artificial intelligence

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and sampler execution can destabilize policy optimization. In this paper, we characterize the interaction between mismatch and the policy-gradient direction, distinguishing local...

Mask-Guided KV Cache Eviction in Block Diffusion Language Models

Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory capacity and generation speed. Reducing these costs requires deciding which past tokens to use for denoising the current block (selection) and which to keep in memory fo...

DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies

Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However, standard ES uniformly averages rewards across problems and compresses problem level population feedback into a single scalar, making it difficult to capture how the learn...

Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering

Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce DecSteer, a System-1 decision operator trained by behavior cloning that lowers this cost by roughly two orders of magnitude. The default operator uses 330K parameters to match a 1.33M-p...

AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD

The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free remedies evict low-importance tokens, an irreversible choice along the sequence axis. We instead keep every token and store it more cheaply along the "feature" axis. We the...

Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers

Neural operators provide fast surrogates for time-dependent PDEs, but autoregressive deployment creates a refinement-allocation problem: prediction errors vary over space and time, while only a finite number of local corrections can be committed along a trajectory. We formulate this as budgeted adaptive neural-operator...

Comparative review of hybrid forecasting models for short-term prediction of building thermal load

In this paper, a comparative review of different hybrid models for short-term forecasting of building thermal demand is carried out. Particularly, the assessment tackles the comparison of data-driven models enhanced with other state-of-the-art techniques. At the first step, the existing techniques reported in the liter...

Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks

Machine learning classifiers for bearing fault detection produce scalar confidence scores that conflate confident errors with genuinely ambiguous predictions, and the conventional truth/falsity pair (F = 1 - T) is algebraically redundant by construction. We operationalize a refined neutrosophic decomposition of a Rando...

DRUG DISCOVERY AND REPOSITIONING STUDIES ASSISTED BY ARTIFICIAL INTELLIGENCE

Computer-aided and artificial intelligence-aided drug design (CADD and AIDD) have long confronted a fundamental challenge: accurate prediction of the binding between dynamically evolving proteins and small-molecule ligands, not to mention the induced-fit interactions that occur throughout the binding process. This talk...

DRUG DISCOVERY AND REPOSITIONING STUDIES ASSISTED BY ARTIFICIAL INTELLIGENCE

Computer-aided and artificial intelligence-aided drug design (CADD and AIDD) have long confronted a fundamental challenge: accurate prediction of the binding between dynamically evolving proteins and small-molecule ligands, not to mention the induced-fit interactions that occur throughout the binding process. This talk...

Views and conditional acceptance of telehealth and artificial intelligence for lifestyle modification among individuals with prediabetes: A qualitative descriptive study

The Homo Sapiens digitalis in society 5.0 towards a sustainable and ethical entrepreneurship

Analyzing the perceptions of 98 undergraduate students in International Business at the Universidad Autónoma de Nayarit regarding the viability of entrepreneurship that links smart city innovation with a democratic framework suggests that higher education must lead the transition toward Society 5.0 through pedagogical...