A field on ReadSearch
Computer Science & AI
Much of the new work in computer science and AI appears first as a preprint on arXiv. ReadSearch reads those listings every day, with papers OpenAlex files under the same subjects, and this page shows the newest it has, from machine learning and language to systems, theory and security.
The newest 1,000 papers, from 4 November 2026 to 5 November 2026: 1,000 arXiv preprints.
Newest papers, page 15
Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness
Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and verifying them by executing tests or by extended reasoning is costly.Network Effect Decomposition for Causal Effect Estimation under Network Interference
Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure.Quasi-polynomial-sized vertex multicut-mimicking networks and kernelization for Vertex Multiway Cut
We give deterministic polynomial-time constructions of vertex multicut-mimicking networks of quasi-polynomial size.TactileLab: Sim-to-Real Dexterous Robot Manipulation with Efficient Shear-Sensitive Tactile Simulation
Robotic simulators that represent shear within tactile sensing are becoming increasingly important for contact-rich manipulation.Compositional Loop Invariant Inference for Multiphase Programs via Structured Neurosymbolic Reasoning
Loop invariants are essential for deductive program verification, yet automatically inferring them for {multiphase programs}, whose loops contain conditional branches that induce multiple execution…InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining
Vision foundation models are the backbone of modern surgical image analysis, yet most surgical systems still rely on encoders pretrained on natural images or on specialist models trained from…When, Where, How: Active In-Context Learning for Tabular Foundation Models
Tabular Foundation Models (TFMs) adapt to a new task only through the labeled rows in their context.A Low Similarity Score Does Not Show Independence after Source-Conditioned Repository Rewriting
Maintainers sometimes cite a low token-similarity score as evidence that an LLM-assisted rewrite of a copyleft project is independent of the original.When Bigger Becomes Brittle: Why Compression Hurts More as Language Models Scale
Quantization and pruning reduce the cost of deploying language models, but their effects are usually reported as benchmark scores.DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning
Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch.AffordJEV: Affordance Grounding by Confirming Candidate Regions
Affordance grounding asks which visible part of an object performs a requested operation, a basic capability for embodied manipulation and human--robot interaction.Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency
Conversational agents can retrieve information directly or delegate retrieval to a subagent.Structure from Collision via Hypothesis-Space Reasoning
Knowledge of the hidden interior structure of an object, including the presence and location of cavities, is essential for predictive simulation, robotic manipulation, and nondestructive inspection.XM4D: 4D Reconstruction through Certifiable Geometric Optimization
Accurate 4D reconstruction remains challenging: jointly estimating camera motion, scene geometry, and non-rigid deformation entails highly nonconvex optimization, making global optimality difficult…Tight Worst-Case Completion-Time Bounds for Dominant Resource Fairness
Dominant Resource Fairness (DRF) is an influential policy for sharing multiple resources among jobs with heterogeneous demands.EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under-constrained…GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving
World action models (WAMs) for autonomous driving couple the driving policy and the visual world model in a single generative network whose objectives are fixed post-training.Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models
Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions.Adaptive Semantic Branching: Disagreement-Localized Cross-Trajectory Regeneration for Reasoning Candidate Expansion
Reasoning trajectories generated for the same problem often arrive at conflicting answers.How Finite Brains Generalize Without Bound: Spatial Memory as a Universal Computer
A child who learns to add small numbers adds numbers of any length.
Get the few papers worth your time in Computer Science & AI every morning.
Choose your topics and ReadSearch reads the new papers in them each day, then brings you the few worth reading, each with its key finding in a sentence.