AI Research

Anthropic published research on July 6 revealing that its AI model Claude has spontaneously developed an internal neural structure called J-space, which mirrors a leading theory of conscious thought and allows detection …

Anthropic's interpretability research reveals that its Claude AI model has self-organized an internal reasoning structure called the 'J-space,' which mirrors the Global Workspace Theory of human consciousness. The J-spac…

Researchers developed a semi-automatic pipeline that converts CT-based cardiac segmentations into simulation-ready meshes in minutes, preserving anatomical and topological consistency. Validated on 58 healthy cardiac CT …

Researchers introduced VERITAS, a domain-agnostic replication framework that uses CLI coding agents to automatically verify scientific claims from papers and code repositories. In tests across 65 papers in computer scien…

Researchers propose a sliding-window-based reinforcement learning (SWRL) framework for dynamic assembly flow shop scheduling with multi-product delivery, addressing challenges from dynamic order arrivals and kitting cons…

Researchers introduced Raven-Agent, the first autonomous trading agent for prediction markets, which achieved the only positive return and positive risk-adjusted return among tested policies in controlled replays over ar…

Researchers introduced the Human-Centric Reflective Architecture (HCRA), a framework for human-AI collaborative decision-making that models the task as a stochastic game and integrates human-calibrated models with reinfo…

Researchers propose cross-survey transfer as a rigorous evaluation framework for silicon sampling, where LLMs predict survey respondents' answers to unseen questions. Testing on Taiwan Election and Democratization Study …

Researchers introduced GRAFT, a per-word pronunciation conditioning mechanism for zero-shot text-to-speech that uses a short spoken sample to control pronunciation of specific words. In a blind English listening study, G…

Researchers found that induction heads in transformers implement two smoothing mechanisms—soft context-matching and BOS token pseudo-counts—that interpolate n-gram estimates, enabling in-context learning to regularize ra…

Researchers studied online adaptation of discrete diffusion models for molecular optimization, finding that combining acquisition, reward shaping, debiasing, replay, and validity control outperforms offline fine-tuning a…

Researchers found that large language models (LLMs) score up to 96% on CBT licensing exams but fail to apply CBT effectively in dialogue, defaulting to validation and reflection. A new metric, Protocol Leverage Force (F)…

Researchers propose Hierarchical Landmark Sparse (HiLS) Attention, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling loss. HiLS-Attention achieves performance comp…

Researchers proposed an uncertainty-aware reinforcement learning framework for algorithmic trading that integrates distributional, epistemic, and aleatoric uncertainty estimations using SHAP-weighted reconstruction, MC D…

Researchers propose ALORE, a scalable and domain-robust estimator for the size of the largest overlap between tables, addressing limitations of the state-of-the-art Armadillo. ALORE reduces mean absolute error by up to 5…

Researchers propose Proactive Thinking, a framework enabling LLMs to pre-compute responses during conversational pauses, reducing latency. A training-free baseline using speculative continual thinking improves interactio…

Researchers at leadership computing facilities developed REDI, an open-source framework that automates the transformation of large-scale scientific datasets into AI-ready training data through a five-stage pipeline. Eval…

Researchers introduced SwarmResearch, an orchestrator-subagent harness that uses a Shepherd Agent to steer a population of Search Agents operating in separate git branches, preventing convergence on single approaches. On…

Researchers introduced a new method, FCPA, to align large language models' generators with their validators, improving consistency by correcting for utterance frequency. Training with FCPA boosted Pearson correlation by …

Researchers developed a multilingual, multimodal NLP framework for early detection of fake news and violence-driven mob activity, achieving 98% accuracy on a fused dataset of 138,256 Bangla and English samples. The syste…