffusion models → Audio, speech and music
Online DPO: Online Direct Preference Optimization with Fast-Slow ChasingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical ModelingLLM reasoning → Reasoning for agents, planning and code +1
Towards a Benchmark for Causal Business Process Reasoning with LLMsLLM reasoning → Reasoning for agents, planning and code
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical MannerLLM safety and security → Jailbreaking
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Online Policy Distillation with Decision-AttentionKnowledge distillation → On-policy and self-distillation for LLMs +1
Revisiting Non-Autoregressive Transformers for Efficient Image SynthesisDiffusion models → Diffusion foundations and sampling
DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation ModelsEfficient LLM inference and serving → Early exit and edge inference
Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RLState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
Diffusion-based Reinforcement Learning for Dynamic UAV-assisted Vehicle Twins Migration in Vehicular MetaversesDeep reinforcement learning methods → RL for energy, networks and operations
3D MRI Synthesis with Slice-Based Latent Diffusion Models: Improving Tumor Segmentation Tasks in Data-Scarce RegimesDiffusion models → Medical imaging and segmentation
ChatSR: Multimodal Large Language Models for Scientific Formula DiscoveryMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Mean-field Chaos Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Experimenting with Multi-Agent Software Development: Towards a Unified PlatformLLM agents and tool use → Software engineering coding agents
Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue ManagementDeep reinforcement learning methods → RL for energy, networks and operations
MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme InterventionLLM safety and security → Safety alignment, refusal and guardrails
LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer GuidanceDiffusion models → Audio, speech and music
Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget ScenariosKnowledge distillation → Knowledge distillation for LLMs
LoCoCo: Dropping In Convolutions for Long Context CompressionEfficient LLM inference and serving → KV cache optimization
CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series ForecastingState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
A Nested Model for AI Design and Validation
Coupling Machine Learning with Ontology for Robotics Applications
Neural Appearance Modeling From Single Images
A Comprehensive Evaluation of Generative Models in Calorimeter Shower Simulation
Solar Power Prediction Using Satellite Data in Different Parts of Nepal
On the Worst Prompt Performance of Large Language Models
Transfer Entropy in Graph Convolutional Neural Networks
Hinge-FM2I: An Approach using Image Inpainting for Interpolating Missing Data in Univariate Time Series
A Survey of Features Used for Representing Black-box Single-objective Continuous Optimization
Rapid Review of Generative AI in Smart Medical Applications
Understanding Inhibition Through Maximally Tense Images
Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
CERET: Cost-Effective Extrinsic Refinement for Text Generation
Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction
Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts
Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
Automata Extraction from Transformers
ThatiAR: Subjectivity Detection in Arabic News Sentences
Exploring the Benefits of Tokenization of Discrete Acoustic Units
Training Through Failure: Effects of Data Consistency in Parallel Machine Learning Training
Privacy-Preserving Optimal Parameter Selection for Collaborative Clustering
VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding
Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
PAPR in Motion: Seamless Point-level 3D Scene Interpolation
Exploring Adversarial Robustness of Deep State Space Models
Enhancing Adversarial Transferability via Information Bottleneck Constraints
Mmm whatcha say? Uncovering distal and proximal context effects in first and second-language word perception using psychophysical reverse correlation
A Two-Stage Adverse Weather Semantic Segmentation Method for WeatherProof Challenge CVPR 2024 Workshop UG2+
Representation Learning with Conditional Information Flow Maximization
I-SIRch: AI-Powered Concept Annotation Tool For Equitable Extraction And Analysis Of Safety Insights From Maternity Investigations
G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes
Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities
Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
Training-Free Robust Interactive Video Object Segmentation
Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networks
Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging
RandONet: Shallow-Networks with Random Projections for learning linear and nonlinear operators
On Uniform, Bayesian, and PAC-Bayesian Deep Ensembles
Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity Recognition
Design of reliable technology valuation model with calibrated machine learning of patent indicators
Novel Approach to Intrusion Detection: Introducing GAN-MSCNN-BILSTM with LIME Predictions
Finite-Sample Identification of Linear Regression Models with Residual-Permuted Sums
A Scalable and Near-Optimal Conformance Checking Approach for Long Traces
Unsupervised learning of Data-driven Facial Expression Coding System (DFECS) using keypoint tracking
MaTableGPT: GPT-based Table Data Extractor from Materials Science Literature
Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
Baking Symmetry into GFlowNets
Recent advancements in computational morphology : A comprehensive survey
Multi-attribute Auction-based Resource Allocation for Twins Migration in Vehicular Metaverses: A GPT-based DRL Approach
Discover Your Neighbors: Advanced Stable Test-Time Adaptation in Dynamic World
Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes
Natural Language-Oriented Programming (NLOP): Towards Democratizing Software Creation
Robust Conformal Prediction Using Privileged Information
Layered Image Vectorization via Semantic Simplification
Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions
Dynamic Importance Learning using Fisher Information Matrix (FIM) for Nonlinear Dynamic Mapping
Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey
DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
Adversarial flows: A gradient flow characterization of adversarial attacks
LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis
Planning Like Human: A Dual-process Framework for Dialogue Planning
Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization
VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect
Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
RAPID: Robust APT Detection and Investigation Using Context-Aware Deep Learning
Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization
Flexible and Adaptable Summarization via Expertise Separation

All 122