Machine learning systems increasingly make life-changing decisions about individuals, such as loan approvals, hiring, and cheating detection, raising a pressing question: how can individuals respond to negative decisions made by these opaque systems? While explainable artificial intelligence (XAI) has largely focused o...
Timo Freiesleben, Kristof Meding, Gunnar König· Proceedings of the AAAI/ACM...· 0 citations
This review summarizes contemporary evidence, evolving indications, technical innovations, and future directions in wrist arthroscopy, highlighting its growing role as a central component of modern hand and wrist surgery.
Parker H. Johnsen, A. B. Chhabra, Brent R. DeGeorge· Journal of Hand Surgery Glob...· 0 citations
Incident response planning is critical for restoring compromised software systems. Existing AIOps methods automate fault diagnosis and remediation and adapt response using feedback, but lack a unified decision basis across planning and execution. This limits their ability to maintain incident state and align actions wi...
Hanlin Jiang, Jionghao Huang, Shaofei Li et al.· 0 citations
Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids. This requires curative curtailment methods that can operate under sparse observability, noisy measurements, and imperfect grid models. Unlike prior end-to-end reinforcem...
Josef Hoppe, Sarra Bouchkati, Farah Nasr et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set. For neural networks, certified training methods based purely on tight relaxation bounds produce networks t...
Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma· 0 citations
The Spec Growth Engine is presented, a lightweight framework that addresses both failure modes through a machine-readable spec graph whose nodes carry explicit contract/design separation, a Spine context assembler that scopes agent context to an ownership path, a vertical-slice growth protocol that enforces hardest-fir...
Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced membership inference. But if output-level success can coexist with retraining-inconsistent residuals in representation space, what kind of forgetting are current evaluations actually certifying? We study this que...
Teresa Pui Yee Yong, Win Kent Ong, Chee Seng Chan· 0 citations
Robots deployed in realistic settings will accumulate experience across many sessions and tasks over their deployment. The robot's tasks may often require it to remember information from multiple sessions ago, making long-context robot memory important for real-world deployments. However, most robot-memory benchmarks t...
Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-specific demonstrations must generalize beyond that object, otherwise data collection requirements become intractable. Recently, fine-tuning of pre-trained billion-parameter...
Nikolaos Tsagkas, Andreas Sochopoulos, Chris Xiaoxuan Lu et al.· 0 citations
Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms...
A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior. However, raw neurons are polysemantic, making learned circuits hard to interpret. Sparse autoencoder (SAE) features alleviate this, but their high dimensional...
Naiyu Yin, Dennis Wei, Tian Gao et al.· 0 citations
Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is challenging, as reinforcement learning often suffers from sparse rewards and weak credit assignment despite matching the prompt-only inference setting, while supervised fine-tunin...
Zhenbang Du, Jun Luo, Zhiwei Zheng et al.· 0 citations
