arXiv:2605.00827v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP). In prevailing architectures, the agent must reason about every tool invocation in every session, consuming tokens proportional to the number of actions performed–even when the task has been solved before. […]
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
arXiv:2605.01874v1 Announce Type: cross Abstract: The performance of machine learning models often relies on large labeled datasets; however, data collected from diverse sources can contain label noise. Recent work has shown that, in noisy settings, there may exist a subset of the training data on which models can achieve performance comparable to training on a […]
Capture Timing-Attention of Events in Clinical Time Series
arXiv:2602.10385v3 Announce Type: replace-cross Abstract: Automatically discovering personalized sequential events from large-scale time-series data is crucial for enabling precision medicine in clinical research, yet it remains a formidable challenge even for contemporary AI models. For example, while transformers capture rich associations, they are mostly agnostic to event timing and ordering, thereby bypassing potential causal reasoning. […]
DocSync: Agentic Documentation Maintenance via Critic-Guided Reflexion
arXiv:2605.02163v1 Announce Type: cross Abstract: Software documentation frequently drifts from executable logic as codebases evolve, creating technical debt that degrades maintainability and causes downstream API misuse. While static analysis tools can detect the absence of documentation, they cannot evaluate its semantic consistency. Conversely, standard Large Language Models (LLMs) offer generative flexibility but frequently hallucinate when […]
Online Generalised Predictive Coding
arXiv:2605.02675v1 Announce Type: cross Abstract: This paper introduces an extension of generalised filtering for online applications. Generalised filtering refers to data assimilation schemes that jointly infer latent states, learn unknown model parameters, and estimate uncertainty in an integrated framework — e.g., estimate state and observation noise — at the same time (i.e., triple estimation). This […]
SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution
arXiv:2508.18983v3 Announce Type: replace Abstract: The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited device memory, making dynamic expert offloading essential. Unlike prior work that treats offloading […]
RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
arXiv:2605.00421v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise in radiology but their deployment is limited by computational requirements that preclude use in resource-constrained clinical environments. We investigate whether small language models (SLMs) of 3-4 billion parameters can achieve strong multi-task radiology performance through LoRA fine-tuning, enabling deployment on consumer-grade CPUs. We train […]
LLM-enabled Social Agents
arXiv:2605.02335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communicate and deliberate through natural language. Yet fluent language use does not by itself yield socially intelligible behaviour. Most current systems remain weakly grounded in roles, norms, intentions, and contextual constraints, limiting […]
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
arXiv:2601.23286v2 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we introduce VideoGPA (Video Geometric […]
aerial-autonomy-stack — a Faster-than-real-time, Autopilot-agnostic, ROS2 Framework to Simulate and Deploy Perception-based Drones
arXiv:2602.07264v2 Announce Type: replace-cross Abstract: Unmanned aerial vehicles are rapidly transforming multiple applications, from agricultural and infrastructure monitoring to logistics and defense. Introducing greater autonomy to these systems can simultaneously make them more effective as well as reliable. Thus, the ability to rapidly engineer and deploy autonomous aerial systems has become of strategic importance. In […]
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
arXiv:2604.28123v2 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduces distributional drift that neither preserves the model’s original capabilities nor faithfully matches the supervision distribution. This problem is further amplified in multimodal reasoning, […]
Green Energy Management for Sustainable Data Centers Using Deep Reinforcement Learning
arXiv:2507.21153v2 Announce Type: replace-cross Abstract: The exponential growth of digital services has positioned data centers among the most energy-intensive infrastructures in the modern economy, raising critical concerns regarding operational costs, carbon emissions, and the sustainable integration of renewable energy sources. This paper proposes a novel Deep Reinforcement Learning (DRL)-based energy management framework for data centers, […]