Papers
Sun 14 Jul 2024
119 papers
- Reinforcement Learning in High-frequency Market MakingDeep reinforcement learning methods → Adversarial robustness and RL in finance
- Addressing Class Imbalance and Data Limitations in Advanced Node Semiconductor Defect Inspection: A Generative Approach for SEM ImagesDiffusion models → Flow matching, time series and science
- Affordance-Guided Reinforcement Learning via Visual PromptingDeep reinforcement learning methods → RL for robot locomotion and manipulation
- Towards Adapting Reinforcement Learning Agents to New Tasks: Insights from Q-ValuesDeep reinforcement learning methods → Deep RL algorithms and representations
- Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
- Follow the Rules: Reasoning for Video Anomaly Detection with Large Language ModelsLLM reasoning → Chain-of-thought reasoning for driving
- Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion ModelsDiffusion models → Video generation
- Disrupting Diffusion-based Inpainters with Semantic DigressionDiffusion models → Robustness, privacy and adversarial aspects
- Enhancing Weakly-Supervised Histopathology Image Segmentation with Knowledge Distillation on MIL-Based Pseudo-LabelsKnowledge distillation → Distillation for medical imaging
- What Makes and Breaks Safety Fine-tuning? A Mechanistic StudyLLM safety and security → Safety alignment, refusal and guardrails
- GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
- On Large Language Model Continual UnlearningLLM safety and security → Machine unlearning
- Key-Point-Driven Mathematical Reasoning Distillation of Large Language ModelLLM reasoning → Prompting and chain-of-thought reasoning +1
- LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
- ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
- DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge DistillationLLM safety and security → Safety alignment, refusal and guardrails
- 3DEgo: 3D Editing on the Go!Diffusion models → 3D, point cloud and scene generation
- Transferable 3D Adversarial Shape Completion using Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Multi-Granularity Semantic Revision for Large Language Model DistillationKnowledge distillation → Knowledge distillation for LLMs
- An Efficient High-Dimensional Gradient Estimator for Stochastic Differential EquationsDeep reinforcement learning methods → RL theory and sample complexity
- Revolutionizing Bridge Operation and Maintenance with LLM-based Agents: An Overview of Applications and InsightsLLM agents and tool use → General LLM agent frameworks and benchmarks
- InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion GenerationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
- Learning to Refuse: Towards Mitigating Privacy Risks in LLMsLLM safety and security → Machine unlearning
- AutoGRAMS: Autonomous Graphical Agent Modeling SoftwareLLM agents and tool use → General LLM agent frameworks and benchmarks
- Lean-STaR: Learning to Interleave Thinking and ProvingLLM reasoning → Mathematical reasoning
- LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable EnvironmentsLLM agents and tool use → Multimodal and embodied agents
- What Appears Appealing May Not be Significant! -- A Clinical Perspective of Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Artificial Intelligence from Idea to Implementation. How Can AI Reshape the Education Landscape?
- Integrating AI Tutors in a Programming Course
- Risks of ignoring uncertainty propagation in AI-augmented security pipelines
- Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View
- SENTINEL: Securing Indoor Localization against Adversarial Attacks with Capsule Neural Networks
- Deep Learning Activation Functions: Fixed-Shape, Parametric, Adaptive, Stochastic, Miscellaneous, Non-Standard, Ensemble
- Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk
- Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV
- Pre-training with Fractional Denoising to Enhance Molecular Property Prediction
- SpreadFGL: Edge-Client Collaborative Federated Graph Learning with Adaptive Neighbor Generation
- LAB-Bench: Measuring Capabilities of Language Models for Biology Research
- Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence
- Comparing Complex Concepts with Transformers: Matching Patent Claims Against Natural Language Text
- Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis
- Mapping the Scholarship of Dark Pattern Regulation: A Systematic Review of Concepts, Regulatory Paradigms, and Solutions from an Interdisciplinary Perspective
- Thyroidiomics: An Automated Pipeline for Segmentation and Classification of Thyroid Pathologies from Scintigraphy Images
- An Interpretable Neural Network for Vegetation Phenotyping with Visualization of Trait-Based Spectral Features
- Ontology-driven Reinforcement Learning for Personalized Student Support
- 3D Foundation Models Enable Simultaneous Geometry and Pose Estimation of Grasped Objects
- The Interpretation Gap in Text-to-Music Generation Models
- Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregation
- RecGS: Removing Water Caustic with Recurrent Gaussian Splatting
- Order parameters and phase transitions of continual learning in deep neural networks
- Augmented prediction of a true class for Positive Unlabeled data under selection bias
- Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation
- Does Burrows' Delta really confirm that Rowling and Galbraith are the same author?
- Numbers Matter! Bringing Quantity-awareness to Retrieval Systems
- Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning
- AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding
- Cross-Lingual Multi-Hop Knowledge Editing
- RS-NeRF: Neural Radiance Fields from Rolling Shutter Images
- psifx -- Psychological and Social Interactions Feature Extraction Package
- Towards detailed and interpretable hybrid modeling of continental-scale bird migration
- Nullpointer at CheckThat! 2024: Identifying Subjectivity from Multilingual Text Sequence
- Deep Learning Algorithms for Early Diagnosis of Acute Lymphoblastic Leukemia
- BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs
- xLSTMTime : Long-term Time Series Forecasting With xLSTM
- Asymptotic Normality of Generalized Low-Rank Matrix Sensing via Riemannian Geometry
- Visual Prompt Selection for In-Context Learning Segmentation
- Weighted Aggregation of Conformity Scores for Classification
- Efficient Facial Landmark Detection for Embedded Systems
- Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing
- PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation
- Maximum mean discrepancies of Farey sequences
- Vector Field Attention for Deformable Image Registration
- Learning to Steer Markovian Agents under Model Uncertainty
- Dominant Design Prediction with Phylogenetic Networks
- Improving Graph Out-of-distribution Generalization Beyond Causality
- Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data
- Multiple data sources and domain generalization learning method for road surface defect classification
- A3S: A General Active Clustering Method with Pairwise Constraints
- V2I-Calib: A Novel Calibration Approach for Collaborative Vehicle and Infrastructure LiDAR Systems
- Curriculum Learning for Small Code Language Models
- GRAPE: Generalizable and Robust Multi-view Facial Capture
- Unexpected Benefits of Self-Modeling in Neural Systems
- Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
- Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
- CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
- Restoring Images in Adverse Weather Conditions via Histogram Transformer
- The Hidden Influence of Latent Feature Magnitude When Learning with Imbalanced Data
- RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation
- SACNet: A Spatially Adaptive Convolution Network for 2D Multi-organ Medical Segmentation
- Look Within, Why LLMs Hallucinate: A Causal Perspective
- Mitigating Translationese in Low-resource Languages: The Storyboard Approach
- Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
- PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration
- Pattern Guided UV Recovery for Realistic Video Garment Texturing
- Optimal Kernel Choice for Score Function-based Causal Discovery
- WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models
- When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset
- MSD: A Benchmark Dataset for Floor Plan Generation of Building Complexes
- Textless Dependency Parsing by Labeled Sequence Prediction
All 119
- A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second
- TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation
- Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification
- A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classification
- STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video
- Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation
- ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots
- Rapid Biomedical Research Classification: The Pandemic PACT Advanced Categorisation Engine
- Part2Object: Hierarchical Unsupervised 3D Instance Segmentation
- Plain-Det: A Plain Multi-Dataset Object Detector
- Data Imputation using Large Language Model to Accelerate Recommendation System
- Have ASkotch: A Neat Solution for Large-scale Kernel Ridge Regression
- SpikeGS: 3D Gaussian Splatting from Spike Streams with High-Speed Camera Motion
- MKDTI: Predicting drug-target interactions via multiple kernel fusion on graph attention network
- Augmented Neural Fine-Tuning for Efficient Backdoor Purification
- HSFusion: A high-level vision task-driven infrared and visible image fusion network via semantic and geometric domain transformation
- Research Experience of an Undergraduate Student in Computer Vision and Robotics
- Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold
- LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid