Papers

New on arXiv

Sun 27 Oct 2024

132 papers

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans WorseLLM reasoning → Prompting and chain-of-thought reasoning
LLM Robustness Against Misinformation in Biomedical Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
TabDiff: a Mixed-type Diffusion Model for Tabular Data GenerationDiffusion models → Flow matching, time series and science
R^3AG: First Workshop on Refined and Reliable Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Generator Matching: Generative modeling with arbitrary Markov processesDiffusion models → Flow matching, time series and science
Deep Reinforcement Learning Agents for Strategic Production Policies in Microeconomic Market SimulationsDeep reinforcement learning methods → Adversarial robustness and RL in finance
Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?LLM reasoning → Reinforcement learning for reasoning
Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse AutoencodersMechanistic interpretability → SAE features and their applications
ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video GenerationDiffusion models → Video generation
Efficient Diversity-based Experience Replay for Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
What Factors Affect Multi-Modal In-Context Learning? An In-Depth ExplorationLLM reasoning → Multimodal reasoning
GrounDiT: Grounding Diffusion Transformers via Noisy Patch TransplantationDiffusion models → Image generation, text-to-image and editing
Hamiltonian Score Matching and Generative FlowsDiffusion models → Flow matching, time series and science
Understanding Communication Preferences of Information Workers in Engagement with Text-Based Conversational AgentsLLM agents and tool use → Social simulation and multi-agent debate
TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model CollaborationLLM agents and tool use → Multimodal and embodied agents
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language ModelsEfficient LLM inference and serving → Speculative decoding +1
Rethinking Data Synthesis: A Teacher Model Training Recipe with InterpretationLLM reasoning → Reasoning benchmarks and evaluation +1
Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from AudiosDiffusion models → Audio, speech and music
FoldMark: Protecting Protein Generative Models with WatermarkingLLM safety and security → Watermarking generated content and models
Wavelet-based Mamba with Fourier Adjustment for Low-light Image EnhancementState-space sequence models (S4, Mamba) → Mamba for image restoration
Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency modelOffline RL and imitation learning from data → Offline RL algorithms
GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance FieldsMixture-of-experts → Vision mixture-of-experts
Accelerating Direct Preference Optimization with Prefix SharingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
WindTunnel -- A Framework for Community Aware Sampling of Large CorporaRetrieval-augmented generation → RAG pipeline design and evaluation
EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge UpdateRetrieval-augmented generation → RAG pipeline design and evaluation
Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel DataLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Network scaling and scale-driven loss balancing for intelligent poroelastography
High quality ECG dataset based on MIT-BIH recordings for improved heartbeats classification
Accelerating Augmentation Invariance Pretraining
E(3)-invariant diffusion model for pocket-aware peptide generation
Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
CloudCast -- Total Cloud Cover Nowcasting with Machine Learning
Deconfounded Time Series Forecasting: A Causal Inference Approach
Self-Supervised Learning and Opportunistic Inference for Continuous Monitoring of Freezing of Gait in Parkinson's Disease
Language Models And A Second Opinion Use Case: The Pocket Professional
Plastic Learning with Deep Fourier Features
PViT: Prior-augmented Vision Transformer for Out-of-distribution Detection
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
Towards an LLM-Based Speech Interface for Robot-Assisted Feeding
Kernel Approximation of Fisher-Rao Gradient Flows
Egocentric and Exocentric Methods: A Short Survey
A successive approximation method in functional spaces for hierarchical optimal control problems and its application to learning
Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol
Practical Bayesian Algorithm Execution via Posterior Sampling
A Framework for Real-Time Volcano-Seismic Event Recognition Based on Multi-Station Seismograms and Semantic Segmentation Models
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
Toward Conditional Distribution Calibration in Survival Prediction
Meta-Learning Approaches for Improving Detection of Unseen Speech Deepfakes
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization
Detection of adrenal anomalous findings in spinal CT images using multi model graph aggregation
Neural rendering enables dynamic tomography
SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
SympCam: Remote Optical Measurement of Sympathetic Arousal
Sebica: Lightweight Spatial and Efficient Bidirectional Channel Attention Super Resolution Network
PaPaGei: Open Foundation Models for Optical Physiological Signals
Info-CELS: Informative Saliency Map Guided Counterfactual Explanation
SIGMA: Single Interpolated Generative Model for Anomalies
Malinowski in the Age of AI: Can large language models create a text game based on an anthropological classic?
Asynchronous Perception Machine For Efficient Test-Time-Training
Search Wide, Focus Deep: Automated Fetal Brain Extraction with Sparse Training Data
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Props for Machine-Learning Security
Fractal Signatures: Securing AI-Generated Pollock-Style Art via Intrinsic Watermarking and Blockchain
MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic music
A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing
Symbotunes: unified hub for symbolic music generative models
Self-correction is Not An Innate Capability in Language Models
Referring Human Pose and Mask Estimation in the Wild
When Less is More: Achieving Faster Convergence in Distributed Edge Machine Learning
MatViX: Multimodal Information Extraction from Visually Rich Articles
Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classification
FIRP: Faster LLM inference via future intermediate representation prediction
Improving Decision Sparsity
MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
Graph Neural Networks on Discriminative Graphs of Words
Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution
A Derivational ChainBank for Modern Standard Arabic
Unlocking Comics: The AI4VA Dataset for Visual Understanding
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
Vector Quantization Prompting for Continual Learning
TEAFormers: TEnsor-Augmented Transformers for Multi-Dimensional Time Series Forecasting
CoralSCOP-LAT: Labeling and Analyzing Tool for Coral Reef Images with Dense Mask
Integrating uncertainty quantification into randomized smoothing based robustness guarantees
MedGo: A Chinese Medical Large Language Model
YourSkatingCoach: A Figure Skating Video Benchmark for Fine-Grained Element Analysis
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis
Causal Modeling in Multi-Context Systems: Distinguishing Multiple Context-Specific Causal Graphs which Account for Observational Support
Deep Learning-Driven Microstructure Characterization and Vickers Hardness Prediction of Mg-Gd Alloys
Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss
ThunderKittens: Simple, Fast, and Adorable AI Kernels
Evaluation of uncertainty estimations for Gaussian process regression based machine learning interatomic potentials
Depth Attention for Robust RGB Tracking
Hierarchical Multiple Kernel K-Means Algorithm Based on Sparse Connectivity
Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns
Unsupervised Feature Selection Algorithm Based on Dual Manifold Re-ranking
Addressing the Pitfalls of Image-Based Structural Health Monitoring: A Focus on False Positives, False Negatives, and Base Rate Bias
Multiple kernel concept factorization algorithm based on global fusion

All 132