arXiv:2602.20180v1 Announce Type: new Abstract: As sidewalk delivery robots become increasingly integrated into urban life, this paper begins with a critical provocation: Is robot labor labor? More than a rhetorical question, this inquiry invites closer attention to the social and political arrangements that robot labor entails. Drawing on ethnographic fieldwork across two smart-city districts in Seoul, we examine how delivery robot labor is collectively sustained. While robotic actions are often framed as autonomous and efficient, we show that […]

Ver mais

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL: rollouts are generated by an evolving policy, and learning is shaped by exploration and reward feedback, unlike supervised fine-tuning (SFT) with fixed trajectories. As a result, prior work often relies on manual curation or simple heuristic filters (e.g., accuracy), which can admit incorrect or […]

Ver mais

TL;DR: Zomato’s “Friend Recommendations” API allows unilateral contact syncing. By uploading a phone number, bad actors can extract a user’s restaurant recommendation history and restaurant coordinates. By mapping overlapping delivery radii, an attacker can estimate a user’s approximate physical location without their consent. GitHub Repository & Full Proof of Concept Code: https://github.com/jatin-dot-py/zomato-intelligence (Status: As of 26 Feb, the endpoints remain unpatched) Last week, I reported a privacy flaw in Zomato’s “Friend Recommendations” feature with a proof-of-concept video and […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 3 Analysis 3.1 Limitations […]

Ver mais

arXiv:2601.02454v1 Announce Type: new Abstract: Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of execution aware feedback. This paper introduces an agentic multi-model testing framework a closed-loop, self-correcting system in which a Test Generation Agent, an Execution and Analysis Agent, and a Review and Optimization Agent collaboratively generate, execute, analyze, and refine tests until convergence. By […]

Ver mais

arXiv:2601.08991v1 Announce Type: new Abstract: The ubiquity of machine learning (ML) and the demand for ever-larger models bring an increase in energy consumption and environmental impact. However, little is known about the energy scaling laws in ML, and existing research focuses on training cost — ignoring the larger cost of inference. Furthermore, tools for measuring the energy consumption of ML do not provide actionable feedback. To address these gaps, we developed Energy Consumption Optimiser (ECOpt): a hyperparameter tuner […]

Ver mais

Hello /rl folks! We are excited to announce another year of the Methods for Open Agent Systems Evaluation Initiative (MOASEI’2026) to be held at the AAMAS’2026 conference in Paphos, Cyprus in May 2026. This competition provides a unique opportunity for participants to showcase their work in decision making within the context of open agent systems to the broader multiagent systems community. We look forward to your participation and hope to see you at the competition! Many real-world applications […]

Ver mais

arXiv:2602.23576v1 Announce Type: new Abstract: Aerial manipulators extend the reach and manipulation capabilities of uncrewed multirotor aerial vehicles for inspection, agriculture, sampling, and delivery. Continuum arm aerial manipulation systems offer lightweight, dexterous, and compliant interaction opportunities. Existing designs allow manipulation only below the UAV which restricts their deployability in multiple directions and through clutter. They are also sensitive to propeller downwash. Addressing these limitations, we present Tilt-X, a continuum arm aerial manipulator that integrates a tilting mechanism, a […]

Ver mais