Medio Ambiente

Calibrating Conservatism for Scalable Oversight

- Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems that may exceed...

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

- Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so...

Internally Referenced Low-Light Enhancement

- Self-supervised low-light image enhancement (LLIE) is highly appealing as it eliminates the reliance on external paired data. However, the lack of external references causes networks to struggle with...

Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration

- LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remains constrained by high token consumption,...

A Goal-Oriented Networking Approach for Intelligent IoT Service Deployment

- The first 6G standardization efforts are about to start, shaping the new generation of mobile networks. The IMT-2030 extends the IMT-2020 by expanding its usage scenarios to Immersive, Massive, and...

Comonadic Morphophonology: A Compositional Framework for Context-Dependent Morphological Rules in Finnish

- Composing finite-state transducers (FSTs) for context-dependent morphophonological rules -- consonant gradation, vowel harmony, possessive suffix assimilation -- leads to multiplicative state...

Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement

- Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string...

How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving

- Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation,...

Fluid Antenna System Meets Low-Resolution ADCs in Energy-Efficient Cell-Free Massive MIMO

- This paper proposes a novel fluid antenna system (FAS)-enabled architecture to improve energy efficiency (EE) without sacrificing capacity. Specifically, we integrate FAS into cell-free massive MIMO...

Building Community-Centred NLP Resources for Puno Quechua

- The preservation of under-resourced languages requires digital tools and resources shaped by and for their speakers. We present the first dedicated ASR resources for Puno Quechua (ISO 639-3: qxp):...

IMU Propagation as Preintegration

- IMU preintegration is widely used in factor-graph-based visual--inertial, lidar--inertial, and radar--inertial state estimation, yet it is often treated as a specialized implementation separate from...

PIRS: Physics-Informed Reward Shaping for SAC-Based Building Energy Management

- Occupant comfort and grid-aware energy efficiency are competing objectives whose joint optimization depends critically on how reward functions are specified in deep reinforcement learning (DRL)...

QuITE: Query-Based Irregular Time Series Embedding

- Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling. Existing approaches typically either (i) design specialized...

The Illusion of Opting in AI-Mediated Consequential Decisions

- Drawing on Ullmann-Margalit's concept of opting (transformative, irrevocable, and shadowed by foreclosed alternatives), we show that current AI systems raise a profound ethical problem that...

Geometry-First Generative Spatial Single-Cell Reconstruction

- Single-cell RNA sequencing (scRNA-seq) profiles large numbers of cells but loses spatial context, whereas spatial transcriptomics (ST) preserves partial spatial structure at lower resolution. Most...

FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales

- Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor configurations,...

MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation

- End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, page layout design, panel rendering, page composition,...

Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization

- Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhibit an imbalanced...

Revisiting Change Detection Methods for their Application to Serac Fall Time-Lapse Monitoring

- In an era where climate change aggravates environmental uncertainties, the identification and detection of event precursors are becoming crucial to mitigate the impacts of disastrous natural hazards....

Examining Agents' Bias Amplification versus Suppression in Multi-Agent Systems

- Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although these systems can enhance task performance and...

Learning Compositional Latent Structure with Vector Networks

- Deep networks are powerful function approximators, but they typically store many different computations in shared weight matrices, making it difficult to selectively reuse or adapt parts of them when...