A new study improving the Huth et al. fMRI language decoding pipeline achieved a mean METEOR score of 0.149 and BLEU-1 score of 0.200, an 11% relative METEOR gain over baseline, but the fMRIFlamingo m…
A new investigation into transformer models for reinforcement learning reveals that larger embedding dimensions produce more sophisticated internal world models and improve interpretability, even thou…
Audio-language models like CLAP fail to handle negation, with accuracy on negation tasks dropping below chance levels, according to a new evaluation framework called NegEval-Audio. Researchers found t…
A new framework called Elenchos, named after the Socratic method of cross-examination, tests large language models on abductive reasoning by placing them in scenarios involving mutated formal systems …
Evolution Strategy (ES) has achieved a 26% reduction in skin friction in turbulent channel flow, outperforming the gradient-based multi-agent controller's 17% reduction and the opposition control meth…
Hi-LeWM, an extension of LeWorldModel (LeWM) that integrates high-level planning over latent subgoals while keeping the low-level LeWM frozen, outperformed its predecessor by 11.3 percentage points at…
Researchers have successfully applied evolution strategies (ES) to fine-tune large language models at a billion-parameter scale without dimensionality reduction, marking a first that challenges reinfo…
A study introducing PoPE (Popperian Placebo-controlled Evaluation) found that small frozen code models with 0.5 to 1.5 billion parameters do not meaningfully learn from their own errors when generatin…
Researchers have released Deep4ge, a massive dataset containing 14,227 training runs from 59 deep neural network programs to help detect faults in deep learning systems. The dataset includes 9,845 fau…
A new Environment Parameter Gradient Theorem challenges traditional reinforcement learning by enabling simultaneous optimization of both policies and environments, according to researchers. The theore…
A new framework, VMoGE (Variational Mixture of Graph Neural Experts), promises to enhance the accuracy of dementia diagnosis using multi-band EEG analysis, achieving an AUC of 0.89 in distinguishing h…
Researchers have introduced a fine-tuned multi-agent framework that uses large language models to detect the Big Five (OCEAN) personality traits from text, achieving improved accuracy and reduced sing…
EG-VAR, a Lean 4-based architecture for AI reasoning, achieved a flawless 120 out of 120 on TableBench numerical reasoning tasks and maintained 100% source fidelity during counterfactual stress tests,…
A new lightweight model, the Lightweight MultiScale AutoEncoder (LMSAE), achieves competitive anomaly detection performance with a model size under 500 KB, slashing inference latency by 9x and cutting…
Researchers introduced PFAdapter, a framework for federated fine-tuning of multimodal large language models on edge devices, that reduces communication costs by nearly 50% while improving accuracy by …
Researchers have developed a physics-informed neural network (PINN) that predicts tension during parachute line extraction, outperforming traditional numerical methods in both computational efficiency…
SinAE, a new AI model from an unnamed research team, unifies molecules, crystals, and proteins into a single Transformer-based architecture, achieving near-lossless reconstructions via flow-matching d…
A new approach using sparse autoencoders (SAEs) is revolutionizing out-of-distribution (OOD) detection by extracting interpretable features from intermediate neural network layers, achieving record pe…
A new training-free attribution method reveals that Feedforward Networks in Transformer models exhibit sparse, structured inter-layer dependencies, where only a small subset of preceding neuron activa…
ConDitar-dev, an advanced drug design framework, achieved a remarkable average binding score of -8.85 kcal/mol and enhanced ADMET properties by 73%, outperforming state-of-the-art SBDD methods. In rea…