Papers

New on arXiv

Tue 10 Dec 2024

373 papers

Research on the Application of Spark Streaming Real-Time Data Analysis System and large language model Intelligent AgentsLLM agents and tool use → Web, search, and research agents
Na'vi or Knave: Jailbreaking Language Models via Metaphorical AvatarsLLM safety and security → Jailbreaking
Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLMLLM safety and security → Jailbreaking
AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent FrameworkLLM agents and tool use → Web, search, and research agents
Preference Adaptive and Sequential Text-to-Image GenerationDeep reinforcement learning methods → RL with diffusion and flow models
Diffusion-Based Attention Warping for Consistent 3D Scene EditingDiffusion models → 3D, point cloud and scene generation
Agents for self-driving laboratories applied to quantum computingLLM agents and tool use → Web, search, and research agents
Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging EventsLLM reasoning → Reasoning for agents, planning and code +1
PAFFA: Premeditated Actions For Fast AgentsLLM agents and tool use → Web, search, and research agents
GPT-2 Through the Lens of Vector Symbolic ArchitecturesMechanistic interpretability → Circuits and mechanistic analysis
Non-Normal Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Rethinking Emotion Annotations in the Era of Large Language ModelsLLM reasoning → Audio-language model reasoning
Score Change of VariablesDiffusion models → Diffusion foundations and sampling
Score-Optimal Diffusion SchedulesDiffusion models → Diffusion foundations and sampling
3DSRBench: A Comprehensive 3D Spatial Reasoning BenchmarkLLM reasoning → Spatial and embodied reasoning
MAGE: A Multi-Agent Engine for Automated RTL Code GenerationLLM agents and tool use → Software engineering coding agents
Mask prior-guided denoising diffusion improves inverse protein foldingDiffusion models → Flow matching, time series and science
Multi-Response Preference Optimization with Augmented Ranking DatasetLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Video Motion Transfer with Diffusion TransformersDiffusion models → Video generation
Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetsDiffusion models → Diffusion and flow policies for robotics
From Slow Bidirectional to Fast Autoregressive Video Diffusion ModelsDiffusion models → Video generation
Make-A-Texture: Fast Shape-Aware Texture Generation in 3 SecondsDiffusion models → 3D, point cloud and scene generation
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataOffline RL and imitation learning from data → Offline RL algorithms +1
Repurposing Pre-trained Video Diffusion Models for Event-based Video InterpolationDiffusion models → Video generation
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse ViewpointsDiffusion models → 3D, point cloud and scene generation
SAT: Dynamic Spatial Aptitude Training for Multimodal Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Motion by Queries: Identity-Motion Trade-offs in Text-to-Video GenerationDiffusion models → Video generation
Granite GuardianLLM safety and security → Safety alignment, refusal and guardrails
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Optimizing Sensor Redundancy in Sequential Decision-Making ProblemsDeep reinforcement learning methods → RL for robot locomotion and manipulation
TRIM: Token Reduction and Inference Modeling for Cost-Effective Language GenerationEfficient LLM inference and serving → Serving systems and request scheduling
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding CustomizationLLM safety and security → Jailbreaking
TraSCE: Trajectory Steering for Concept ErasureDiffusion models → Robustness, privacy and adversarial aspects +1
Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy OptimizationOffline RL and imitation learning from data → Offline multi-agent RL
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive AnnotationsRetrieval-augmented generation → Multimodal RAG
DRUM: Learning Demonstration Retriever for Large MUlti-modal ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge GraphsRetrieval-augmented generation → RAG pipeline design and evaluation
Swarm Behavior CloningOffline RL and imitation learning from data → Imitation learning methods +1
Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion ModelDiffusion models → Medical imaging and segmentation
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Mobile Video DiffusionDiffusion models → Video generation
Unlocking the Potential of Reverse Distillation for Anomaly DetectionKnowledge distillation → Detection and dense prediction distillation
Defending Against Neural Network Model Inversion Attacks via Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
Automatic Database Configuration Debugging using Retrieval-Augmented Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
Contractive Dynamical Imitation Policies for Efficient Out-of-Sample RecoveryOffline RL and imitation learning from data → Imitation learning methods
Anomaly detection using Diffusion-based methodsDiffusion models → Flow matching, time series and science
Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic ScenariosMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
FireFlow: Fast Inversion of Rectified Flow for Image Semantic EditingDiffusion models → Image generation, text-to-image and editing
ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
LLM-guided Task and Motion Planning using Knowledge-based ReasoningLLM reasoning → Spatial and embodied reasoning
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-SequenceState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber WorldLLM reasoning → Spatial and embodied reasoning +2
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled EnvironmentWorld models → World models for language agents
Parallel Simulation for Log-concave Sampling and Score-based Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized EvaluationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERTRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Non-Progressive Influence Maximization in Dynamic Social NetworksDeep reinforcement learning methods → RL for games and combinatorial optimization
LOGen: Toward Lidar Object Generation by Point DiffusionWorld models → World modeling from LiDAR generation
Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
NeSyA: Neurosymbolic AutomataLLM reasoning → Reasoning benchmarks and evaluation
ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)LLM reasoning → Multimodal reasoning
Bidirectional Mamba state-space model for anomalous diffusionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Goal-Driven Reasoning in DatalogMTL with Magic SetsLLM reasoning → Reasoning benchmarks and evaluation
Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content GenerationLLM safety and security → Vision-language and text-to-image safety
Moderating the Generalization of Score-based Generative ModelDiffusion models → Diffusion foundations and sampling
Parseval Regularization for Continual Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
MPSI: Mamba enhancement model for pixel-wise sequential interaction Image Super-ResolutionState-space sequence models (S4, Mamba) → Vision Mamba backbones
PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flipsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
When Graph Meets Retrieval Augmented Generation for Wireless Networks: A Tutorial and Case StudyRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Effective Reward Specification in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Reinforcement Learning Policy as Macro Regulator Rather than Macro PlacerDeep reinforcement learning methods → RL for energy, networks and operations
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception PriorsDiffusion models → Inverse problems and image restoration
RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-ResolutionDiffusion models → Inverse problems and image restoration
MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal ModelsLLM reasoning → Multimodal reasoning
Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language ModelsLLM agents and tool use → Social simulation and multi-agent debate
FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction ErrorDiffusion models → Diffusion foundations and sampling
DiffCLIP: Few-shot Language-driven Multimodal ClassifierMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Maya: An Instruction Finetuned Multilingual Multimodal ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt EnsemblingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts SystemsMixture-of-experts → Efficient MoE training and inference systems
ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge
A Survey on Recent Advances in Self-Organizing Maps
Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB
Pharmacophore-guided de novo drug design with diffusion bridge
A Physics-Embedded Dual-Learning Imaging Framework for Electrical Impedance Tomography
Minimum Weighted Feedback Arc Sets for Ranking from Pairwise Comparisons
Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education
Lessons From an App Update at Replika AI: Identity Discontinuity in Human-AI Relationships
CogSimulator: A Model for Simulating User Cognition & Behavior with Minimal Data for Tailored Cognitive Enhancement
How to Choose a Threshold for an Evaluation Metric for Large Language Models
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
Generative Modeling and Data Augmentation for Power System Production Simulation
Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models
Observing Micromotives and Macrobehavior of Large Language Models
Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering
CAP: Evaluation of Persuasive and Creative Image Generation
Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation

All 373