Real-time AI-curated news from 100,678+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present a federated learning approach to detect passive eavesdropping attacks in smart grids by combining graph neural networks with temporal modeling. The system achieves 98.32% per-timestep accuracy while preserving data privacy through decentralized training, addressing a critical vulnerability in grid infrastructure where attackers silently gather topology and consumption data.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce FAMPE, a novel attribution method that uses frequency-domain analysis to improve explainability in deep neural networks. By separately perturbing high and low-frequency components through FFT-based techniques, the method outperforms existing attribution approaches on ImageNet across multiple architectures without requiring manual baseline selection.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers have developed Token Probability Deviation (TPD), a method to detect whether questions were included in a reasoning model's distillation training data. The technique addresses data contamination risks in reasoning distillation, where benchmark data may inadvertently inflate model performance metrics, achieving up to 31% improvement in detection accuracy.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present CWE-BENCH-PYTHON, a large-scale benchmark demonstrating that poorly formulated prompts significantly increase the likelihood of LLMs generating insecure code. The study shows advanced prompting techniques like Chain-of-Thought can effectively mitigate these security risks, establishing prompt quality as a critical factor in AI-generated code safety.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers introduce MemSearcher, an AI agent framework that optimizes how large language models handle multi-turn interactions by maintaining compact memory instead of concatenating full conversation history. The approach uses a novel multi-context GRPO training method and demonstrates superior performance while maintaining stable token counts, reducing computational overhead.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose PCMDE, a new evaluation metric for synthetic multimodal images that combines large language models with vision-language models and physics-based reasoning to better assess semantic and structural accuracy than existing benchmarks like BLIP and CLIPScore. The three-stage approach addresses limitations in current metrics' ability to capture domain-specific and context-dependent image quality.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers propose using pulse-width modulation (PWM) with reinforcement learning to optimize optogenetic bioprocess control, enabling precise gene expression tuning through light-based switching rather than intensity adjustment. This approach addresses the limitation of steep dose-response curves in biotechnology by alternating light ON/OFF states within control periods, improving controllability and production efficiency in protein synthesis and metabolic regulation.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce a family of deterministic games designed to test Multi-Agent Reinforcement Learning (MARL) scalability for decentralized UAV swarm control tasked with relaying critical data. While baseline policies using Dijkstra's algorithm perform comparably to standard MARL algorithms for small agent counts, existing MARL approaches demonstrate significant scalability limitations as swarm size increases.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers introduce PerfCoder, a specialized family of large language models fine-tuned to generate high-performance optimized code through interpretable, customized strategies rather than brute-force scaling. The system outperforms existing models on code performance benchmarks and can generate human-readable optimization feedback that further improves outcomes when paired with larger models.
🧠 GPT-5
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce DT-PBO, a tree-based surrogate model for Preferential Bayesian Optimization that prioritizes interpretability over traditional Gaussian Process approaches. The method achieves competitive performance on benchmark functions while providing transparent insights into decision-maker preferences, addressing critical needs in high-stakes domains like healthcare.
$MKR
AINeutralarXiv – CS AI · May 116/10
🧠Researchers challenge recent claims that Chain-of-Thought (CoT) reasoning in language models is unfaithful when it omits prompt-injected hints. The study argues the Biasing Features metric conflates incompleteness with unfaithfulness, and demonstrates through multiple evaluation approaches that non-verbalized hints can still causally influence predictions, suggesting token constraints rather than model deception explain missing hint mentions.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce Safety-Biased Trust Region Policy Optimisation (SB-TRPO), a reinforcement learning algorithm designed to satisfy strict safety constraints in critical applications while maintaining task performance. The method dynamically balances safety compliance with reward improvement through principled policy updates, with formal guarantees of safety progress.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers found that base large language models do not replicate human motivated reasoning patterns when tested across four political studies. Unlike humans who adjust their reasoning based on desired conclusions, LLMs show different behavioral patterns, raising concerns about using these models for opinion simulation and argument assessment tasks.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose R-GTD, a regularized gradient temporal-difference learning algorithm that maintains convergence guarantees even when the feature interaction matrix becomes singular—a practical limitation in existing GTD methods. The geometric analysis provides explicit error bounds and addresses a key stability challenge in off-policy reinforcement learning with function approximation.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers identify a market inefficiency in LLM-as-a-service pricing where providers are financially incentivized to increase test-time compute usage beyond what meaningfully improves output quality, inflating costs for users. They propose a reverse second-price auction mechanism where providers compete on both price and quality, with users paying only for marginal value created relative to alternatives.
🧠 Llama
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce a spectral filtering method for learning complex-valued linear dynamical systems with sector-bounded spectrum, achieving dimension-free regret bounds for sequence prediction. The approach uses Slepian basis functions and demonstrates that learning efficiency depends on an effective dimension independent of state space size, with applications to signal processing and quantum systems.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present a theoretical framework showing how mini-batch noise in Adam optimizer training affects the implicit bias toward sharper or flatter loss landscape regions, finding that optimal momentum hyperparameters shift based on batch size—small batches favor the default (0.9, 0.999) settings while larger batches benefit from closer β₁ and β₂ values.
AINeutralarXiv – CS AI · May 116/10
🧠TopoPrune introduces a topology-based framework for data pruning that addresses instability issues in geometric methods by leveraging intrinsic data structure rather than extrinsic geometry. The approach combines manifold approximation with persistent homology to achieve high accuracy at extreme pruning rates (90%) while maintaining robustness across architectures and noise conditions.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce Mixture-of-Masters (MoM), a sparse mixture-of-experts chess language model that routes moves through specialized GPT experts trained on individual grandmaster playing styles. The system outperforms dense transformer baselines and maintains interpretability by dynamically selecting which grandmaster persona to channel based on game state.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers introduce INCAMA, a novel method for inferring causal brain networks from indirect neuroimaging data like fMRI. The approach addresses the fundamental challenge that brain imaging signals are distorted by physics of hemodynamics and volume conduction, making direct causal inference impossible without accounting for these measurement artifacts.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose a new approach to entropy control in Reinforcement Learning with Verifiable Rewards (RLVR) for Large Language Models, addressing the problem of policy entropy collapse through dynamic gradient-preserving clipping mechanisms. The method uses importance sampling analysis and dynamic thresholds to maintain output diversity and prevent vanishing gradients during training, demonstrating improved performance across benchmarks.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce VESPO, a new method for training large language models using reinforcement learning that solves the variance problem in off-policy updates. The technique uses a principled mathematical approach to weight sequences rather than tokens, enabling stable training even when data becomes stale, with demonstrated improvements on math and code generation tasks.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers introduce AdaCorrection, a framework that improves the efficiency of Diffusion Transformers (DiTs) used in image and video generation by adaptively correcting cached features during inference. The method maintains generation quality while reducing computational costs through intelligent cache reuse without requiring retraining or additional supervision.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce γ-weakly θ-up-concavity, a mathematical framework that unifies optimization approaches for non-convex functions by generalizing DR-submodular and One-Sided Smooth functions. The framework proves these functions are upper-linearizable, enabling improved approximation guarantees for both offline and online optimization problems across various constraint structures.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers introduce Goldilocks, a curriculum learning strategy that improves reinforcement learning efficiency for language models by having a teacher model dynamically select training questions of optimal difficulty for the student model. This addresses the sample inefficiency problem in sparse-reward RL training and demonstrates performance gains on reasoning tasks compared to standard approaches.
