Papers

New on arXiv

Tue 28 Jan 2025

242 papers

Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona InteractionLLM reasoning → Reasoning for agents, planning and code
Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare WorkersRetrieval-augmented generation → Medical and biomedical RAG
Contextually Entangled Gradient Mapping for Optimized LLM ComprehensionLLM reasoning → Test-time compute and efficient thinking
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content ModerationLLM safety and security → Jailbreaking
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language ModelRetrieval-augmented generation → Privacy and security of RAG
MDDM: A Molecular Dynamics Diffusion Model to Predict Particle Self-AssemblyDiffusion models → Flow matching, time series and science
A sketch of an AI control safety caseLLM agents and tool use → Agent threats, guardrails and governance +1
Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds DecodingWorld models → World models for language agents
Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference OptimizationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
A Contrastive Teacher-Student Framework for Novelty Detection under Style ShiftsKnowledge distillation → Detection and dense prediction distillation
Integrating Reinforcement Learning and AI Agents for Adaptive Robotic Interaction and Assistance in Dementia CareLLM agents and tool use → Medical and scientific domain agents +1
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama GenerationDiffusion models → 3D, point cloud and scene generation
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingLLM reasoning → Reinforcement learning for reasoning
IC-Portrait: In-Context Matching for View-Consistent Personalized PortraitDiffusion models → Image generation, text-to-image and editing
Scanning Trojaned Models Using Out-of-Distribution SamplesLLM safety and security → Backdoor and data poisoning attacks
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse AutoencodersMechanistic interpretability → SAE features and their applications
Scenario Understanding of Traffic Scenes Through Large Visual Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Histoires Morales: A French Dataset for Assessing Moral AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AILLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
COS(M+O)S: Curiosity and RL-Enhanced MCTS for Exploring Story Space via Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Token-by-Token Regeneration and Domain Biases: A Benchmark of LLMs on Advanced Mathematical Problem-SolvingLLM reasoning → Mathematical reasoning
Learning Mean Field Control on Sparse GraphsDeep reinforcement learning methods → Multi-agent reinforcement learning
Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
Generative diffusion models from a PDE perspectiveDiffusion models → Diffusion foundations and sampling
Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning StrategiesLLM reasoning → Reinforcement learning for reasoning
Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical SolversLLM reasoning → Reasoning benchmarks and evaluation
Multiple Abstraction Level Retrieve Augment GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language ModelsKnowledge distillation → Knowledge distillation for LLMs
On Rollouts in Model-Based Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial PurifierDiffusion models → Robustness, privacy and adversarial aspects
Irony Detection, Reasoning and Understanding in Zero-shot LearningLLM reasoning → Multimodal reasoning
HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits ProblemsLLM reasoning → Reinforcement learning for reasoning
Flow Matching: Markov Kernels, Stochastic Processes and Transport PlansDiffusion models → Flow matching, time series and science
DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
A Stochastic Dynamical Theory of LLM Self-Adversariality: Modeling Severity Drift as a Critical ProcessLLM reasoning → Test-time compute and efficient thinking
Beyond-Labels: Advancing Open-Vocabulary Segmentation With Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Improving Partially Observed Trajectories Forecasting by Target-driven Self-DistillationKnowledge distillation → Multimodal distillation
DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat GenerationDiffusion models → 3D, point cloud and scene generation
ITVTON: Virtual Try-On Diffusion Transformer Based on Integrated Image and TextDiffusion models → 3D, point cloud and scene generation
Efficient Knowledge Distillation of SAM for Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
Post-Training Quantization for Vision Mamba with k-Scaled Quantization and ReparameterizationState-space sequence models (S4, Mamba) → Vision Mamba backbones
Consistency Diffusion Models for Single-Image 3D Reconstruction with PriorsDiffusion models → 3D, point cloud and scene generation
Distilling Large Language Models for Network Active Queue ManagementKnowledge distillation → Knowledge distillation for LLMs
Dream to Drive with Predictive Individual World ModelWorld models → World models for autonomous driving +1
On the Interplay Between Sparsity and Training in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and BenchmarkDeep reinforcement learning methods → RL for autonomous driving and traffic
xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM JailbreakingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
One Head Eight Arms: Block Matrix based Low Rank Adaptation for CLIP-based Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion ModelsDiffusion models → Video generation
3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action GenerationLLM reasoning → Spatial and embodied reasoning +1
Optimizing Code Runtime Performance through Context-Aware Retrieval-Augmented GenerationRetrieval-augmented generation → RAG for code
MACI: Multi-Agent Collaborative Intelligence for Adaptive Reasoning and Temporal PlanningLLM reasoning → Reasoning for agents, planning and code +1
MME-Industry: A Cross-Industry Multimodal Evaluation BenchmarkMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Improving Vision-Language-Action Model with Online Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +2
Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine UnlearningLLM safety and security → Machine unlearning
Exploratory Mean-Variance Portfolio Optimization with Regime-Switching Market DynamicsDeep reinforcement learning methods → Adversarial robustness and RL in finance
Contextual Reinforcement in Multimodal Token Compression for Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
Large Language Model Critics for Execution-Free Evaluation of Code ChangesLLM agents and tool use → Software engineering coding agents
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
Sparse Autoencoders Trained on the Same Data Learn Different FeaturesMechanistic interpretability → SAE features and their applications
FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary UnlearningLLM safety and security → Machine unlearning
Safe Reinforcement Learning for Real-World Engine ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
CascadeV: An Implementation of Wurstchen Architecture for Video GenerationDiffusion models → Video generation
CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web NavigationLLM agents and tool use → Web, search, and research agents
Applying Ensemble Models based on Graph Neural Network and Reinforcement Learning for Wind Power ForecastingDeep reinforcement learning methods → RL for energy, networks and operations
Benchmarking Model Predictive Control and Reinforcement Learning Based Control for Legged Robot Locomotion in MuJoCo SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Policy alone is probably not the solution: A large-scale experiment on how developers struggle to design meaningful end-user explanations
The Trust Calibration Maturity Model for Characterizing and Communicating Trustworthiness of AI Systems
Adversarial Robustness of Partitioned Quantum Classifiers
Generative AI in K-12 Education: The CyberScholar Initiative
Instruction-Based Fine-tuning of Open-Source LLMs for Predicting Customer Purchase Behaviors
Balancing Content Size in RAG-Text2SQL System
LLMs Provide Unstable Answers to Legal Questions
Bridging Contrastive Learning and Domain Adaptation: Theoretical Perspective and Practical Application
A two-stage dual-task learning strategy for early prediction of pathological complete response to neoadjuvant chemotherapy for breast cancer using dynamic contrast-enhanced magnetic resonance images
DISC: Dataset for Analyzing Driving Styles In Simulated Crashes for Mixed Autonomy
HadamRNN: Binary and Sparse Ternary Orthogonal RNNs
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model
Image Velocimetry using Direct Displacement Field estimation with Neural Networks for Fluids
Divergent Emotional Patterns in Disinformation on Social Media? An Analysis of Tweets and TikToks about the DANA in Valencia
Machine learning of microstructure--property relationships in materials leveraging microstructure representation from foundational vision transformers
Towards Understanding Depth Perception in Foveated Rendering
Linguistic Analysis of Sinhala YouTube Comments on Sinhala Music Videos: A Dataset Study
Language Modelling for Speaker Diarization in Telephonic Interviews
VidSole: A Multimodal Dataset for Joint Kinetics Quantification and Disease Detection with Deep Learning
Knoop: Practical Enhancement of Knockoff with Over-Parameterization for Variable Selection
RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Deep-and-Wide Learning: Enhancing Data-Driven Inference via Synergistic Learning of Inter- and Intra-Data Representations
Testing Conditional Mean Independence Using Generative Neural Networks
Post-Training Quantization for 3D Medical Image Segmentation: A Practical Study on Real Inference Engines
Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection
A Guaranteed-Stable Neural Network Approach for Optimal Control of Nonlinear Systems
Compact Neural TTS Voices for Accessibility

All 242