Frayed RoPE and Long Inputs: A Geometric Perspective
arXiv:2603.18017v1 Announce Type: new
Abstract: Rotary Positional Embedding (RoPE) is a widely adopted technique for encoding position in language models, which, while effective, causes performance breakdown when input length exceeds training length. Prior analyses assert (rightly) that long inputs...
Engineering Verifiable Modularity in Transformers via Per-Layer Supervision
arXiv:2603.18029v1 Announce Type: new
Abstract: Transformers resist surgical control. Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage. This Hydra effect renders interpretability illusory: w...
InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model
arXiv:2603.18031v1 Announce Type: new
Abstract: Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic complexity, whereas M...
Taming Epilepsy: Mean Field Control of Whole-Brain Dynamics
arXiv:2603.18035v1 Announce Type: new
Abstract: Controlling the high-dimensional neural dynamics during epileptic seizures remains a significant challenge due to the nonlinear characteristics and complex connectivity of the brain. In this paper, we propose a novel framework, namely Graph-Regularize...
DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models
arXiv:2603.18048v1 Announce Type: new
Abstract: Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematic...
arXiv:2603.18073v1 Announce Type: new
Abstract: Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new knowledge fro...
Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction
arXiv:2603.18085v1 Announce Type: new
Abstract: Recent incidents have highlighted alarming cases where human-AI interactions led to negative psychological outcomes, including mental health crises and even user harm. As LLMs serve as sources of guidance, emotional support, and even informal therapy,...
Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI
arXiv:2603.18104v1 Announce Type: new
Abstract: Prevailing AI training infrastructure assumes reverse-mode automatic differentiation over IEEE-754 arithmetic. The memory overhead of training relative to inference, optimizer complexity, and structural degradation of geometric properties through trai...
Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows
arXiv:2603.18122v1 Announce Type: new
Abstract: Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is converted to code ...
How can life sciences organizations overcome rising costs, regulatory complexity, and data silos to bring therapies to market faster, without compromising patient safety, and could AI be the key to doing so responsibly?
At NVIDIA’s GTC 2026, CEO Jensen Huang laid out a sweeping vision for AI’s next era. From chips and agent frameworks to robotics and real-time graphics, Huang’s keynote made one thing clear: The future of AI will be built on infrastructure, and NVIDIA intends to own it.
A foundation model for electrodermal activity data
arXiv:2603.16878v1 Announce Type: new
Abstract: Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and open...
Federated Multi Agent Deep Learning and Neural Networks for Advanced Distributed Sensing in Wireless Networks
arXiv:2603.16881v1 Announce Type: new
Abstract: Multi-agent deep learning (MADL), including multi-agent deep reinforcement learning (MADRL), distributed/federated training, and graph-structured neural networks, is becoming a unifying framework for decision-making and inference in wireless systems w...
Multi-Agent Reinforcement Learning for Dynamic Pricing: Balancing Profitability,Stability and Fairness
arXiv:2603.16888v1 Announce Type: new
Abstract: Dynamic pricing in competitive retail markets requires strategies that adapt to fluctuating demand and competitor behavior. In this work, we present a systematic empirical evaluation of multi-agent reinforcement learning (MARL) approaches-specifically...
From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning
arXiv:2603.16901v1 Announce Type: new
Abstract: Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall...
Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
arXiv:2603.17021v1 Announce Type: new
Abstract: Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model-based planning approaches, this problem conceptualization process ofte...
Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
arXiv:2603.17112v1 Announce Type: new
Abstract: A common architectural pattern in advanced AI reasoning systems is the symbolic graph network: specialized agents or modules connected by delegation edges, routing tasks through a dynamic execution graph. Current schedulers optimize load and fitness b...
How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment
arXiv:2603.17169v1 Announce Type: new
Abstract: Deducing whodunit proves challenging for LLM agents. In this paper, we implement a text-based multi-agent version of the classic board game Clue as a rule-based testbed for evaluating multi-step deductive reasoning, with six agents drawn from GPT-4o-m...
arXiv:2603.17216v1 Announce Type: new
Abstract: With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and current LLMs of...
From engagement to fulfillment: How Agentic AI is rewriting product metrics
As AI agents begin executing tasks on users’ behalf, traditional engagement metrics are becoming less meaningful. In the age of agentic AI, product teams may need a new north star: measuring whether user intent was successfully fulfilled.
When AI judges AI: The hidden dangers of reasoning models in alignment
The race to build more capable AI systems has created an unexpected problem:
As we push toward more sophisticated models, we need equally sophisticated ways to evaluate and align them.
Tokenization Tradeoffs in Structured EHR Foundation Models
arXiv:2603.15644v1 Announce Type: new
Abstract: Foundation models for structured electronic health records (EHRs) are pretrained on longitudinal sequences of timestamped clinical events to learn adaptable patient representations. Tokenization -- how these timelines are converted into discrete model...
Alternating Reinforcement Learning with Contextual Rubric Rewards
arXiv:2603.15646v1 Announce Type: new
Abstract: Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured, multi-dimensional, conte...