· ai
[Paper] An Agentic Framework for Neuro-Symbolic Programming
Integrating symbolic constraints into deep learning models could make them more robust, interpretable, and data-efficient. Still, it remains a time-consuming an...
-
- · ai
[Paper] Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty
Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor)...
- · ai
[Paper] Exploring the Performance of Large Language Models on Subjective Span Identification Tasks
Identifying relevant text spans is important for several downstream tasks in NLP, as it contributes to model explainability. While most span identification appr...
- · ai
[Paper] Grading Handwritten Engineering Exams with Multimodal Large Language Models
Handwritten STEM exams capture open-ended reasoning and diagrams, but manual grading is slow and difficult to scale. We present an end-to-end workflow for gradi...
- · ai
[Paper] Precision Autotuning for Linear Solvers via Contextual Bandit-Based RL
We propose a reinforcement learning (RL) framework for adaptive precision tuning of linear solvers, and can be extended to general algorithms. The framework is ...
- · ai
[Paper] Multi-Level Feature Fusion for Continual Learning in Visual Quality Inspection
Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in mo...
- · ai
[Paper] Detecting Performance Degradation under Data Shift in Pathology Vision-Language Model
Vision-Language Models have demonstrated strong potential in medical image analysis and disease diagnosis. However, after deployment, their performance may dete...
- · ai
[Paper] Efficient Deep Demosaicing with Spatially Downsampled Isotropic Networks
In digital imaging, image demosaicing is a crucial first step which recovers the RGB information from a color filter array (CFA). Oftentimes, deep learning is u...
- · ai
[Paper] BSAT: B-Spline Adaptive Tokenizer for Long-Term Time Series Forecasting
Long-term time series forecasting using transformers is hampered by the quadratic complexity of self-attention and the rigidity of uniform patching, which may b...
- · ai
[Paper] A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference
Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizabil...
- · ai
[Paper] TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications
Ticket troubleshooting refers to the process of analyzing and resolving problems that are reported through a ticketing system. In large organizations offering a...
- · ai
[Paper] Cost Optimization in Production Line Using Genetic Algorithm
This paper presents a genetic algorithm (GA) approach to cost-optimal task scheduling in a production line. The system consists of a set of serial processing ta...