AI Research

Researchers propose an additive causal construction (ACC) framework for multi-source image fusion that addresses cross-system discrepancy and entanglement, improving out-of-distribution generalization. The method, valida…

Researchers identified five failure modes in perturbation-based construct-validity audits of AI safety benchmarks, demonstrating that implementation details can silently invalidate audit conclusions. In a case study of t…

Researchers introduced QuantFlow, a federated Mamba-based foundation model for time-series forecasting that combines inverted sequence embedding, bidirectional state-space decoders, quantile regression, and federated lea…

Researchers introduced the Lifting Neural Operator (LiNO), a multiresolution neural operator built on the second-generation wavelet lifting scheme, to learn solution operators of differential equations. LiNO adaptively d…

Researchers compared process and outcome reward structures for reinforcement learning with verifiable rewards (RLVR) in small language models, finding that process-only supervision achieved 63.73% accuracy on GSM8K versu…

Researchers propose Lagrangian Reward Augmentation (LARA), a framework for inference-time alignment of language models that enforces safety constraints by dualizing a constrained optimization problem into a one-dimension…

Researchers propose a hybrid block diffusion language model (BDLM) combining Mamba and attention mechanisms that restricts reverse Mamba scans to the active denoising block, enabling exact caching across blocks. At 87M p…

Researchers revised the GestaltMML paper on arXiv, describing a Transformer-based multimodal model that combines frontal facial images, demographics, and clinical text to improve rare genetic disease diagnosis accuracy. …

Researchers at arXiv and Phys. Rev. Research have developed a training framework that ranks and paces quantum machine learning samples by informativeness, adapting classical curriculum learning and hard-example-mining to…

Researchers introduced CAGE-1, an evaluation framework for enterprise agentic AI that assesses control, assurance, and governance before deployment. The framework tests authority, policy enforcement, retrieval quality, m…

Researchers introduced SecureCROWN, the first framework for privacy-preserving neural network robustness verification using secure two-party computation. It allows a model owner and data owner to jointly compute certifie…

Researchers propose a fuzzy-logic extension of Answer Set Programming (ASP) to bridge numerical data and qualitative reasoning, using learning-based membership functions and semantically enriched predicates. The framewor…

Researchers propose single-prover interactive proofs for AI safety, eliminating the need for debate between two AI models. The new method works for oracle-aided computations under robustness or low-degree polynomial assu…

Researchers propose R²PO, a method that decouples rollout and inference policies for LLM reasoning, achieving accuracy gains of 3.4% on MATH-500 and 1.3% on APPS. The approach attaches a lightweight Residual Rollout-Head…

Researchers propose FlashBlock, a cached block-external attention mechanism that reduces attention computation and KV cache access in block diffusion models for long-context generation. The method achieves up to 1.44× hi…

Researchers introduced SkillOpt-Lite, a minimal skill optimization pipeline for autonomous agents that accelerates convergence and improves performance, achieving +8.8 points on LiveMath with GPT-5.5 and +25.4 points wit…

Researchers from arXiv found that large language models share a common geometric structure in how context transforms concept representations, with displacement patterns that are semantically organized and transferable ac…

Anthropic CEO Dario Amodei revealed in a Bloomberg interview that he has only one direct report, chief of staff Avital Balwit, while his sister and co-founder Daniela Amodei oversees all other executives as president. Th…

YouTuber Husk IRL placed three phones running different conversational AI agents together and asked them to count to 100. The agents negotiated a shared approach but repeatedly agreed with and reinforced each other, fail…

Asian tech stocks slumped on July 2, 2026, as investors locked in profits after Samsung Electronics' shares surged over 180% earlier in the year. Samsung dropped 9% and SK Hynix fell up to 14.57%, dragging the Kospi inde…