Elastic scaling in cloud native environments is essential for maintaining service quality and resource efficiency. In practice, frequent traffic bursts and shifts in workload distributions make rule-based methods or approaches with a single optimization objective insufficient. They struggle to ensure system stability and decision reliability at the same time. To address this challenge, this study formulates elastic scaling as a risk-constrained reinforcement learning problem from a sequential decision perspective. A unified framework is used to model resource adjustment […]

Ver mais

Federated learning (FL) research increasingly relies on single-node simulations with hundreds or thousands of virtual clients, making both efficiency and reproducibility essential. Yet parallel client training often introduces nondeterminism through shared random state and scheduling variability, forcing researchers to trade throughput for reproducibility or to implement custom control logic within complex frameworks. We present BlazeFL, a lightweight framework for single-node FL simulation that alleviates this trade-off through free-threaded shared-memory execution and deterministic randomness management. BlazeFL uses thread-based parallelism […]

Ver mais

Quadruped robots are used for primary searches during the early stages of indoor fires. A typical primary search involves quickly and thoroughly looking for victims under hazardous conditions and monitoring flammable materials. However, situational awareness in complex indoor environments and rapid stair climbing across different staircases remain the main challenges for robot-assisted primary searches. In this project, we designed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize both navigation and locomotion. In the first stage, the […]

Ver mais

arXiv:2603.05521v1 Announce Type: new Abstract: We define a method how digital ecosystems (including data spaces) may autonomously define and “advertise” credentials they issue or they trust in the form of so-called ecosystem trust profiles. An ecosystem trust profile collects all (verifiable) credentials and issuers sorted by trust scope accepted (“trusted”) by a particular ecosystem. We then show how a minimal trust relation between ecosystems may be defined using ecosystem trust frameworks of different ecosystems and explore a few […]

Ver mais

arXiv:2604.01437v1 Announce Type: new Abstract: With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black boxes, making it difficult to justify the superiority of Agentic AI approaches over baselines. Furthermore, missing information in the evaluation design description frequently renders the reproduction of results infeasible. To synthesize current evaluation practices for Agentic AI in SE, this […]

Ver mais

Video Question Answering (VideoQA) presents significant challenges, demanding comprehensive understanding of dynamic visual content, object interactions, and complex temporal-causal logic. While Multimodal Large Language Models (MLLMs) offer powerful reasoning capabilities, existing approaches often provide singular, potentially flawed reasoning paths, limiting the robustness and depth of VideoQA models. To address these limitations, we propose Contextualized Diverse Reasoning (CDR), a novel framework designed to furnish VideoQA models with richer, multi-perspective auxiliary supervision. CDR comprises three key innovations: a Diverse Reasoning […]

Ver mais

Hey folks, I’m in the midst of some interview prep / learning RL (right now working through spinningup, trying to code/derive some algos from scratch, and building a few example projects) somewhat from scratch. I’ve found that having accountability is really helpful for making sure progress is made. Anyone in the same boat who wants an accountability partner? I imagine daily/regular checkins, progress on learning/projects (aka a mini “build in public”), feedback on each others plans, and even […]

Ver mais

arXiv:2604.18697v1 Announce Type: new Abstract: Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently protected against broader memorization risks. However, we show that indistinguishability properties are neither sufficient nor necessary for preventing data extraction in LLM APIs. We formalize a privacy-game separation between extraction and indistinguishability-based privacy, showing that indistinguishability and inextractability are incomparable: upper-bounding distinguishability does not upper-bound extractability. To address this […]

Ver mais

arXiv:2604.08577v1 Announce Type: new Abstract: Large Language Models (LLMs) tend to respond correctly to prompts that align to the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on multi-step reasoning problems. To address this problem, we propose a Distributionally Robust Token Optimization (DRTO) approach, which combines token-level Reinforcement Learning from Human Feedback (RLHF) with Distributionally Robust Optimization (DRO). DRTO bounds worst case token-wise rewards by […]

Ver mais

arXiv:2603.26685v1 Announce Type: new Abstract: Recent advances in computer vision facilitate fully automatic extraction of object-centric relational representations from visual-inertial data. These state representations, dubbed 3D scene graphs, are a hierarchical decomposition of real-world scenes with a dense multiplex graph structure. While 3D scene graphs claim to promote efficient task planning for robot systems, they contain numerous objects and relations when only small subsets are required for a given task. This magnifies the state space that task planners […]

Ver mais