arXiv:2605.04396v1 Announce Type: cross Abstract: Recent work has shown that Transformers’ compositional generalization is governed by emphcomplexity control, initialization scale and weight decay, which steers training toward low-complexity reasoning solutions rather than high-complexity memorization. Existing analyses, however, treat complexity control as a single static hyperparameter choice, leaving open emphwhen during training this control is actually […]
Misaligned by Reward: Socially Undesirable Preferences in LLMs
arXiv:2605.05003v1 Announce Type: cross Abstract: Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited insight into whether these models capture socially desirable preferences. As a result, important failures in social alignment can remain hidden. […]
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
arXiv:2605.04363v1 Announce Type: cross Abstract: TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting to the majority class in the training dataset. To address this limitation, we propose DistPFN, the […]
ARMATA: Auto-Regressive Multi-Agent Task Assignment
arXiv:2605.04225v1 Announce Type: cross Abstract: Coordinating multi-agent systems over spatially distributed areas requires solving a complex hierarchical problem: first distributing areas among agents (allocation) and subsequently determining the optimal visitation order (routing). Existing methods typically decouple these stages ignoring inter-stage dependencies or rely on decentralized heuristics that lack global context. In this work, we propose […]
Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
arXiv:2605.04341v1 Announce Type: cross Abstract: We study distillation for large language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally efficient at inference time. While prior approaches to parameter-efficient distillation, such as LoRA, reduce adaptation cost, they leave the dense backbone unchanged and […]
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
arXiv:2512.03847v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex and unreliable supervision signals can destabilize training and harm generalization. While existing approaches such as worst-case optimization (e.g., RFQI, CQL) and mean-based methods (e.g., PPO, GRPO) can […]
Centrality-Based Pruning for Efficient Echo State Networks
arXiv:2603.20684v2 Announce Type: replace-cross Abstract: Echo State Networks (ESNs) are a reservoir computing framework widely used for nonlinear time-series prediction. However, despite their effectiveness, randomly initialized reservoirs often contain redundant nodes, leading to unnecessary computational overhead and reduced efficiency. In this work, we propose a graph centrality-based pruning approach that interprets the reservoir as a […]
SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
arXiv:2605.01720v2 Announce Type: replace-cross Abstract: Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings. While such resources are important for semantic understanding, they do not directly provide a unified interface for open-world recognition and translation, or for modern pose-driven sign language […]
Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework
arXiv:2605.05055v1 Announce Type: cross Abstract: Localization in 5G and 6G networks is essential for important use cases such as intelligent transportation, smart factories, and smart cities. Although deep learning has enabled improving localization accuracy, depending on the deployment scenario and the effort required for dataset collection campaigns on a given infrastructure, the training process for […]
Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
arXiv:2508.02115v4 Announce Type: replace-cross Abstract: Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. Existing backdoor detection techniques fall into two categories, passive and proactive, depending on whether the server proactively intervenes in […]
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
arXiv:2602.17753v2 Announce Type: replace-cross Abstract: Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and inconsistently documented, posing obstacles to both researchers and policymakers. To address these challenges, this paper presents the 2025 […]
Optimizing Split Learning Latency in TinyML-Based IoT Systems
arXiv:2507.16594v2 Announce Type: replace-cross Abstract: Split learning (SL) addresses the limitation of running deep learning inference directly on low-power edge/IoT nodes, in which it executes part of the inference process on the sensor and offloading the remainder to a companion device. Despite its promise, the inference latency of SL on constrained hardware under realistic low-power […]