· ai
[Paper] Provable Benefits of Sinusoidal Activation for Modular Addition
This paper studies the role of activation functions in learning modular addition with two-layer neural networks. We first establish a sharp expressivity gap: si...
-
- · ai
[Paper] ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts
Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented...
- · ai
[Paper] Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handlin...
- · ai
[Paper] Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent
We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (t...
- · ai
[Paper] Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising capabilities for au...
- · ai
[Paper] LFM2 Technical Report
We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities. Using hardware-in-the-loop archi...
- · ai
[Paper] Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning
Split learning is well known as a method for resolving data privacy concerns by training a model on distributed devices, thereby avoiding data sharing that rais...
- · ai
[Paper] MegaChat: A Synthetic Persian Q&A Dataset for High-Quality Sales Chatbot Evaluation
Small and medium-sized enterprises (SMEs) in Iran increasingly leverage Telegram for sales, where real-time engagement is essential for conversion. However, dev...
- · ai
[Paper] Learning-Augmented Online Bipartite Matching in the Random Arrival Order Model
We study the online unweighted bipartite matching problem in the random arrival order model, with $n$ offline and $n$ online vertices, in the learning-augmented...
- · ai
[Paper] Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting
We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather...
- · ai
[Paper] Agentic AI Framework for Smart Inventory Replenishment
In contemporary retail, the variety of products available (e.g. clothing, groceries, cosmetics, frozen goods) make it difficult to predict the demand, prevent s...
- · ai
[Paper] Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach
Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have...