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 39
Bug2Scenario: Root-Cause-Preserving Test Scenario Amplification for Autonomous Driving Software
Simulation-based fuzzing exposes autonomous driving system (ADS) failures by repeatedly mutating and executing scenarios, but converting one failure into reusable regression scenarios remains…Homology Features for X-Ray Hyperspectral Images Segmentation
Characterizing Multi-Energy X-ray Transmission (XRT) hyperspectral images presents significant challenges for traditional classification frameworks due to high-dimensional redundancy and non-linear…A Dichotomy for Terminal Cyclability
Given an undirected graph $G$ and a set $R \subseteq V(G)$ of terminals, Terminal Cyclability asks whether $G$ contains a simple cycle visiting every vertex of $R$.Zuse: A Decision Model for European Languages
Decision models read a document and return a probability for each of a fixed set of options instead of generating text.Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation.CAPE-JEPA - Cross-modal Adversarial Probabilistic Embedding JEPA
Cross-modal remote sensing image retrieval (RS-CMIR) requires representations that are simultaneously modality-invariant and semantically discriminative, despite the profound physical gap between…A Polynomial Erdős-Pósa bound for Eulerian digraphs
In [Combinatorica 1996], Reed, Robertson, Seymour and Thomas proved Younger's conjecture dating back to 1973 that states that directed cycles have the Erdős-Pósa property.HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents
The performance of large language model (LLM) agents depends on both the underlying model and the harness that governs interaction with tools and the environment.Learning Noise Optimization for Reward Alignment in Few-Step Generative Models
Reward alignment for diffusion- and flow-based generative models is often formulated over stochastic trajectories, making it less suitable for few-step deterministic generators.Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks
Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run locally without sending the code to a hosted…CrossPressor: Scalable Cross-View Fusion for Feed-Forward 3D Gaussian Splatting
Feed-forward 3D Gaussian Splatting (3D-GS) becomes increasingly difficult to scale to long multi-view sequences.A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models
People often make decisions by holistically reasoning over heterogeneous forms of personal information.CLEAR: Structured Specifications for Controllable Long-Horizon ML Research Engineering
Large language model (LLM) agents are increasingly being used to automate machine learning (ML) research workflows, ranging from code development and experiment execution to research reproduction…Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
Several widely used families of Graph Neural Networks carry a positive-definite geometric prior.NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation
Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the…Consistency Learning and Distillation for One-Step MIMO-OFDM Channel Estimation
Iterative neural channel estimators can improve recovery under pilot contamination, but repeated network evaluations increase inference cost.Evaluating Human-LLM Alignment on Visualization Preference
There are often multiple valid visualizations, spanning different chart types, visual encodings, and aesthetic choices, that can all support a user's goal of analyzing a dataset.Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification
While recent feed-forward 3D Gaussian Splatting methods enable efficient driving-scene reconstruction from surround-view images, their reliance on a single observation fundamentally hinders…DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation
Physics sensing in evolving environments requires reconstructing dense spatiotemporal fields from sparse observations while adapting where future observations should be collected.Building a Method: Challenges and Lessons from Developing an Impact Evaluation Framework for Public Investment in Open Source Software
Modern societies and institutions depend on an invisible layer of open digital infrastructure: foundational, openly accessible digital technologies that support a broad range of social and economic…
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.