The Morning
From the arXiv
LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization
his paper introduces Agentic AI, powered by LLMs, as a novel approach for autonomous control of 5G/6G networks, moving beyond traditional rule-based automation. It bridges the gap in existing research by detailing how agentic capabilities can be integrated with network control planes, protocols, and standardization efforts. The contribution lies in providing a comprehensive framework and survey for developing and deploying these intelligent, goal-driven network agents.
Understanding Reasoning from Pretraining to Post-Training
This paper investigates how pretraining choices influence the effectiveness of reinforcement learning (RL) for improving large language model (LLM) reasoning. Using chess as a controlled environment, the authors demonstrate that pretraining scale and data sign…
QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides
This paper addresses the instability of using low-precision NVFP4 for Reinforcement Learning (RL) rollouts in Mixture-of-Experts (MoE) models. The core method, QUADS, stabilizes NVFP4 RL by aligning quantization errors between the rollout and training processe…
DSWorld: A Data Science World Model for Efficient Autonomous Agents
This paper introduces DSWorld, a Data Science World Model designed to predict the outcomes of data science operations before execution, thereby reducing costly trial-and-error. The core method involves constructing structured states, routing operations efficie…
Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities
This paper evaluates open-weight Large Language Models (LLMs) for automatically generating structured threat information (STIX) from plain-text descriptions of vulnerabilities in Connected and Autonomous Vehicles (CAVs). The core method involves creating a dat…
Knowledge-Centric Agents for Workflow Generation
This paper proposes a **knowledge-centric framework** for generating complex visual creation workflows, moving beyond simple text-to-JSON generation. The core method involves **kno…
CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach
This paper proposes a sentiment-augmented deep reinforcement learning approach for active cryptocurrency and stock trading. The core method involves training agents using technical…
More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
This paper demonstrates that a general-purpose vision-language model, trained at a large scale with diverse remote sensing data and tasks, can achieve state-of-the-art performance …
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization
PagedWeight addresses the memory bottleneck in serving Mixture-of-Experts (MoE) LLMs by dynamically quantizing expert weights at runtime. This method intelligently balances the pre…
An MLIR-Based Compilation Method for Large Language Models
This paper introduces an MLIR-based compilation method for Large Language Models (LLMs) to address deployment challenges on AI accelerators. It utilizes two dialects: TopOp for hig…
The Town Square
A developer replaced a $120,000 bowling center system with a $1,600 setup using ESP32 microcontrollers.
Workshops
ktransformers is a flexible framework for optimizing LLM inference and fine-tuning across diverse hardware, enabling efficient experimentation with various acceleration techniques.
This repository provides a hands-on guide to building and deploying AI systems from the ground up, focusing on practical application and sharing knowledge.
