Papers

New on arXiv

Fri 3 Jan 2025

189 papers

PersonaAI: Leveraging Retrieval-Augmented Generation and Personalized Context for AI-Driven Digital AvatarsRetrieval-augmented generation → Agentic RAG, agents and memory
AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with StructuresOffline RL and imitation learning from data → Offline RL algorithms
Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
ArtCrafter: Text-Image Aligning Style Transfer via Embedding ReframingDiffusion models → Image generation, text-to-image and editing
A Separable Self-attention Inspired by the State Space Model for Computer VisionState-space sequence models (S4, Mamba) → Vision Mamba backbones
Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech InteractionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Cross-Modal Attention Calibration for LVLM Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Structural and Statistical Audio Texture Knowledge Distillation for Acoustic ClassificationKnowledge distillation → Speech and audio distillation
Virgo: A Preliminary Exploration on Reproducing o1-like MLLMLLM reasoning → Multimodal reasoning
EnerVerse: Envisioning Embodied Future Space for Robotics ManipulationWorld models → Embodied and robot world models
QuArch: A Question-Answering Dataset for AI Agents in Computer ArchitectureLLM agents and tool use → Agent memory systems
Evaluating Scenario-based Decision-making for Interactive Autonomous Driving Using Rational Criteria: A SurveyEnd-to-end autonomous driving → Reinforcement learning for driving
Turning Logic Against Itself : Probing Model Defenses Through Contrastive QuestionsLLM reasoning → Reasoning for agents, planning and code +1
CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style AdaptationDiffusion models → Audio, speech and music
A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM ResponsesLLM agents and tool use → General LLM agent frameworks and benchmarks +1
MoColl: Agent-Based Specific and General Model Collaboration for Image CaptioningLLM agents and tool use → Multimodal and embodied agents
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language ModelsLLM safety and security → Prompt injection and agent security
SDPO: Segment-Level Direct Preference Optimization for Social AgentsLLM agents and tool use → Reinforcement learning for LLM agents +1
Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
Efficient LLM Inference with Activation Checkpointing and Hybrid CachingEfficient LLM inference and serving → Serving systems and request scheduling
Ingredients: Blending Custom Photos with Video Diffusion TransformersDiffusion models → Video generation
Nonparametric estimation of a factorizable density using diffusion modelsDiffusion models → Diffusion foundations and sampling
A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and PreconditioningDeep reinforcement learning methods → RL theory and sample complexity
SaLoRA: Safety-Alignment Preserved Low-Rank AdaptationLLM safety and security → Safety alignment, refusal and guardrails
Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual EncodersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
AgentRefine: Enhancing Agent Generalization through Refinement TuningLLM agents and tool use → General LLM agent frameworks and benchmarks
Inversely Learning Transferable Rewards via Abstracted StatesOffline RL and imitation learning from data → Inverse reinforcement learning +1
CoT-based Synthesizer: Enhancing LLM Performance through Answer SynthesisLLM reasoning → Prompting and chain-of-thought reasoning
HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
ACE: Anti-Editing Concept Erasure in Text-to-Image ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
ICPC: In-context Prompt Compression with Faster InferenceEfficient LLM inference and serving → Prompt and context compression
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based SystemsLLM safety and security → Prompt injection and agent security
Multivariate Time Series Anomaly Detection using DiffGAN ModelDiffusion models → Flow matching, time series and science
Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations
Contrastive Learning Augmented Social Recommendations
Defending Compute Thresholds Against Legal Loopholes
Custom Loss Functions in Fuel Moisture Modeling
Cyber Shadows: Neutralizing Security Threats with AI and Targeted Policy Measures
Dissecting a Small Artificial Neural Network
FLAME: Financial Large-Language Model Assessment and Metrics Evaluation
Applications of natural language processing in aviation safety: A review and qualitative analysis
Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)
A Survey on Large Language Models with some Insights on their Capabilities and Limitations
Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition
Navigation Variable-based Multi-objective Particle Swarm Optimization for UAV Path Planning with Kinematic Constraints
Classifier-Guided Captioning Across Modalities
Boosting Explainability through Selective Rationalization in Pre-trained Language Models
SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets
Tree-NET: Enhancing 2D Medical Image Segmentation Through Efficient Low-Level Feature Training
Effective LLM-Driven Code Generation with Pythoness
A hybrid marketplace of ideas
Relaxation-assisted reverse annealing on nonnegative/binary matrix factorization
Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance Recognition
How Your Location Relates to Health: Variable Importance and Interpretable Machine Learning for Environmental and Sociodemographic Data
Online Detection of Water Contamination Under Concept Drift
Learning Fricke signs from Maass form Coefficients
Applying Text Mining to Analyze Human Question Asking in Creativity Research
Instruction-Following Pruning for Large Language Models
AI-Powered Cow Detection in Complex Farm Environments
Laws of thermodynamics for exponential families
Counterfactual Explanation for Auto-Encoder Based Time-Series Anomaly Detection
The interplay between domain specialization and model size
RadHop-Net: A Lightweight Radiomics-to-Error Regression for False Positive Reduction In MRI Prostate Cancer Detection
AGGA: A Dataset of Academic Guidelines for Generative AI and Large Language Models
Active Learning Enables Generation of Molecules that Advance the Known Pareto Front
DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring
Advancing Pancreatic Cancer Prediction with a Next Visit Token Prediction Head on top of Med-BERT
Modeling COVID-19 spread in the USA using metapopulation SIR models coupled with graph convolutional neural networks
Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI
MRG: A Multi-Robot Manufacturing Digital Scene Generation Method Using Multi-Instance Point Cloud Registration
An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
Architecture for Trajectory-Based Fishing Ship Classification with AIS Data
Deep Clustering via Gradual Community Detection
3D Cloud reconstruction through geospatially-aware Masked Autoencoders
Dynamic Feature Fusion: Combining Global Graph Structures and Local Semantics for Blockchain Fraud Detection
CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System
Detecting Music Performance Errors with Transformers
Metadata Conditioning Accelerates Language Model Pre-training
MixGCN: Scalable GCN Training by Mixture of Parallelism and Mixture of Accelerators
MADGEN: Mass-Spec attends to De Novo Molecular generation
VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment
Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap
Improving Transducer-Based Spoken Language Understanding with Self-Conditioned CTC and Knowledge Transfer
On robust recovery of signals from indirect observations
Fusion-DeepONet: A Data-Efficient Neural Operator for Geometry-Dependent Hypersonic and Supersonic Flows
Abstractive Text Summarization for Contemporary Sanskrit Prose: Issues and Challenges
Bridging Classification and Segmentation in Osteosarcoma Assessment via Foundation and Discrete Diffusion Models
GoBERT: Gene Ontology Graph Informed BERT for Universal Gene Function Prediction
Transformer-Driven Inverse Problem Transform for Fast Blind Hyperspectral Image Dehazing
Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting
Mingling with the Good to Backdoor Federated Learning
Exoplanet Detection via Differentiable Rendering
Training-Free Adversarial Robustness in Computational MRI

All 189