Papers

New on arXiv

Tue 8 Apr 2025

303 papers

Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive SurveyRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion ModelDiffusion models → Diffusion foundations and sampling
BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language ModelsLLM reasoning → Causal reasoning in LLMs
Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning ContextLLM reasoning → Mathematical reasoning
Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language ModelsLLM safety and security → Watermarking generated content and models
Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical ReasoningLLM reasoning → Hallucination detection and mitigation +1
D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object RecognitionDiffusion models → 3D, point cloud and scene generation
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuningMixture-of-experts → Mixture of LoRA experts
SPIRe: Boosting LLM Inference Throughput with Speculative DecodingEfficient LLM inference and serving → Speculative decoding
Understanding Machine Unlearning Through the Lens of Mode ConnectivityLLM safety and security → Machine unlearning
Sharpness-Aware Parameter Selection for Machine UnlearningLLM safety and security → Machine unlearning
SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RLDeep reinforcement learning methods → Safe and constrained RL
Comparing Self-Disclosure Themes and Semantics to a Human, a Robot, and a Disembodied AgentLLM agents and tool use → Social simulation and multi-agent debate
An Information-Geometric Approach to Artificial CuriosityDeep reinforcement learning methods → Deep RL algorithms and representations
Accelerating LLM Inference Throughput via Asynchronous KV Cache PrefetchingEfficient LLM inference and serving → KV cache optimization
DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation PlatformDiffusion models → Flow matching, time series and science
Hogwild! Inference: Parallel LLM Generation via Concurrent AttentionEfficient LLM inference and serving → Serving systems and request scheduling
FEABench: Evaluating Language Models on Multiphysics Reasoning AbilityLLM reasoning → Spatial and embodied reasoning
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
TxGemma: Efficient and Agentic LLMs for TherapeuticsLLM agents and tool use → Medical and scientific domain agents
Heuristic Methods are Good Teachers to Distill MLPs for Graph Link PredictionKnowledge distillation → Graph neural network distillation
SkillFlow: Scalable and Efficient Agent Skill Retrieval SystemLLM agents and tool use → Agent skill learning and evolution
V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Adversarial Training of Reward ModelsLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
Multimedia and Visual Analytics in the Agentic EraLLM agents and tool use → Multimodal and embodied agents
Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent ReasoningRetrieval-augmented generation → Agentic RAG, agents and memory
Accelerating Vehicle Routing via AI-Initialized Genetic AlgorithmsDeep reinforcement learning methods → RL for games and combinatorial optimization
Robo-taxi Fleet Coordination at Scale via Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Leanabell-Prover: Posttraining Scaling in Formal ReasoningLLM reasoning → Mathematical reasoning
Trust-Region Twisted Policy ImprovementDeep reinforcement learning methods → RL theory and sample complexity
Multi-Sense Embeddings for Language Models and Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
OSDM-MReg: Multimodal Image Registration based One Step Diffusion ModelDiffusion models → Inverse problems and image restoration
CamC2V: Context-aware Controllable Video GenerationDiffusion models → Video generation
Information-Theoretic Reward Decomposition for Generalizable RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
An Empirical Study of GPT-4o Image Generation CapabilitiesDiffusion models → Image generation, text-to-image and editing
Smart Exploration in Reinforcement Learning using Bounded Uncertainty ModelsDeep reinforcement learning methods → RL theory and sample complexity
Deep RL-based Autonomous Navigation of Micro Aerial Vehicles (MAVs) in a complex GPS-denied Indoor EnvironmentDeep reinforcement learning methods → RL for robot navigation and UAV control
PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene ScenarioLLM reasoning → Chain-of-thought reasoning for driving
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
Agent Guide: A Simple Agent Behavioral Watermarking FrameworkLLM agents and tool use → Agent threats, guardrails and governance +1
Are Generative AI Agents Effective Personalized Financial Advisors?LLM agents and tool use → Financial trading and forecasting agents
On the Importance of Conditioning for Privacy-Preserving Data AugmentationDiffusion models → Robustness, privacy and adversarial aspects
PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language ModelsRetrieval-augmented generation → RAG for recommendation
Adaptive Substructure-Aware Expert Model for Molecular Property PredictionMixture-of-experts → Medical and biomedical MoE
Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive JailbreakingLLM safety and security → Vision-language and text-to-image safety
Leveraging Robust Optimization for LLM Alignment under Distribution ShiftsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Federated Unlearning Made Practical: Seamless Integration via Negated Pseudo-GradientsLLM safety and security → Federated unlearning and poisoning
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning IncentivizationLLM reasoning → Reinforcement learning for reasoning
PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference LearningMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
DefMamba: Deformable Visual State Space ModelState-space sequence models (S4, Mamba) → Vision Mamba backbones
How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLMLLM reasoning → Spatial and embodied reasoning
MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
DDT: Decoupled Diffusion TransformerDiffusion models → Diffusion foundations and sampling
LLM×MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long ResourcesLLM reasoning → Reasoning benchmarks and evaluation
Retrieval Augmented Generation with Collaborative Filtering for Personalized Text GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
QEMesh: Employing A Quadric Error Metrics-Based Representation for Mesh GenerationDiffusion models → 3D, point cloud and scene generation
Single-Agent vs. Multi-Agent LLM Strategies for Automated Student Reflection AssessmentLLM agents and tool use → Educational agents and math problem solving
STRIVE: A Think & Improve Approach with Iterative Refinement for Enhancing Question Quality EstimationLLM reasoning → Reasoning benchmarks and evaluation
Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role SeparatorsLLM safety and security → Prompt injection and agent security
On the Suitability of Reinforcement Fine-Tuning to Visual TasksLLM reasoning → Multimodal reasoning
VC-LLM: Automated Advertisement Video Creation from Raw Footage using Multi-modal LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion ModelsDiffusion models → Flow matching, time series and science
Sugar-Coated Poison: Benign Generation Unlocks LLM JailbreakingLLM safety and security → Jailbreaking
Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-TuningLLM reasoning → Reasoning benchmarks and evaluation
PTRL: Prior Transfer Deep Reinforcement Learning for Legged Robots LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM ExtractionLLM agents and tool use → General LLM agent frameworks and benchmarks
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMsLLM reasoning → Reasoning for agents, planning and code +1
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-ThoughtLLM reasoning → Multimodal reasoning
DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative DecodingEfficient LLM inference and serving → Speculative decoding
Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Multi-fidelity Reinforcement Learning Control for Complex Dynamical SystemsDeep reinforcement learning methods → RL theory and sample complexity
Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and ObservationsMixture-of-experts → MoE theory and gating functions
TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
A Lightweight Large Vision-language Model for Multimodal Medical ImagesMultimodal LLMs / vision-language models → Medical vision-language models
MicroNN: An On-device Disk-resident Updatable Vector DatabaseRetrieval-augmented generation → Vector search and ANN indexes
Outcome-Based Education: Evaluating Students' Perspectives Using Transformer
The Evolution of Rough Sets 1970s-1981
It's the same but not the same: Do LLMs distinguish Spanish varieties?
Mathematical Insights into Protein Architecture: Persistent Homology and Machine Learning Applied to the Flagellar Motor
Better artificial intelligence does not mean better models of biology
Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge
Exposure to Content Written by Large Language Models Can Reduce Stigma Around Opioid Use Disorder in Online Communities
Leveraging Auto-Distillation and Generative Self-Supervised Learning in Residual Graph Transformers for Enhanced Recommender Systems
A temporal scale transformer framework for precise remaining useful life prediction in fuel cells
InfoGain Wavelets: Furthering the Design of Graph Diffusion Wavelets
Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
Fusing Global and Local: Transformer-CNN Synergy for Next-Gen Current Estimation
SafeChat: A Framework for Building Trustworthy Collaborative Assistants and a Case Study of its Usefulness
Evaluating the Fitness of Ontologies for the Task of Question Generation
Towards Simple Machine Learning Baselines for GNSS RFI Detection
Secure Text Mail Encryption with Generative Adversarial Networks
Artificial Intelligence Index Report 2025
Exploiting Meta-Learning-based Poisoning Attacks for Graph Link Prediction
Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications
Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphs
Sparsified-Learning for High-Dimensional Heavy-Tailed Locally Stationary Time Series, Concentration and Oracle Inequalities
Deep Fair Learning: Task-Aware Fair Representations via Joint Distance-Covariance Regularization

All 303