Real-time AI-curated news from 100,618+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
AINeutralarXiv – CS AI · May 116/10
🧠A comprehensive empirical study reveals that reported inefficiencies in multi-LLM routing systems are substantially inflated by evaluation artifacts rather than genuine model limitations. Researchers found that LLM-as-a-judge biases, output truncation, and format mismatches account for a significant portion of measured failures, suggesting current routing cost-quality tradeoff estimates significantly overstate the actual unsolvability ceiling.
🧠 Llama
AINeutralarXiv – CS AI · May 116/10
🧠Researchers reveal that spatiotemporal deepfake detection models are vulnerable to evasion attacks because they rely on fragile temporal spectrum cues rather than robust semantic understanding. The team proposes SpInShield, a defense framework using learnable spectral adversaries and shortcut suppression to improve detection robustness, achieving 21.30 percentage points better AUC against amplitude spectral attacks.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers propose an inertial motion learning framework for tracking shared bikes in GNSS-denied environments like urban canyons, combining mechanical constraints with mixture-of-experts models to achieve 12% accuracy improvements over baselines. The system leverages pedaling behavior patterns to dynamically calibrate wheel speed estimates, demonstrating practical viability through real-world deployment data from DiDi's bike-sharing platform.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers conducted a controlled empirical study evaluating three LLMs (Claude Haiku, DeepSeek-Chat, Gemini 2.5 Flash) for qualitative coding of psychological safety in software engineering communities. Multi-shot prompting improved Claude Haiku's performance but not the others, while all models exhibited systematic biases in coding predictions, providing evidence-based guidelines for LLM-assisted qualitative research.
🧠 Claude🧠 Gemini
AINeutralarXiv – CS AI · May 116/10
🧠Researchers demonstrate that physics-informed machine learning can predict fluid flows in industrial stirred tanks with significantly less training data than purely data-driven approaches. The study reveals diminishing returns in accuracy beyond moderate dataset sizes, with physics-based constraints proving most valuable in low-data regimes.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce CFM-SD, a causal discovery method that leverages physical simulators to identify cause-and-effect relationships in scientific domains while handling latent confounders—a common problem in molecular design and materials science. The approach achieves significantly higher accuracy than existing methods and demonstrates practical improvements in real-world applications like toxicity prediction and battery optimization.
AIBearisharXiv – CS AI · May 116/10
🧠Researchers conducted a pre-registered study testing insider threat detection systems against adaptive LLM-driven adversaries and found a counterintuitive result: sophisticated insider threats actually generate lower suspicion signals than innocent users, suggesting current detection mechanisms may fail against adaptive adversaries. The study releases open-source simulation tools and data, challenging fundamental assumptions in cybersecurity.
AIBearisharXiv – CS AI · May 116/10
🧠Researchers have successfully demonstrated methods to remove watermarks from large language model outputs through various text manipulation techniques including paraphrasing and machine translation. The study reveals that current watermarking schemes designed to prevent misuse of LLMs are vulnerable to attack, raising questions about their effectiveness as security measures.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce SHRED, a machine unlearning method for large language models that removes memorized private or copyrighted data without requiring a curated retain set of examples. By selectively demoting logits of high-information tokens while preserving model utility through self-distillation, SHRED achieves superior trade-offs between forgetting efficacy and performance compared to existing retain-set-dependent approaches.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose Deconfounded Hierarchical Gate (DHG), a novel approach to improve physics-constrained deep generative models' ability to extrapolate beyond training conditions. The method counterintuitively finds that excluding target-domain data during pretraining improves extrapolation performance by 39%, achieving 46% better results on lithium-ion battery temperature prediction benchmarks.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers identify why Graph Neural Network explanations produce inconsistent results when re-applied to their own outputs, attributing this to context perturbation during re-explanation. They propose Self-Denoising, a training-free post-processing method that improves explanation quality with minimal computational overhead.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose Implicit Preference Alignment (IPA), a machine learning framework that improves hand motion generation in human image animation without requiring expensive paired preference data. The method uses self-generated samples and a hand-aware optimization mechanism to enhance animation quality while reducing data curation overhead.
AIBullisharXiv – CS AI · May 116/10
🧠Researchers demonstrate that ProteinJEPA, a latent-space prediction technique, can complement traditional masked language modeling (MLM) in protein language models, achieving better downstream task performance when combined strategically. The optimal approach—masked-position MLM+JEPA—wins 10 out of 16 evaluation tasks against MLM-only baselines while maintaining computational efficiency.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose a novel Ensemble Distributionally Robust Bayesian Optimisation algorithm that addresses context distributional uncertainty in zeroth-order optimization. The method achieves sublinear regret bounds while remaining computationally tractable, improving upon existing state-of-the-art approaches.
AINeutralarXiv – CS AI · May 116/10
🧠Response-G1 introduces a novel framework for real-time video understanding that uses explicit scene graphs to align video evidence with query-specific response conditions, enabling Video-LLMs to make more accurate timing decisions during streaming video analysis without requiring fine-tuning.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce POISE, a reinforcement learning method that uses a language model's internal hidden states to estimate baseline values for policy optimization, eliminating the computational overhead of separate critic models. The approach demonstrates comparable performance to existing methods while requiring significantly less compute, enabling more efficient training of large reasoning models.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce Causal Energy Minimization (CEM), a theoretical framework that reinterprets Transformer layer architecture through energy-based optimization principles. The approach derives weight-tied attention and gated MLPs as gradient updates on energy functions, revealing new design spaces for parameter-efficient Transformer variants that maintain baseline performance at hundred-million-parameter scales.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce SAM 3D Animal, a promptable framework for reconstructing multiple animals in 3D from single images, addressing key challenges like occlusion and species variation. The team also releases Herd3D, a new multi-animal dataset with over 5K images, achieving state-of-the-art results across multiple benchmarks.
AINeutralarXiv – CS AI · May 115/10
🧠Nürnberg NLP's ensemble approach for detecting psychological defence mechanisms achieved first place in the PsyDefDetect shared task by leveraging nine independent voters across different model architectures and training methods. The strategy prioritizes error independence over single-model strength, addressing the inherent ambiguity in classifying overlapping psychological categories.
AINeutralarXiv – CS AI · May 116/10
🧠LithoBench introduces a comprehensive benchmark dataset for evaluating large multimodal models on remote-sensing lithology interpretation, containing 10,000 expert-annotated instances across cognitive levels from identification to reasoning. The research reveals significant gaps in current vision-language models' ability to handle knowledge-intensive geological tasks, highlighting the challenges of applying general-purpose AI to specialized domain expertise.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present Bharat ABIS, a billion-scale multimodal biometric identification system built on open-source architecture that processes fingerprint, face, and iris data for India's Aadhaar database. The system achieves 0.3% false non-match rate on 220 million identities and processes 100 searches per second, demonstrating practical scalability for country-level identity infrastructure.
AINeutralarXiv – CS AI · May 116/10
🧠A theoretical paper demonstrates that principals using standard scoring rules to oversee strategic AI agents face an inherent impossibility: achieving both honest reporting and accurate calibration simultaneously. The research identifies step-function approval thresholds as the only mechanism that preserves calibration while maintaining incentive compatibility, with specific equivalence properties under the Brier score.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce TRACE, a benchmark dataset for evaluating tourism recommendation systems that combine multi-turn dialogue, verifiable review citations, and rejection recovery. The dataset reveals a significant gap in existing conversational recommender systems: LLMs excel at recall but cite weakly, while retrieval-based systems ground better but struggle with accuracy and adaptation.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers decomposed room impulse responses to understand which acoustic components enable single-channel speaker distance estimation, finding that without time calibration, models rely on early reflections and achieve 1.29m error, while time-calibrated models achieve 0.14m accuracy using propagation delay alone.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduced DRIP-R, a benchmark designed to evaluate how large language model-based agents handle ambiguous retail policies where multiple valid interpretations exist. The study reveals that frontier AI models fundamentally disagree on identical policy-ambiguous scenarios, exposing a critical gap in agent decision-making capabilities for real-world applications.
