AI & Machine Learning · Computer Science & AI
Artificial Intelligence
The newest papers in Artificial Intelligence that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 11 October 2026 to 5 November 2026: 4,993 arXiv preprints and 7 OpenAlex records.
Get the few papers worth your time in Artificial Intelligence every morning.
Follow Artificial Intelligence and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 7
Value-oriented policy distillation for interpretable wind farm power control
Wind farm power control can help the system maintain balance and avoid blackouts.The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model
Multimodal language models can simulate different observers, yet it remains unclear how assigned perspectives reshape their internal representations and whether these changes govern their judgements.Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining
Recent neural decoding approaches achieve strong performance by training on large collections of paired neural-behavioral recordings, but such datasets are expensive, invasive, and difficult to scale.Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations
After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it.DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection
Generalist Anomaly Detection (GAD) aims to detect anomalies in unseen domains using only a few reference samples.Accelerating Safe Reinforcement Learning with Massive Parallelism
We investigate the problem of scaling safe reinforcement learning (safe RL) to massively parallel training regimes, where a large number of environments are exe- cuted with short rollout horizons.Aligning Policy Encoders with a Shape Teacher
3D-aware representations can improve robotic manipulation by providing geometric information that is robust to changes in viewpoint, object position, and occlusion.LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation
Neural theorem proving increasingly uses retrieved premises and project context to support proof generation.A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing
Contextual integrity (CI) holds that appropriate information flow depends on context-specific norms.AutoCompress: Automated Hardware-Guided Model Compression
LLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory.First-Token Attraction in Mamba Dynamics
We study token dynamics in deep Mamba models, with a particular focus on the attracting role of the first token.Measured Coupling for Parallel Decoding in Diffusion Language Models
Diffusion language models can write many tokens per step, but must choose which tokens are safe to commit together.RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines
Reward machines (RMs) have been proposed as a reward formulation in reinforcement learning (RL) to capture non-Markovian tasks where credit assignment depends on history.Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation
Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear.Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement
Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks.Enhancing Local and Global Structure in Compressed AI Agent Memory
AI agents store text as embedding vectors and compress them at scale.VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception
Robotic perception increasingly relies on heterogeneous sensor suites combining cameras with emerging modalities (event, SPAD, iToF/dToF, and thermal).NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma
Current medical benchmarks typically break down clinical competence into isolated factual questions, single-image tasks, or static case vignettes.MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation
Visuomotor policies trained through imitation learning are highly sensitive to changes in camera viewpoint.FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning
Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity.