22,940 AI articles curated from 50+ sources with AI-powered sentiment analysis, importance scoring, and key takeaways.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers have catalogued 195 AI safety benchmarks released since 2018, revealing that rapid proliferation of evaluation tools has outpaced standardization efforts. The study identifies critical fragmentation: inconsistent metric definitions, limited language coverage, poor repository maintenance, and lack of shared measurement standards across the field.
🏢 Hugging Face
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce RePAIR, a framework enabling users to instruct large language models to forget harmful knowledge, misinformation, and personal data through natural language prompts at inference time. The system uses a training-free method called STAMP that manipulates model activations to achieve selective unlearning with minimal computational overhead, outperforming existing approaches while preserving model utility.
AIBullisharXiv – CS AI · Apr 157/10
🧠AutoSurrogate is an LLM-driven framework that automates the construction of deep learning surrogate models for subsurface flow simulation, enabling domain scientists without machine learning expertise to build high-quality models through natural language instructions. The system autonomously handles data profiling, architecture selection, hyperparameter optimization, and quality assessment while managing failure modes, demonstrating superior performance to expert-designed baselines on geological carbon storage tasks.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers introduce MemJack, a multi-agent framework that exploits semantic vulnerabilities in Vision-Language Models through coordinated jailbreak attacks, achieving 71.48% attack success rates against Qwen3-VL-Plus. The study reveals that current VLM safety measures fail against sophisticated visual-semantic attacks and introduces MemJack-Bench, a dataset of 113,000+ attack trajectories to advance defensive research.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose a case-based learning framework enabling LLM-based autonomous agents to extract and reuse knowledge from past tasks, improving performance on complex real-world problems. The method outperforms traditional zero-shot, few-shot, and prompt-based baselines across six task categories, with gains increasing as task complexity rises.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce IDEA, a framework that converts Large Language Model decision-making into interpretable, editable parametric models with calibrated probabilities. The approach outperforms major LLMs like GPT-5.2 and DeepSeek R1 on benchmarks while enabling direct expert knowledge integration and precise human-AI collaboration.
🧠 GPT-5
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce DocSeeker, a multimodal AI system designed to improve long document understanding by implementing structured analysis, localization, and reasoning workflows. The breakthrough addresses critical limitations in existing large language models that struggle with lengthy documents due to high noise levels and weak training signals, achieving superior performance on both short and ultra-long documents.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers introduce VLM-DeflectionBench, a new benchmark with 2,775 samples designed to evaluate how large vision-language models handle conflicting or insufficient evidence. The study reveals that most state-of-the-art LVLMs fail to appropriately deflect when faced with noisy or misleading information, highlighting critical gaps in model reliability for knowledge-intensive tasks.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose a two-stage LLM framework that uses one model to translate XAI technical outputs into natural language and a second model to verify accuracy, faithfulness, and completeness before delivering explanations to users. The framework includes iterative refinement mechanisms and demonstrates improved reliability across multiple XAI techniques and LLM families.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers tested whether large language models exhibit the Identifiable Victim Effect (IVE)—a well-documented cognitive bias where people prioritize helping a specific individual over a larger group facing equal hardship. Across 51,955 API trials spanning 16 frontier models, instruction-tuned LLMs showed amplified IVE compared to humans, while reasoning-specialized models inverted the effect, raising critical concerns about AI deployment in humanitarian decision-making.
🏢 OpenAI🏢 Anthropic🏢 xAI
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers have identified critical vulnerabilities in mobile GUI agents powered by large language models, revealing that third-party content in real-world apps causes these agents to fail significantly more often than benchmark tests suggest. Testing on 122 dynamic tasks and over 3,000 static scenarios shows misleading rates of 36-42%, raising serious concerns about deploying these agents in commercial settings.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers have identified a critical privacy vulnerability in LLM-based multi-agent systems, demonstrating that communication topologies can be reverse-engineered through black-box attacks. The Communication Inference Attack (CIA) achieves up to 99% accuracy in inferring how agents communicate, exposing significant intellectual property and security risks in AI systems.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers propose a cognitive diagnostic framework that evaluates large language models across fine-grained ability dimensions rather than aggregate scores, enabling targeted model improvement and task-specific selection. The approach uses multidimensional Item Response Theory to estimate abilities across 35 dimensions for mathematics and generalizes to physics, chemistry, and computer science with strong predictive accuracy.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers identified a critical failure mode in LLM-based agents called policy-invisible violations, where agents execute actions that appear compliant but breach organizational policies due to missing contextual information. They introduced PhantomPolicy, a benchmark with 600 test cases, and Sentinel, an enforcement framework using counterfactual graph simulation that achieved 93% accuracy in detecting violations compared to 68.8% for baseline approaches.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose Coupled Weight and Activation Constraints (CWAC), a novel safety alignment technique for large language models that simultaneously constrains weight updates and regularizes activation patterns to prevent harmful outputs during fine-tuning. The method demonstrates that existing single-constraint approaches are insufficient and outperforms baselines across multiple LLMs while maintaining task performance.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose Safe-FedLLM, a defense framework addressing security vulnerabilities in federated large language model training by detecting malicious clients through analysis of LoRA update patterns. The lightweight classifier-based approach effectively mitigates attacks while maintaining model performance and training efficiency, representing a significant advancement in securing distributed LLM development.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers introduce REL, a benchmark framework that evaluates relational reasoning in large language models by measuring Relational Complexity (RC)—the number of entities that must be simultaneously bound to apply a relation. The study reveals that frontier LLMs consistently degrade in performance as RC increases, exposing a fundamental limitation in higher-arity reasoning that persists even with increased compute and in-context learning.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose a label-free self-supervised reinforcement learning framework that enables language models to follow complex multi-constraint instructions without external supervision. The approach derives reward signals directly from instructions and uses constraint decomposition strategies to address sparse reward challenges, demonstrating strong performance across both in-domain and out-of-domain instruction-following tasks.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce CropVLM, a reinforcement learning-based method that enables Vision-Language Models to dynamically focus on relevant image regions for improved fine-grained understanding tasks. The approach works with existing VLMs without modification and demonstrates significant performance gains on text recognition and document analysis without requiring human-labeled training data.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce Vec-LUT, a novel vector-based lookup table technique that dramatically improves ultra-low-bit LLM inference on edge devices by addressing memory bandwidth underutilization. The method achieves up to 4.2x performance improvements over existing approaches, enabling faster LLM execution on CPUs than specialized NPUs.
AIBearisharXiv – CS AI · Apr 157/10
🧠Researchers introduce RT-LRM, a comprehensive benchmark for evaluating the trustworthiness of Large Reasoning Models across truthfulness, safety, and efficiency dimensions. The study reveals that LRMs face significant vulnerabilities including CoT-hijacking and prompt-induced inefficiencies, demonstrating they are more fragile than traditional LLMs when exposed to reasoning-induced risks.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers introduce HORIZON, a diagnostic benchmark for identifying and analyzing why large language model agents fail at long-horizon tasks requiring extended action sequences. By evaluating state-of-the-art models across multiple domains and proposing an LLM-as-a-Judge attribution pipeline, the study provides systematic methodology for understanding agent limitations and improving reliability.
🧠 GPT-5🧠 Claude
AIBearishFortune Crypto · Apr 147/10
🧠A growing backlash against AI is emerging from diverse constituencies including Gen Z and rural America, manifesting through both protest and infrastructure disruption. The movement reflects broader concerns about AI's environmental impact, labor displacement, and societal consequences, with activists targeting data centers and tech companies.
AINeutralArs Technica – AI · Apr 147/10
🧠The UK government's Mythos AI has become the first AI system to successfully complete a complex multi-step cybersecurity infiltration challenge, demonstrating tangible progress in AI capability assessment. This breakthrough helps distinguish genuine AI security threats from speculative hype, providing clearer benchmarks for evaluating AI systems' real-world vulnerabilities.
AIBullishFortune Crypto · Apr 147/10
🧠U.S. utilities are planning to increase capital spending by 30% to $1.4 trillion over the next five years, largely driven by infrastructure demands from AI data centers and related construction projects. This massive investment wave is occurring simultaneously with rising consumer rate hikes, though these spending increases and rate increases operate through separate mechanisms.
