Papers

New on arXiv

Sat 16 Aug 2025

141 papers

SCOPE: A Generative Approach for LLM Prompt CompressionEfficient LLM inference and serving → Prompt and context compression
Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action SpacesDeep reinforcement learning methods → RL for robot locomotion and manipulation
Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice QuestionsLLM safety and security → Prompt injection and agent security
QuickMerge++: Fast Token Merging with Autoregressive PriorEfficient LLM inference and serving → Visual token pruning in multimodal models
Benchmarking LLM-based agents for single-cell omics analysisLLM agents and tool use → Medical and scientific domain agents
RLNVR: Reinforcement Learning from Non-Verified Real-World RewardsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Demystifying Foreground-Background Memorization in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning QualityLLM reasoning → Clinical and biomedical applications
Infusing fine-grained visual knowledge to Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Simple o3: Towards Interleaved Vision-Language ReasoningLLM reasoning → Multimodal reasoning +1
Overcoming Knowledge Discrepancies: Structuring Reasoning Threads through Knowledge Balancing in Interactive ScenariosLLM reasoning → Reasoning benchmarks and evaluation
Error Propagation Mechanisms and Compensation Strategies for Quantized DiffusionDiffusion models → Diffusion foundations and sampling
MAPF-World: Action World Model for Multi-Agent Path FindingWorld models → World models for navigation +1
Generic Event Boundary Detection via Denoising DiffusionDiffusion models → Video generation
VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language ModelsRetrieval-augmented generation → Multimodal RAG
Mitigating Jailbreaks with Intent-Aware LLMsLLM safety and security → Jailbreaking
Fully Spiking Actor-Critic Neural Network for Robotic ManipulationDeep reinforcement learning methods → Spiking and neuromorphic RL
Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard ProblemsLLM reasoning → Multimodal reasoning
FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech SynthesisMixture-of-experts → Multimodal MoE models
MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product UnderstandingMixture-of-experts → Multimodal MoE models
AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured ReasoningLLM reasoning → Reasoning for agents, planning and code +1
FutureX: An Advanced Live Benchmark for LLM Agents in Future PredictionLLM agents and tool use → Financial trading and forecasting agents
Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned AnsweringMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
Human Centric General Physical Intelligence for Agile Manufacturing AutomationVision-language-action models → Generalist VLA models and benchmarks
A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and BeyondLLM agents and tool use → General LLM agent frameworks and benchmarks
CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMsLLM reasoning → Reasoning for agents, planning and code
CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text DetectionLLM agents and tool use → General LLM agent frameworks and benchmarks
Optimizing Token Choice for Code Watermarking: An RL ApproachLLM safety and security → Watermarking generated content and models
TimeSenCLIP: A Time Series Vision-Language Model for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
ExploreVLM: Closed-Loop Robot Exploration Task Planning with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic PressuresLLM agents and tool use → Social simulation and multi-agent debate
SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-SuppressDiffusion models → Robustness, privacy and adversarial aspects +1
Integrating Symbolic RL Planning into a BDI-based Autonomous UAV Framework: System Integration and SIL ValidationDeep reinforcement learning methods → RL for robot navigation and UAV control
EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
AdaRing: Towards Ultra-Light Vision-Language Adaptation via Cross-Layer Tensor Ring DecompositionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic FrameworkLLM agents and tool use → Medical and scientific domain agents
LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with MambaState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models +1
Discovering and Analyzing Stochastic Processes to Reduce Waste in Food Retail
A Fluid Antenna Enabled Physical Layer Key Generation for Next-G Wireless Networks
Observation-guided Interpolation Using Graph Neural Networks for High-Resolution Nowcasting in Switzerland
Conditional Generative Adversarial Networks Based Inertial Signal Translation
MedFormer: a data-driven model for forecasting the Mediterranean Sea
Exploring the Efficacy of Convolutional Neural Networks in Sleep Apnea Detection from Single Channel EEG
Capabilities of GPT-5 across critical domains: Is it the next breakthrough?
Multi-Modal Drift Forecasting of Leeway Objects via Navier-Stokes-Guided CNN and Sequence-to-Sequence Attention-Based Models
Few-shot Class-incremental Fault Diagnosis by Preserving Class-Agnostic Knowledge with Dual-Granularity Representations
A Novel Unified Extended Matrix for Graph Signal Processing: Theory and Application
User-Assistant Bias in LLMs
Implicit Hypergraph Neural Network
Domain Translation of a Soft Robotic Arm using Conditional Cycle Generative Adversarial Network
No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
AI sustains higher strategic tension than humans in chess
Research on Conversational Recommender System Considering Consumer Types
Modeling GRNs with a Probabilistic Categorical Framework
Utilizing the RAIN method and Graph SAGE Model to Identify Effective Drug Combinations for Gastric Neoplasm Treatment
YOLO11-CR: a Lightweight Convolution-and-Attention Framework for Accurate Fatigue Driving Detection
Scalable RF Simulation in Generative 4D Worlds
Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing
RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis
AICRN: Attention-Integrated Convolutional Residual Network for Interpretable Electrocardiogram Analysis
LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data
MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization
KP-INR: A Dual-Branch Implicit Neural Representation Model for Cardiac Cine MRI Reconstruction
DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy
Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
DualFit: A Two-Stage Virtual Try-On via Warping and Synthesis
Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine
Generative Medical Event Models Improve with Scale
STEM: Efficient Relative Capability Evaluation of LLMs through Structured Transition Samples
Enhancing 3D point accuracy of laser scanner through multi-stage convolutional neural network for applications in construction
J6: Jacobian-Driven Role Attribution for Multi-Objective Prompt Optimization in LLMs
Unified Conformalized Multiple Testing with Full Data Efficiency
Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability
Content Accuracy and Quality Aware Resource Allocation Based on LP-Guided DRL for ISAC-Driven AIGC Networks
Generalized invariants meet constitutive neural networks: A novel framework for hyperelastic materials
VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks
Robust Data Fusion via Subsampling
Large Language Models Enable Design of Personalized Nudges across Cultures
FAIRVAR: Fair Federated Learning via Variance Regularization
Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation
Q-FSRU: Quantum-Augmented Frequency-Spectral Fusion for Medical Visual Question Answering
Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases
BConformeR: A Conformer Based on Mutual Sampling for Unified Prediction of Continuous and Discontinuous Antibody Binding Sites
Active inference for action-unaware agents
WiseLVAM: A Novel Framework For Left Ventricle Automatic Measurements
AI Models for Depressive Disorder Detection and Diagnosis: A Review
FedUHD: Unsupervised Federated Learning using In-Memory Hyperdimensional Computing
InstDrive: Instance-Aware 3D Gaussian Splatting for Driving Scenes
Predicting ChatGPT Use in Assignments: Implications for AI-Aware Assessment Design
Optimizing Neural Architectures for Hindi Speech Separation and Enhancement in Noisy Environments
Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network
Universal Learning of Nonlinear Dynamics
Exploring Spatial-Temporal Dynamics in Event-based Facial Micro-Expression Analysis
Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models
A note on simulation methods for the Dirichlet-Laplace prior
Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
TBGRecall: A Generative Retrieval Model for E-commerce Recommendation Scenarios

All 141