AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEvolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search
arXiv:2609.19799v1 Announce Type: cross Abstract: LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of…
- arXiv cs.AIagentsLong-horizon autoformalization of a core theorem underlying MIP* = RE
arXiv:2609.19814v3 Announce Type: replace-cross Abstract: Landmark mathematical formalizations have taken specialist teams years to complete. We present FormalFlow, a system that coordinates AI proving agents under human…
- arXiv cs.AIresearchCoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection
arXiv:2609.19818v3 Announce Type: replace-cross Abstract: Audio deepfake detectors are expected to remain robust to diverse attacks, datasets, and recording conditions, yet collecting training data that cover every futur…
- arXiv cs.AIresearchReproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
arXiv:2609.19831v1 Announce Type: cross Abstract: In this reproducibility study, we investigate the transparency and scrutability of recommender systems enhanced by incorporating generated natural-language user profiles…
- arXiv cs.AIresearchTrust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies
arXiv:2609.19844v2 Announce Type: replace-cross Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework cove…
- arXiv cs.AIresearchImproving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision
arXiv:2609.19846v1 Announce Type: cross Abstract: As generalist robot policies gain vision and language from web-scale pretraining, demonstrations remain costly to collect and tied to the robot that recorded them. Latent…
- arXiv cs.AIresearchPACE: Precise AI Cinematic Expression
arXiv:2609.19853v2 Announce Type: replace-cross Abstract: Between a screenplay and a film sits a planning problem that is spatial first: who stands where, and what a camera sees from where it stands. An image diffusion m…
- arXiv cs.AIresearchA Functional Pilot for Certified Freshness-Aware Semantic--Spatial Range Retrieval
arXiv:2609.19855v2 Announce Type: replace-cross Abstract: Geographic applications need every object inside a radius that satisfies a semantic threshold, yet embedding indexes return approximate top-ranked lists and may o…
- arXiv cs.AIresearchZarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference
arXiv:2609.19868v1 Announce Type: cross Abstract: Autoregressive language models (ARMs) are constrained by sequential, left-to-right generation, while masked diffusion models (MDMs) enable parallel decoding but suffer fr…
- arXiv cs.AIresearchPetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces
arXiv:2609.19883v1 Announce Type: cross Abstract: Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or are costly to extend…
- arXiv cs.AIagentsClashBench: Conflicts Leading Agents to Seize and Harm
arXiv:2609.19892v1 Announce Type: cross Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing resources with limit…
- arXiv cs.AIagentsLearning and Transferring Closed-Loop Robot Software
arXiv:2609.19906v3 Announce Type: replace-cross Abstract: Closed-loop robot policies require observation processing, state management, and situation-dependent branching, making them costly to design and tune manually. Al…
- arXiv cs.AIresearchKoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms
arXiv:2609.19916v1 Announce Type: cross Abstract: Large language models (LLMs) are typically evaluated on static benchmarks, even though natural language constantly evolves through newly emerging words and meanings. Exis…
- arXiv cs.AIresearchEfficiently Distributed Federated Learning
arXiv:2609.19972v1 Announce Type: cross Abstract: Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quick…
- arXiv cs.AIresearchMaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation
arXiv:2609.19974v1 Announce Type: cross Abstract: Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout ex…
- arXiv cs.AIresearchPast, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
arXiv:2609.19985v2 Announce Type: replace-cross Abstract: Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter…
- arXiv cs.AIresearchAVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models
arXiv:2609.19991v1 Announce Type: cross Abstract: Omni models can describe video content, but can they locate events in time, preserve event order, and judge audio-visual synchronization? We introduce AVTrace (Audio-Visu…
- arXiv cs.AIresearchEPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning
arXiv:2609.20004v1 Announce Type: cross Abstract: Reward-based reinforcement learning for language models, exemplified by Group Relative Policy Optimization (GRPO), collapses an entire stochastic trajectory into a single…
- arXiv cs.AIresearchDynamic Generalized Gromov-Wasserstein Optimal Transport
arXiv:2609.20008v2 Announce Type: replace-cross Abstract: Gromov--Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly relevant for…
- arXiv cs.AIresearchGovernance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems
arXiv:2609.20016v1 Announce Type: cross Abstract: The EU AI Act (Regulation 2024/1689) imposes technical obligations on high-risk AI providers, yet Articles 8-15 were drafted for predictive AI and leave seven technical g…
- arXiv cs.AIresearchAstronex-World 1.0: Real-Time Interactive World Model Foundation
arXiv:2609.20034v1 Announce Type: cross Abstract: We present Astronex-World 1.0, an open controllable video world-model foundation. Given a text prompt (text-to-video) or an initial observation (image-to-video), the mode…
- arXiv cs.AIresearchCorrect Now, Insufficient Later: Auditing Update Sufficiency in Context Compression
arXiv:2609.20045v1 Announce Type: cross Abstract: A memory can answer a current query correctly while discarding distinctions required by a later update. We investigate this failure with a paired-history audit: two histo…
- arXiv cs.AIagentsThe Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents
arXiv:2609.20050v2 Announce Type: replace-cross Abstract: Retrieval assembles repository context by ranking passages for relevance to the current query. A coding agent halfway through an issue has already read much of wh…
- arXiv cs.AIresearchAI Should Facilitate Democratic Deliberation at Scale
arXiv:2609.20059v1 Announce Type: cross Abstract: AI systems can strengthen democracy by supporting deliberation at scale by addressing cognitive, social, platform-design, and market-driven frictions, while preserving hu…
- arXiv cs.AIagentsRobust Workflow Generation via Adversarial Learning for Audio Deepfake Detection
arXiv:2609.20063v1 Announce Type: cross Abstract: The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security risks in practical ap…
- arXiv cs.AIresearchPointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation
arXiv:2609.20066v1 Announce Type: cross Abstract: Event cameras offer high temporal resolution and motion sensitivity for tiny UAV detection, yet distant targets generate sparse and fragmented events that are easily over…
- arXiv cs.AIresearchFrom Generative to Discriminative: Lightweight Adaptation of SpeechLLMs for Multimodal Emotion Recognition
arXiv:2609.20081v2 Announce Type: replace-cross Abstract: SpeechLLMs can recognise emotion by generating a label token, but this approach relies on the LLM's existing output representations. We compare this generative ap…
- arXiv cs.AIresearchMATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
arXiv:2609.20082v1 Announce Type: cross Abstract: Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior fro…
- arXiv cs.AIagentsA Scalable Trust Discovery Architecture for the Internet of Agents
arXiv:2609.20095v1 Announce Type: cross Abstract: The Internet of Agents is expected to enable large numbers of autonomous agents to discover, verify, and collaborate with each other across heterogeneous platforms. Howev…
- arXiv cs.AIresearchMulti-Dimensional Prosody Judgment For Live Streaming Speech Synthesis
arXiv:2609.20124v1 Announce Type: cross Abstract: Evaluating live streaming speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as emotion, intonation, and energy which traditional MOS…
- arXiv cs.AIresearchLocal Sparsity Enables Unsupervised LLM Safety Detection
arXiv:2609.20129v2 Announce Type: replace-cross Abstract: Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks…
- arXiv cs.AIresearchAdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
arXiv:2609.20130v1 Announce Type: cross Abstract: Recent memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution. However, our analysis reveals t…
- arXiv cs.AIresearchCross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
arXiv:2609.20139v1 Announce Type: cross Abstract: Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs…
- arXiv cs.AIagentsDesigning Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants
arXiv:2609.20143v1 Announce Type: cross Abstract: Cognitive offloading to AI can reduce opportunities to practice skills, creating risks of deskilling. However, it remains unclear how to prevent deskilling without restri…
- arXiv cs.AIresearchBridging Modalities on the Cortex: Surface-based MRI to PET Translation with a Diffusion Bridge
arXiv:2609.20147v1 Announce Type: cross Abstract: Cortical hypometabolism measured by Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a highly sensitive biomarker for dementia diagnosis. However, high costs,…
- arXiv cs.AIresearchQUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
arXiv:2609.20156v2 Announce Type: replace-cross Abstract: Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training found…
- arXiv cs.AIresearchFacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System
arXiv:2609.20175v1 Announce Type: cross Abstract: The filter bubble is a notorious issue in Recommender Systems (RSs), which describes the phenomenon whereby users are exposed to a limited and narrow range of information…
- arXiv cs.AIresearchVLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots
arXiv:2609.20191v2 Announce Type: replace-cross Abstract: Running vision-language navigation fully onboard an aerial robot is hard, since grounding, planning, and control must share limited compute and a single-stage err…
- arXiv cs.AIresearchSoftTri: Smooth Triangular Membership Functions for Adaptive Fuzzy Inference Systems
arXiv:2609.20194v1 Announce Type: cross Abstract: Triangular membership functions (MFs) are widely used in fuzzy systems because of their interpretability, low parameterization complexity, and strong locality properties.…
- arXiv cs.AIresearchMusic Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study
arXiv:2609.20195v1 Announce Type: cross Abstract: Audio-language models increasingly generate confident music descriptions that are unsupported by the input audio. We present, to our knowledge, the first music-specific,…
- arXiv cs.AIresearchScene-Conditioned Relation Routing for urban cellular activity forecasting
arXiv:2609.20209v1 Announce Type: cross Abstract: Urban cellular activity forecasting requires jointly modeling heterogeneous spatiotemporal signals, including SMS usage, mobile network traffic, and call activity. Existi…
- arXiv cs.AIresearchIs It Still Worth Training a Classical Model in the Era of LLMs? A Crossover Benchmark on Tabular Data
arXiv:2609.20218v1 Announce Type: cross Abstract: Large language models can label a tabular row from a plain-English description with no training - a capability now shipping in mainstream spreadsheet tools such as Micros…
- arXiv cs.AIresearchSelf-complementary completions on six vertices
arXiv:2609.20231v1 Announce Type: cross Abstract: Let \(\cthreshold(n)\) be the largest integer \(q\) such that every loopless digraph on \(n\) vertices with at most \(q\) arcs is isomorphic to a spanning subdigraph of a…
- arXiv cs.AIresearchLens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning
arXiv:2609.20252v1 Announce Type: cross Abstract: High-quality representations are essential for a wide range of downstream tasks. Dedicated embedding models are explicitly optimized for representation learning, yet thei…
- arXiv cs.AIresearchRisk-Set Transported Synthetic Control with Difference-in-Differences Adjustment under Staggered Treatment Adoption
arXiv:2609.20264v1 Announce Type: cross Abstract: In staggered treatment-adoption designs, later-treated units are valid controls for an earlier-treated cohort only until their own treatment begins, so the admissible don…
- arXiv cs.AIresearchCleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models
arXiv:2609.20267v1 Announce Type: cross Abstract: Concept erasure aims to selectively eliminate undesired visual semantics from pre-trained generative models without compromising their general utility. Extending concept…
- arXiv cs.AIresearchA Hybrid Gaze-Motor Imagery BCI Framework for Effective Decision Communication
arXiv:2609.20273v1 Announce Type: cross Abstract: Non-invasive brain-computer interfaces (BCIs) and eye-tracking technologies offer promising communication pathways; however, motor imagery (MI)-based BCIs often suffer fr…
- arXiv cs.AIresearchA Multi-Objective Optimisation Framework for Corticomuscular EEG-EMG Pair Selection in Hybrid BCI
arXiv:2609.20275v1 Announce Type: cross Abstract: Hybrid brain-computer interface (BCI) systems that integrate electroencephalography (EEG) and electromyography (EMG) signals have shown significant potential in improving…
- arXiv cs.AIresearchLabeled Incidence Structures for Native Transformer Modeling of Text, Knowledge Graphs, and Hypergraphs
arXiv:2609.20278v2 Announce Type: replace-cross Abstract: Current Transformer interfaces index tokens by one or more integer coordinates, which determine their addresses inside attention. In RoPE and its multi-axis or hi…
- arXiv cs.AIresearchHuman and AI-generated texts between modal logic and statistics
arXiv:2609.20311v1 Announce Type: cross Abstract: We read the geometry of semantic neighbourhood graphs as modal logic and give that reading a statistical form, in order to make precise the structural difference between…