New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Monday 19 October
- PaperHow Benchmark Graph Construction Shapes Multi-Hop KG Navigation: A Controlled Audit of PathQuestion and PathQuestion-Large
Multi-hop knowledge-graph question answering (KGQA) benchmarks are often treated as fixed language-and-reasoning tasks, but for navigation-based methods, difficulty also
- PaperBridged Self-Distillation for On-Policy Learning
On-policy distillation can transfer the reasoning capabilities of a strong teacher to a smaller student. However, distillation from a stronger teacher model faces two mis
- PaperForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds
Animals build cognitive maps of vast environments, use them to perform map-based navigation, and might even be reusing the same circuitry used in spatial reasoning for cr
- PaperWhen Coding Agents Outpace Review: Evaluating PRD-Driven Development in Mature Enterprise Repositories
Coding agents increasingly undertake development tasks in mature enterprise repositories, yet existing benchmarks offer limited insight into whether they fulfill complete
- PaperFrom Legacy to Contemporary: Scalable Color Modernization for Long Videos
Bringing legacy video back to contemporary screens does not necessarily make it look contemporary. Earlier imaging pipelines often leave color casts, muted chroma, weak c
- PaperAnswer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization
An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finaliza
- PaperBOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning
Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We st
- PaperSelecting the Best Few with Human Evaluators: Adaptively Combining Ratings and Pairwise Comparisons
This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLMs, award nominees, or new pro
- PaperCTLite: Lightweight Irregular Multivariate Time Series Forecasting with Reusable Continuous-Time Summaries
Irregular multivariate time series forecasting (IMTSF) requires capturing temporal dynamics and cross-variable dependencies from sparse, asynchronous observations. Existi
- PaperMultiCard: Multiple Attribute Cardinality Estimation via Deep Learning
Cardinality estimation is essential for query optimization, but most existing learned estimators focus on a single predicate type, such as string LIKE clauses or numerica
- PaperAn Empirical Study of Parameter-Efficient Fine-Tuning for Mixture-of-Experts LLMs
Parameter-efficient fine-tuning (PEFT) methods are critical for adapting large models under resource-constrained settings. However, as mixture-of-experts (MoE) architectu
- PaperAutonomous intelligence for mining productivity: a multi-agent AI approach to operational value creation
Integrated Remote Operation Centres (IROCs) are emerging as the architectural frontier of Industry 4.0 for capital-intensive sectors such as mining, oil and gas, and ener
- PaperLong-wave Infrared Polarimetric Remote Sensing Image Fusion for Vehicle Detection
Blurred vehicle contours and low contrast limit detection performance in infrared remote sensing imagery, while existing fusion methods may introduce polarization noise a
- PaperGAIDA: Generative AI for Human-in-the-Loop Document Annotation
Document annotation is a fundamental yet labor-intensive step in building document information extraction systems. While Optical Character Recognition (OCR) and Large Lan
- PaperHGASurv: Hierarchical Granularity-Aware Multimodal Integration for Survival Prediction
Multimodal survival prediction jointly analyzes histopathological whole-slide images (WSIs), genomic profiles, and clinical variables to stratify patients by risk. Howeve
- PaperPhyPro-FM: A Physics and Prompt-Guided Graph Foundation Model for Contingency Analysis
The continuous evolution of next-generation power systems, characterized by the high penetration of renewable energy resources and dynamic topology variations, poses form
- PaperLogit Averaging During Training Sets a New State of the Art for Non-Invasive Speech BCI
Non-invasive brain-computer interfaces are in practice limited by signal-to-noise ratio, and recent state-of-the-art methods address this limitation by aggregating over r
- PaperCARRS: A Constraint-Aware, Real-Time Routing System for Emergency Vehicles in Urban Environments
Emergency vehicles such as police vehicles, fire engines, and ambulances require a stable and efficient route optimization to reach life-critical events in the shortest t
- PaperVibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement
Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capabil
- PaperA Generic On-Board AI Processing Chain for Earth Observation: From Application Development to Embedded Deployment and Mission-Level Orchestration
Earth observation satellites acquire more data than they can downlink. Extracting information on board with artificial intelligence (AI) turns the satellite into a data-r
- PaperLarge-Scale Biomedical RAG: Corpus Scaling, Document Representation, and Efficiency Trade-offs
We present a controlled, large-scale evaluation of how corpus scale, document representation, and reranking affect the effectiveness and efficiency of biomedical Retrieva
- PaperCIS-Transolver: A Cross-Layer Incremental-State Neural Operator for Fine-Scale Automotive Aerodynamic Flow Prediction
Neural operators offer an efficient data-driven approach to rapid prediction of complex automotive aerodynamic flows. However, spectral bias and other factors limit accur
- PaperTyped Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit Priors
Typed decision models (TDMs) return a probability over caller-defined options, and Jev is described by its vendor as calibrated. But in deployment class frequencies chang
- PaperThe Control Layer Behind Rule-Following Agents Trading Across Market Conditions
Trading discipline often fails people. Our study tested whether four AI trading agents followed their strategies and risk rules. Offering traders the evidence and an agen
- PaperTriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform Consistency
Post-hoc out-of-distribution detection usually relies on a single signal extracted from a frozen classifier, such as confidence, energy, features, or gradients. This depe
- PaperMCDA: Multi-View Graph Contrastive Learning with Dynamic Topology Augmentation for Functional MRI Analysis
Resting-state fMRI (rs-fMRI) is a vital non-invasive tool for diagnosing brain disorders and uncovering pathological mechanisms. However, existing graph contrastive learn
- PaperStrucChunk: Structure-Aware Retrieval for Legal Document RAG
Retrieval-Augmented Generation (RAG) can ground LLM outputs in domain-specific knowledge, but legal documents are hard: standard chunking fragments hierarchical argument
- PaperCARNet: End-to-End Coupled Association-Recognition Network for Fine-Grained Multi-Drone Collaborative Detection
Multi-drone collaborative detection aims to enhance target recognition by leveraging complementary observations from overlapping aerial viewpoints. Existing approaches ty
- PaperSelective Transfer through Sequence Distillation: From Benchmark Knowledge to Backdoor Behaviour
Knowledge distillation is widely used to transfer capabilities from teacher models to student models, but recent work shows that it can also transfer unintended teacher p
- PaperThe Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search Agents
Language-model agents increasingly solve complex tasks through parallel reasoning and asynchronous information gathering. Controlled replay across two model families and
- PaperCAST: Cast-Admissible Generative Design and Shape Optimization with Paired Depth Images
Deep generative design can produce complex geometries, but unconstrained representations may create undercuts that prevent release from a two-part mold. We present CAST,
- PaperAnswering While You Type: Optimizing Time-to-Answer with Streaming Generation
Work on efficient large-language-model inference has concentrated almost entirely on reducing the cost of decoding once a request is complete. The quantity a user experie
- PaperRobotic Photography System based on Vision-Language-Action Model
Modern robotic photography requires understanding photographic intent, planning camera motions, and producing aesthetically pleasing images in complex environments. We pr
- PaperToward Online Robust Zero-Sum Markov Games with Function Approximation
Online robust zero-sum Markov games pose a coupled operator-learning and game-solving problem: from nominal interaction data, the learner must recover a worst-case minima
- PaperLearning SOCP Solver Dynamics with Graph Neural Networks
Second-order cone programs (SOCPs) are a fundamental class of convex optimization problems widely applied across engineering domains. Classical interior-point methods are
- PaperTrust Your Targets: Is Target Propagation Block-Diagonal Gauss-Newton?
Target propagation (TP) is a backpropagation alternative in which local targets carry the global learning signal. Prior works claim that TP performs Gauss-Newton (GN) opt
- PaperPhysics-anchored residual quantum neural networks for cloud-cover parameterization
Compact quantum neural networks have been explored for cloud-cover parameterization, but their predictive value depends on how physical knowledge is incorporated and whic
- PaperFrom Cause to Effect: Generating Intermediate Event Chains in Videos
Video-Language Models (VLMs) excel at visual recognition but struggle with causal reasoning. Current evaluations are flawed: multiple-choice QA allows shortcuts, and open
- PaperTIM: Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology Report Generation
Automatic radiology report generation (RRG) aims to translate medical images into diagnostic text, reducing radiologists' workload and standardizing clinical documentatio
- PaperDecomposed Relation Extraction from Aviation Accident Narratives: Evaluating Transformer-Based Safety Knowledge Discovery under Relational Sparsity
Relation extraction from aviation accident narratives is challenging because genuine safety relations are sparse among possible concept pairs. This study evaluates a deco
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.