Papers

New on arXiv

Fri 24 May 2024

419 papers

AMGPT: a Large Language Model for Contextual Querying in Additive ManufacturingRetrieval-augmented generation → Medical and biomedical RAG
Clustered Retrieved Augmented Generation (CRAG)Retrieval-augmented generation → RAG pipeline design and evaluation
Embedding-Aligned Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Expert-Token Resonance MoE: Bidirectional Routing with Efficiency Affinity-Driven Active SelectionMixture-of-experts → Expert routing strategies
Large Language Model Sentinel: LLM Agent for Adversarial PurificationLLM agents and tool use → Agent threats, guardrails and governance
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign UsersLLM safety and security → Vision-language and text-to-image safety
Robustifying Safety-Aligned Large Language Models through Clean Data CurationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
OLLIE: Imitation Learning from Offline Pretraining to Online FinetuningOffline RL and imitation learning from data → Imitation learning methods
How to Leverage Diverse Demonstrations in Offline Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
How Culturally Aware are Vision-Language Models?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Federated Offline Policy Optimization with Dual RegularizationOffline RL and imitation learning from data → Offline RL algorithms +1
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor FreezingDiffusion models → Robustness, privacy and adversarial aspects
Momentum-Based Federated Reinforcement Learning with Interaction and Communication EfficiencyDeep reinforcement learning methods → RL for energy, networks and operations
Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time ComplexityDiffusion models → Diffusion foundations and sampling
Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context LearningRetrieval-augmented generation → Privacy and security of RAG
BadGD: A unified data-centric framework to identify gradient descent vulnerabilitiesLLM safety and security → Backdoor and data poisoning attacks
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-ImprovementLLM reasoning → Multimodal reasoning +3
MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
ExactDreamer: High-Fidelity Text-to-3D Content Creation via Exact Score MatchingDiffusion models → 3D, point cloud and scene generation
Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward MachineDeep reinforcement learning methods → Adversarial robustness and RL in finance
Hacc-Man: An Arcade Game for Jailbreaking LLMsLLM safety and security → Jailbreaking
Score Distillation via Reparametrized DDIMDiffusion models → 3D, point cloud and scene generation
Diffusion Bridge Implicit ModelsDiffusion models → Diffusion foundations and sampling
Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video GenerationDiffusion models → Medical imaging and segmentation +1
Quality-aware Masked Diffusion Transformer for Enhanced Music GenerationDiffusion models → Audio, speech and music
Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution MapDeep reinforcement learning methods → RL for energy, networks and operations
Diff-DTI: Fast Diffusion Tensor Imaging Using A Feature-Enhanced Joint Diffusion ModelDiffusion models → Medical imaging and segmentation
Spatio-temporal Value Semantics-based Abstraction for Dense Deep Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
Looking Backward: Streaming Video-to-Video Translation with Feature BanksDiffusion models → Video generation
Wasserstein Distances, Neuronal Entanglement, and SparsityMechanistic interpretability → Circuits and mechanistic analysis
Score-based generative models are provably robust: an uncertainty quantification perspectiveDiffusion models → Diffusion foundations and sampling
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Disease-informed Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Chain-of-Thought Prompting for Demographic Inference with Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMsLLM reasoning → Hallucination detection and mitigation +1
Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse ProblemsDiffusion models → Inverse problems and image restoration
What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Class Machine Unlearning for Complex Data via Concepts Inference and Data PoisoningLLM safety and security → Machine unlearning
An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse ProblemsDiffusion models → Inverse problems and image restoration
M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal ModelsLLM reasoning → Multimodal reasoning +1
Nonlinear denoising score matching for enhanced learning of structured distributionsDiffusion models → Diffusion foundations and sampling
Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map GenerationDiffusion models → 3D, point cloud and scene generation
Neuromorphic dreaming: A pathway to efficient learning in artificial agentsWorld models → Latent dynamics models and model-based RL
Efficient Adversarial Training in LLMs with Continuous AttacksLLM safety and security → Jailbreaking
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision ModelsState-space sequence models (S4, Mamba) → Vision Mamba backbones
Transformer-XL for Long Sequence Tasks in Robotic Learning from DemonstrationOffline RL and imitation learning from data → Robot learning from demonstration
Certifiably Robust RAG against Retrieval CorruptionRetrieval-augmented generation → Privacy and security of RAG
Thinking Forward: Memory-Efficient Federated Finetuning of Language ModelsLLM reasoning → Test-time compute and efficient thinking
SEP: Self-Enhanced Prompt Tuning for Visual-Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Learning Generalizable Human Motion Generator with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Erase to Enhance: Data-Efficient Machine Unlearning in MRI ReconstructionLLM safety and security → Machine unlearning
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spacesDeep reinforcement learning methods → RL for robot locomotion and manipulation
Human-in-the-loop Reinforcement Learning for Data Quality Monitoring in Particle Physics ExperimentsDeep reinforcement learning methods → RL for energy, networks and operations
Learning to Discretize Denoising Diffusion ODEsDiffusion models → Diffusion foundations and sampling
Towards Natural Machine UnlearningLLM safety and security → Machine unlearning
Unlearning during Learning: An Efficient Federated Machine Unlearning MethodLLM safety and security → Federated unlearning and poisoning
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud AnalysisState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
TD3 Based Collision Free Motion Planning for Robot NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
Hybrid Context Retrieval Augmented Generation Pipeline: LLM-Augmented Knowledge Graphs and Vector Database for Accreditation Reporting AssistanceRetrieval-augmented generation → RAG robustness and adaptive retrieval
Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety CriticsDeep reinforcement learning methods → Safe and constrained RL
Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning ModelsLLM safety and security → Membership inference attacks
Model-free reinforcement learning with noisy actions for automated experimental control in opticsDeep reinforcement learning methods → RL for energy, networks and operations
Luban: Building Open-Ended Creative Agents via Autonomous Embodied VerificationLLM agents and tool use → Reinforcement learning for LLM agents
MambaVC: Learned Visual Compression with Selective State SpacesState-space sequence models (S4, Mamba) → Vision Mamba backbones
Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasetsKnowledge distillation → Detection and dense prediction distillation
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning RateDeep reinforcement learning methods → Deep RL algorithms and representations
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree SearchWorld models → World models for language agents
Cross-Domain Policy Adaptation by Capturing Representation MismatchDeep reinforcement learning methods → Deep RL algorithms and representations
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View SynthesizerDiffusion models → 3D, point cloud and scene generation
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced OptimizationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLMMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound GenerationDiffusion models → Audio, speech and music
Challenges and Opportunities in 3D Content GenerationDiffusion models → 3D, point cloud and scene generation
Towards Understanding the Working Mechanism of Text-to-Image Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph GuidanceDiffusion models → Image generation, text-to-image and editing
Decaf: Data Distribution Decompose Attack against Federated LearningLLM safety and security → Federated unlearning and poisoning
Enhancing Text-to-Image Editing via Hybrid Mask-Informed FusionDiffusion models → Image generation, text-to-image and editing
Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving GradientDiffusion models → Robustness, privacy and adversarial aspects +1
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer MechanismLLM reasoning → Prompting and chain-of-thought reasoning
Learning Invariant Causal Mechanism from Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ArtWeaver: Advanced Dynamic Style Integration via Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Test-Time Multimodal Backdoor Detection by Contrastive PromptingLLM safety and security → Backdoor and data poisoning attacks
Conditional Variational Auto Encoder Based Dynamic Motion for Multi-task Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
Accelerating 3D Molecule Generation via Jointly Geometric Optimal TransportDiffusion models → Flow matching, time series and science
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical GuaranteeDeep reinforcement learning methods → Adversarial robustness and RL in finance
Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem SolvingDiffusion models → Medical imaging and segmentation
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image PerceptionMultimodal LLMs / vision-language models → Image editing and quality assessment +1
iREPO: implicit Reward Pairwise Difference based Empirical Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Learning from True-False Labels via Multi-modal Prompt RetrievingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
iVideoGPT: Interactive VideoGPTs are Scalable World ModelsWorld models → Embodied and robot world models +1
NIVeL: Neural Implicit Vector Layers for Text-to-Vector GenerationDiffusion models → Diffusion foundations and sampling
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMsLLM reasoning → Test-time compute and efficient thinking +1
ODGEN: Domain-specific Object Detection Data Generation with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient InferenceRetrieval-augmented generation → Generation and context integration +1
TrojanForge: Generating Adversarial Hardware Trojan Examples Using Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance

All 419