arXiv:2603.06330v1 Announce Type: cross Abstract: Behaviour Change Techniques (BCTs) are central to digital health interventions, yet selecting and delivering effective techniques remains challenging. Contextual bandits enable statistically grounded optimisation of BCT selection, while Large Language Models (LLMs) offer flexible, context-sensitive message generation. We conducted a 4-week study on physical activity motivation (N=54; 9 post-study interviews) […]
The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
arXiv:2603.06290v1 Announce Type: new Abstract: Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture the latent semantic topology and temporal dependencies essential for holistic sensemaking. We introduce EpisTwin, a neuro-symbolic framework that grounds […]
Dynamic Chunking Diffusion Transformer
arXiv:2603.06351v1 Announce Type: cross Abstract: Diffusion Transformers process images as fixed-length sequences of tokens produced by a static $textitpatchify$ operation. While effective, this design spends uniform compute on low- and high-information regions alike, ignoring that images contain regions of varying detail and that the denoising process progresses from coarse structure at early timesteps to fine […]
Physical Simulator In-the-Loop Video Generation
arXiv:2603.06408v1 Announce Type: cross Abstract: Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects often move inconsistently across frames, exhibit implausible dynamics, or violate physical constraints, limiting the realism and reliability of AI-generated videos. We address this […]
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
arXiv:2603.06333v1 Announce Type: new Abstract: Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We introduce SAHOO, a practical framework to monitor and control drift through three safeguards: (i) the Goal Drift Index (GDI), a learned multi-signal detector combining […]
Remote Sensing Image Classification Using Deep Ensemble Learning
arXiv:2603.05844v1 Announce Type: cross Abstract: Remote sensing imagery plays a crucial role in many applications and requires accurate computerized classification techniques. Reliable classification is essential for transforming raw imagery into structured and usable information. While Convolutional Neural Networks (CNNs) are mostly used for image classification, they excel at local feature extraction, but struggle to capture […]
NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches
arXiv:2603.06492v1 Announce Type: cross Abstract: We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an architectural augmentation that adds nonlinear low-rank branches to transformer linear layers. Unlike LoRA and other parameter-efficient fine-tuning (PEFT) methods, NOBLE is designed for pretraining from scratch. The branch is a permanent part of the architecture as opposed to an adapter […]
Reconstruct! Don’t Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
arXiv:2603.05887v1 Announce Type: cross Abstract: Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it does not guarantee content preservation in reconstructed speech. In this work, we demonstrate that self-supervised representation reconstruction (SSRR) loss fundamentally improves codec training and performance. First, SSRR significantly accelerates convergence, […]
Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
arXiv:2603.06394v1 Announce Type: new Abstract: Large language models (LLMs) can now translate a researcher’s plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are difficult to guarantee when an LLM decides what runs. Semi-structured interviews with 18 experts across 10 industrial R&D stakeholders surface 2 competing requirements–deterministic, constrained execution and […]
Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
arXiv:2603.05900v1 Announce Type: cross Abstract: Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular optimization, where each data point typically provides only a single optimized reference molecule and no step-by-step optimization trajectory. We reveal that answer-only […]
Fly360: Omnidirectional Obstacle Avoidance within Drone View
arXiv:2603.06573v1 Announce Type: cross Abstract: Obstacle avoidance in unmanned aerial vehicles (UAVs), as a fundamental capability, has gained increasing attention with the growing focus on spatial intelligence. However, current obstacle-avoidance methods mainly depend on limited field-of-view sensors and are ill-suited for UAV scenarios which require full-spatial awareness when the movement direction differs from the UAV’s […]
Sampling-based Continuous Optimization for Messenger RNA Design
arXiv:2603.06559v1 Announce Type: new Abstract: Designing messenger RNA (mRNA) sequences for a fixed target protein requires searching an exponentially large synonymous space while optimizing properties that affect stability and downstream performance. This is challenging because practical mRNA design involves multiple coupled objectives beyond classical folding criteria, and different applications prefer different trade-offs. We propose a […]