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
- PaperALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior Cloning
Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can e
- PaperLearning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents
Self-improving agents aim to continuously improve their behavior by learning from experience after deployment. However, accumulating and reusing more experience does not
- PaperWhen Guidance Becomes a Guard: Early Interception of Unsafe Inputs in Text-to-Image Generation
Text-to-image diffusion models can produce unsafe content, while output filtering intervenes only after synthesis. We investigate whether native generation signals enable
- PaperTeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions
The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio e
- PaperLabel Authority in Speech Emotion Recognition: Intended and Perceived Ground Truth in Emozionalmente
Ground truth in Speech Emotion Recognition (SER) is often presented as a single categorical fact, yet an acted emotion and the emotion heard by listeners describe differe
- PaperWenSight-Decision-1 for Direct Decisions under E-commerce Rules
E-commerce decisions require applying natural-language rules to the available case evidence. We introduce WenSight-Decision-1, a shared model that scores supplied options
- PaperRethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent trade-off between task adaptatio
- PaperReliable Estimation of Differential Privacy under Selection Bias
Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP) mechanisms. Auditors typically use Membership Inf
- PaperFake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricated headlines from real news. Because they read the
- PaperR2-GP: Variance-Calibrated Priors for Additive Gaussian Processes
We develop R2-GP, an R2D2-type prior for Gaussian process (GP) generalised additive models (GAMs) that calibrates explained variance ($R^2$) for Matérn covariance kernels
- PaperThe Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its Limits
We study whether geometric relationships between conversation turns, memory texts, and queries can predict answer correctness before generation. We evaluate four memory i
- PaperLong-form Video-to-Text Summarization using Recursive Language Models
While VideoLLMs have made significant progress in understanding short video benchmarks, they often struggle to summarize long-form ones. This is mainly due to performance
- PaperPhysiology-Aware Graph Attention for Early Ventricular Reentry Prediction
Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains diffic
- PaperHarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL
Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewards can become ineffective as
- PaperSNO-PI: Label-Scarce SNOMED CT Entity Linking with Pre-trained Encoders and Curated Terminology Knowledge
We present SNO-PI, the top-performing submission on SNOMED International's SNOMED CT Entity Linking Benchmark as of 18 October 2026. SNO-PI achieves a macro character IoU
- PaperGoverning the Rule Space. Ruliology, Computational Irreducibility and Anticipatory Governance of Quantum Technologies
The regulation of emerging technologies is often conceived as a strategy of catching up, because legislators arrive too late. Yet gathering signals, constructing scenario
- PaperSelf-Consistency of Entity Sets and Citations in a Deep Research System under Repeated Prompting
Deep research agents (DRA) are commonly used for open-ended synthesis tasks where closed-world QA benchmarks are poorly suited to characterize relevant aspects of perform
- PaperLocal data augmentation for imbalanced binary classification
Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the pres
- PaperCo-Evolving Policy and Reward for Code Generation: A Mechanistic Study of Single-Adapter Drift
Reinforcement learning with verifiable rewards (RLVR) is particularly well suited to code generation because generated programs can be objectively evaluated through execu
- PaperWhere Does Rhetorical Distortion Live? A Multi-Platform, Multi-Language Measurement of Influencer Content
Much of the manipulation in online influencer content is not false but disproportionate: an accurate fact is framed as historic, urgent, or catastrophic. Fact-checking an
- PaperPolicy-Adaptive Credit Assignment for Spatial Reasoning with Verifiable Rewards
Image-based spatial reasoning requires perception, decomposition, and inference, but the stage that limits accuracy can change during training. Answer-level rewards neith
- PaperExpert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeus
oollim is a locally executable system for evaluating L2 English pronunciation accuracy, fluency, and prosody on a consumer computer. The system combines pretrained XLS-R,
- PaperA Simple and General Approach to top-$k$ Selection
This paper considers the Bayesian top-$k$ identification problem, wherein a decision maker is tasked with selecting $k$ items from a pool of items of unknown quality. To
- PaperLaMER: Language-Conditioned Multi-Expert Routing for Weakly Supervised Referring Expression Comprehension
Referring Expression Comprehension (REC) localizes the image region described by a natural language expression, underpinning applications such as autonomous navigation, h
- PaperOne Fact, Many Places: Redundant Evidence in Long Visual Documents Breaks Single-Gold Evaluation of Retrieval, Citation and Attribution
Document understanding is increasingly judged on where an answer comes from, scored against annotated gold locations as if each fact lived in one place. In long visual do
- 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
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.