AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRethinking Routing Exploration in Modern Mixture-of-Experts
arXiv:2610.22353v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-gra…
- arXiv cs.AIresearchCoDA: Co-Evolution of Data Engines and Action Policies
arXiv:2610.22362v1 Announce Type: cross Abstract: Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify…
- arXiv cs.AIresearchT2-z: Test-Time Optimization of Environment Latents for Robotic World Models
arXiv:2610.22364v1 Announce Type: cross Abstract: Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor…
- arXiv cs.AIresearchDiscovering state-of-the-art quantum circuits with large language models
arXiv:2610.22367v1 Announce Type: cross Abstract: Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum advantage also requ…
- arXiv cs.AIresearchLIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
arXiv:2610.22372v1 Announce Type: cross Abstract: Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has be…
- arXiv cs.AIresearchAtomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation
arXiv:2502.13392v3 Announce Type: replace Abstract: Pioneering companies such as Waymo have deployed electric robo-taxi services in several U.S. cities. Operating such fleets requires coordinating ride matching, vehicle…
- arXiv cs.AIresearchGraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment
arXiv:2510.26309v2 Announce Type: replace Abstract: Regulatory compliance is an important requirement in many industrial and administrative settings. Yet compliance assessment remains difficult because regulatory require…
- arXiv cs.AIresearchChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems
arXiv:2601.01982v2 Announce Type: replace Abstract: Large language models (LLMs) excel at natural language tasks but remain brittle in domains requiring precise logical and symbolic reasoning. Chaotic dynamical systems p…
- arXiv cs.AIresearchJEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures
arXiv:2602.17162v4 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature". While effective at captu…
- arXiv cs.AIresearchTowards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies
arXiv:2604.03376v2 Announce Type: replace Abstract: Current work on radiology report evaluation has focused primarily on LLM-based metrics for chest X-rays (CXR), leaving open whether such approaches remain robust across…
- arXiv cs.AIresearchLanguage models recognize dropout and Gaussian noise applied to their activations
arXiv:2604.17465v3 Announce Type: replace Abstract: We provide evidence that language models can detect, localize and, to a degree, verbalize the difference between a-semantic perturbations applied to their activations.…
- arXiv cs.AIresearchPathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
arXiv:2605.23074v2 Announce Type: replace Abstract: Large Reasoning Language Models (LRMs) tackle complex tasks through test-time scaling, generating long-form Chain-of-Thought (CoT) trajectories during inference. These…
- arXiv cs.AIresearchKACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
arXiv:2606.00532v2 Announce Type: replace Abstract: Context-engineering methods improve a frozen language model by learning text from execution feedback and placing it in the prompt. When one learned prompt carries every…
- arXiv cs.AIresearchAI Alignment From Social Choice Perspectives
arXiv:2606.21550v2 Announce Type: replace Abstract: Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflict…
- arXiv cs.AIresearchMind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools
arXiv:2607.18253v2 Announce Type: replace Abstract: Large language model (LLM) query routers typically assign each query to a suitable model that balances response accuracy and monetary cost. Subsequently, separate syste…
- arXiv cs.AIresearchAI and Consumer Rights in India Working Paper
arXiv:2608.12863v2 Announce Type: replace Abstract: As AI systems proliferate in consumer facing applications, questions about liability for AI related harms remain unresolved. This working paper examines whether India's…
- arXiv cs.AIresearchWhen Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
arXiv:2608.14610v2 Announce Type: replace Abstract: Legal reasoning requires identifying which version of a statute applies to a case, typically based on when the legally relevant events occurred rather than when the cas…
- arXiv cs.AIresearchMEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data
arXiv:2608.22141v2 Announce Type: replace Abstract: Enterprise repositories are large, heteroge- neous, and continuously updated, making re- trieval difficult when efficient access, source- faithful evidence, and cross-q…
- arXiv cs.AIresearchDesign the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning
arXiv:2608.27906v4 Announce Type: replace Abstract: Reinforcement learning has advanced large language models on tasks with reliable verifiers, where checking an outcome provides a clear basis for reward. Extending this…
- arXiv cs.AIresearchBLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
arXiv:2608.31105v2 Announce Type: replace Abstract: Users of a deployed language model routinely encounter behaviours that have never been observed during testing, since deployment puts the model through orders of magnit…
- arXiv cs.AIresearchTask-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training
arXiv:2609.02244v2 Announce Type: replace Abstract: Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete. Task-level natural-language priors can provide useful guidance…
- arXiv cs.AIresearchT-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts
arXiv:2609.12286v2 Announce Type: replace Abstract: Introducing large language models (LLMs) into evolutionary computation enables semantic generation of candidates, but the classical problem of maintaining population di…
- arXiv cs.AIresearchDistributionally Robust Regularization of Sparse Integer Programming Trained Learning Models
arXiv:2311.01994v2 Announce Type: replace-cross Abstract: Building explainable machine learning models is crucial for human users to be able to interpret the proposed statistical relationship obtained from the training d…
- arXiv cs.AIresearchInkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write
arXiv:2402.05804v5 Announce Type: replace-cross Abstract: Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink. How…
- arXiv cs.AIresearchPairwise Difference Learning for Classification
arXiv:2406.20031v2 Announce Type: replace-cross Abstract: Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to o…
- arXiv cs.AIresearchLLMR: Knowledge Distillation with a Large Language Model-Induced Reward
arXiv:2409.12500v2 Announce Type: replace-cross Abstract: Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) tasks. However, these…
- arXiv cs.AIresearchSTAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs
arXiv:2411.10957v2 Announce Type: replace-cross Abstract: This paper addresses domain adaptation in graph-structured data under chronological splits. We consider transductive semi-supervised node classification (SSNC), i…
- arXiv cs.AIresearchA self-learning framework for adaptive free-form pipe routing in aeroengines
arXiv:2504.03669v2 Announce Type: replace-cross Abstract: Pipe routing is a highly complex, time-consuming, and no-deterministic polynomial-time hard (NP-hard) problem in aeroengine design. Despite extensive research eff…
- arXiv cs.AIresearchTowards Reliable Long-Context Reasoning: Detecting Unanswerable Questions via FactGuard
arXiv:2504.05607v2 Announce Type: replace-cross Abstract: Despite the success of Large Language Models (LLMs) in long-context tasks, their reliability in recognizing unanswerable questions remains a critical challenge. I…
- arXiv cs.AIresearchPanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution
arXiv:2507.09227v2 Announce Type: replace-cross Abstract: Interest in generating realistic synthetic medical images has grown in recent years. Such datasets can mitigate the scarcity of public data for artificial intelli…
- arXiv cs.AIresearchAdaptive Duration Model for Text Speech Alignment
arXiv:2507.22612v3 Announce Type: replace-cross Abstract: Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn th…
- arXiv cs.AIresearchUniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
arXiv:2508.04136v4 Announce Type: replace-cross Abstract: Few-shot fine-grained visual classification (FGVC) aims to discriminate between subtly different categories with very limited data. While Multimodal Large Languag…
- arXiv cs.AIresearchChronoberg: A 250-Year Diachronic Corpus with Temporal Affective Lexicons for Language Model Analysis
arXiv:2509.22360v3 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at operating at scale by leveraging social media and data crawled from the web. Whereas existing corpora are diverse, their fre…
- arXiv cs.AIresearchUncovering Grounding IDs: How External Cues Shape Multi-Modal Binding
arXiv:2509.24072v5 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) perform well on multimodal tasks, but their ability to reason and precisely align visual and textual information still has ro…
- arXiv cs.AIresearchMulti-task Neural Diffusion Processes
arXiv:2510.03419v3 Announce Type: replace-cross Abstract: Neural diffusion processes provide a scalable, non-Gaussian approach to modelling distributions over functions, but existing formulations are limited to single-ta…
- arXiv cs.AIresearchRAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data
arXiv:2510.08667v3 Announce Type: replace-cross Abstract: Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer di…
- arXiv cs.AIresearchScientific feedback reveals productive regimes beyond training conventions
arXiv:2512.15756v2 Announce Type: replace-cross Abstract: Human-imposed design conventions can restrict the alternatives represented in scientific training data and shape the search preferences learned by generative mode…
- arXiv cs.AIresearchBenchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration
arXiv:2512.20159v2 Announce Type: replace-cross Abstract: Code from LLM-assisted development may contain defects like API hallucinations, motivating the development of code evaluation metrics to assess such code before d…
- arXiv cs.AIresearchContextual Probability and Operational Minimality in Tug-of-War Decision Making
arXiv:2601.10034v4 Announce Type: replace-cross Abstract: What connects minimal decision-making to contextual probability? We address this question through the Tug-of-War (TOW) principle, a resource-coupled mechanism for…
- arXiv cs.AIresearchVDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents
arXiv:2602.00122v5 Announce Type: replace-cross Abstract: Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tab…
- arXiv cs.AIresearchProduct Interaction: An Algebraic Formalism for Deep Learning Architectures
arXiv:2602.02573v2 Announce Type: replace-cross Abstract: Modern neural architectures are largely developed as distinct empirical constructions, despite recurring principles across convolutional, attention, state-space,…
- arXiv cs.AIresearchLanguage Models Struggle to Use Representations Learned In-Context
arXiv:2602.04212v3 Announce Type: replace-cross Abstract: Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of arti…
- arXiv cs.AIresearchReText: Text Boosts Generalization in Image-Based Person Re-identification
arXiv:2602.05785v2 Announce Type: replace-cross Abstract: Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While visual feature…
- arXiv cs.AIresearchRMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
arXiv:2603.01229v4 Announce Type: replace-cross Abstract: Robotic manipulation policies have made rapid progress in recent years, yet most existing approaches give limited consideration to memory capabilities. Consequent…
- arXiv cs.AIresearchLearning Not To Interfere: Adapting Experts For Model Merging
arXiv:2603.13467v2 Announce Type: replace-cross Abstract: Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of intere…
- arXiv cs.AIresearchFrom Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding
arXiv:2603.15270v3 Announce Type: replace-cross Abstract: Medical coding, which assigns standardized ICD codes to clinical documents, is a fundamental yet challenging task in modern healthcare. It requires extensive know…
- arXiv cs.AIresearchWhat Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals
arXiv:2603.20990v5 Announce Type: replace-cross Abstract: Which properties of hard-negative supervision track dense-retriever transfer before training? We compare lexical noncoverage, frozenencoder similarity statistics,…
- arXiv cs.AIresearchInverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
arXiv:2603.23463v3 Announce Type: replace-cross Abstract: Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offe…
- arXiv cs.AIresearchTensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models
arXiv:2604.17104v3 Announce Type: replace-cross Abstract: Modern model hubs store hundreds of petabytes of large language models (LLMs), with fine-tuned variants dominating the storage footprint. These variants contain s…
- arXiv cs.AIresearchEmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
arXiv:2604.20012v2 Announce Type: replace-cross Abstract: Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-she…