Real-time AI-curated news from 28,452+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
Researchers introduce Parallax, a security framework that structurally separates AI reasoning from execution to prevent autonomous agents from carrying out malicious actions even when compromised. The system achieves 98.9% attack prevention across adversarial tests, addressing a critical vulnerability in enterprise AI deployments where prompt-based safeguards alone prove insufficient.
Researchers have conducted a comprehensive survey on hallucinations in Video Large Language Models (Vid-LLMs), identifying two core types—dynamic distortion and content fabrication—and their root causes in temporal representation limitations and insufficient visual grounding. The study reviews evaluation benchmarks, mitigation strategies, and proposes future directions including motion-aware encoders and counterfactual learning to improve reliability.
Researchers demonstrate that instruction-tuned large language models suffer severe performance degradation when subject to simple lexical constraints like banning a single punctuation mark or common word, losing 14-48% of response quality. This fragility stems from a planning failure where models couple task competence to narrow surface-form templates, affecting both open-weight and commercially deployed closed-weight models like GPT-4o-mini.
Researchers have identified a critical vulnerability in large language models where safety guardrails fail across low-resource languages despite strong performance in high-resource ones. The team proposes LASA (Language-Agnostic Semantic Alignment), a new method that anchors safety protocols at the semantic bottleneck layer, dramatically reducing attack success rates from 24.7% to 2.8% on tested models.
Researchers demonstrate that large language models develop internal planning representations that scale with model size, enabling them to implicitly plan future outputs without explicit verbalization. The study on Qwen-3 models (0.6B-14B parameters) reveals mechanistic evidence of latent planning through neural features that predict and shape token generation, with planning capabilities increasing consistently across model scales.
Researchers introduce Criticality-Aware Adversarial Training (CAAT), a parameter-efficient method that identifies and fine-tunes only the most robustness-critical parameters in Vision Transformers, achieving 94.3% of standard adversarial training robustness while tuning just 6% of model parameters. This breakthrough addresses the computational bottleneck preventing large-scale adversarial training deployment.
Researchers present OSC, a hardware-efficient framework that addresses the challenge of deploying Large Language Models with 4-bit quantization by intelligently separating activation outliers into a high-precision processing path while maintaining low-precision computation for standard values. The technique achieves 1.78x speedup over standard 8-bit approaches while limiting accuracy degradation to under 2.2% on state-of-the-art models.
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.
Researchers introduce Lightning OPD, an offline on-policy distillation framework that eliminates the need for live teacher inference servers during large language model post-training. By enforcing 'teacher consistency'—using the same teacher model for both supervised fine-tuning and distillation—the method achieves comparable performance to standard OPD while delivering 4x speedup and significantly reducing infrastructure costs.
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.
Researchers propose Schema-Adaptive Tabular Representation Learning, which uses LLMs to convert structured clinical data into semantic embeddings that transfer across different electronic health record schemas without retraining. When combined with imaging data for dementia diagnosis, the method achieves state-of-the-art results and outperforms board-certified neurologists on retrospective diagnostic tasks.
Researchers demonstrate that multi-token prediction (MTP) outperforms standard next-token prediction (NTP) for training language models on reasoning tasks like planning and pathfinding. Through theoretical analysis of simplified Transformers, they reveal that MTP enables a reverse reasoning process where models first identify end states then reconstruct paths backward, suggesting MTP induces more interpretable and robust reasoning circuits.
Researchers conducted the first systematic study of order bias in Large Language Models used for high-stakes decision-making, finding that LLMs exhibit strong position effects and previously undocumented name biases that can lead to selection of strictly inferior options. The study reveals distinct failure modes in AI decision-support systems, with proposed mitigation strategies using temperature parameter adjustments to recover underlying preferences.
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.
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.
Researchers introduce dual-trace memory encoding for LLM agents, pairing factual records with narrative scene reconstructions to improve cross-session recall by 20+ percentage points. The method significantly enhances temporal reasoning and multi-session knowledge aggregation without increasing computational costs, advancing the capability of persistent AI agent systems.
Researchers introduce Decoding by Perturbation (DeP), a training-free method that reduces hallucinations in multimodal large language models by applying controlled textual perturbations during decoding. The approach addresses the core issue where language priors override visual evidence, achieving improvements across multiple benchmarks without requiring model retraining or visual manipulation.
Researchers empirically evaluated 450 LLM-generated Python scripts for construction safety and found alarming reliability gaps, including a 45% silent failure rate where code executes but produces mathematically incorrect safety outputs. The study demonstrates that current frontier LLMs lack the deterministic rigor required for autonomous safety-critical engineering applications, necessitating human oversight and governance frameworks.
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.
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.
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.
Researchers present Chain-of-Models Pre-Training (CoM-PT), a novel method that accelerates vision foundation model training by up to 7.09X through sequential knowledge transfer from smaller to larger models in a unified pipeline, rather than training each model independently. The approach maintains or improves performance while significantly reducing computational costs, with efficiency gains increasing as more models are added to the training sequence.
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.
Researchers demonstrate an autonomous LLM agent capable of executing a complete research loop—reading, reproducing, critiquing, and extending computational physics papers. Testing across 111 papers reveals the agent identifies substantive flaws in 42% of cases, with 97.7% of issues requiring actual computation to detect, and produces a publishable peer-review comment on a Nature Communications paper without human direction.
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.
