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…
Sunday 18 October
- PaperViCoR: Estimating Visual Necessity via Counterfactual Residuals for Multimodal Medical Data Selection
Medical vision-language models often exhibit hidden stratification, where high overall performance masks failures on subtle visual findings and overlapping clinical condi
- PaperRAIL-5G: A Challenging Real-World Dataset and Benchmark for AI-Based 5G Indoor Localization
Reliable radio-based indoor localization is essential for industrial automation, yet existing methods are often evaluated in environments that do not fully reflect the se
- PaperChronoChart: Setup-Agnostic Channel Charting for Label-Free Indoor Localization
Accurate radio-based indoor localization remains challenging in multipath-rich and dynamic indoor environments. Supervised fingerprinting methods achieve high positioning
- PaperShallow Probes Are Sufficient for Near-Oracle Personalization Depth Allocation in Federated Learning
Rather than proposing a new federated optimizer, we study whether a small client-specific measurement budget can support cost-aware personalization-depth decisions under
- PaperAcharya 2.0: An AI Tutor for Self-Learning Subjects in Hindi
Text processing is crucial for low-resource languages as it enables the development of tools and technologies that bridge the digital divide and provide equitable access
- PaperSampling and Curvature in First-Exit Comparisons for Momentum SGD
First-exit prediction for momentum SGD depends on sampling information that pointwise gradient laws omit. Strongly convex finite pools with identical pointwise laws and m
- PaperReranking Answers of Large Language Models with Knowledge Graphs
Answering natural language questions over knowledge graph data is challenging due to the vast number of facts, which can be difficult to process and navigate. One potenti
- PaperConcept Representations in Vector Space: Toward an Interdisciplinary Study of Meaning Variation
An increasing number of disciplines recognize the explanatory potential of meaning-bearing mental structures through which individuals interpret the world and guide their
- PaperDialogue Generation for Conversational Recommendation Using User Search Interactions and Knowledge Graphs
Large-scale conversational recommendation datasets typically require manual dialogue construction or annotation. We propose SearCl, which automatically generates conversa
- PaperMemory, Know Your PLACE: Governing Lifecycle State and Query-Time Eligibility in Persistent-Memory Agents
Persistent memory turns prior interactions into durable agent state, but existing systems provide limited control over whether that state remains valid and whether it sho
- PaperAn Information-Geometric Framework for OCS-Reconfigurable Interconnect Topology in Large-Scale AI Clusters
Optical Circuit Switches (OCS) make inter-pod wiring in AI clusters programmable, posing design questions on wiring choice, symmetry departure, and reconfigurations. We p
- PaperWorld Models, Trees and Foundation Models for Retail Forecasting: Evidence from Four Public Data Sets
A retailer makes different decisions at different grains of the product, store and time hierarchy: store orders for an item in a store, supplier funding for an item acros
- PaperLAMB: Latent Multi-Hypothesis Beliefs for Long-Horizon Large Language Agents
Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states. Although effective,
- PaperM-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21
Self-supervised molecular representation learning is increasingly used to improve transfer on small, label-limited property prediction tasks, yet commonly used contrastiv
- PaperIndistinguishable Agents: Training Agent Privacy as Twin-World Indistinguishability
LLM agents search, shop and send messages for their users, and every action is seen by some party. Existing privacy training rewards agents for not mentioning protected i
- PaperLegal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations
People ask conversational AI models about their legal rights, obligations, procedures, and personal situations that may have legal consequences. To study this behavior, w
- PaperDo LLMs Reproduce the Age Gap in Loneliness? Evaluating Survey Simulation against European Survey Data
Large language models (LLMs) are often used to simulate survey respondents, but matching survey averages does not establish accurate demographic differences. We test whet
- PaperDeep Auxiliary Learning via Bilevel Feature Optimization for Label-Efficient Medical Image Segmentation
Auxiliary learning (AL), which can improve the performance of a primary task by leveraging related auxiliary tasks, is commonly regarded as a special case of multi-task l
- PaperMorpheus: a fully local, defense-in-depth de-identification engine for Greek clinical text - a benchmark evaluation
Background and Objective: Clinical free text cannot leave the hospital without de-identification, yet no de-identification system or benchmark exists for Greek clinical t
- PaperLearning without Overwriting: Structural Knowledge Fusion for Continual Learning
Catastrophic forgetting in sequential deep learning arises from a fixed-capacity architectural constraint: parameter updates encoding new tasks perturb weight subspaces s
- PaperFHKAN: Fractional Hermite Kolmogorov-Arnold Networks for Data-Driven and Physics-Informed Learning
Kolmogorov-Arnold Networks (KANs) replace fixed scalar weights by learnable univariate maps, yet most spectral KANs still rely on Chebyshev polynomials that live on a bou
- PaperPLANE: Plug-and-Play Fine-Grained Visual Experts for Hallucination Mitigation in Large Vision-Language Models
Large Vision-Language Models (LVLMs) commonly suffer from hallucinations, which appear as fabricating non-existent objects or outputting incorrect attributes and spatial
- PaperA Multi-granularity Interaction Network for Relational Triple Extraction
Relational triple extraction identifies entity relations from raw sentences without depending on entity type information. The performance of traditional methods is seriou
- PaperImage Dehazing as In-Context Tabular Inference
Image dehazing is traditionally addressed through handcrafted physical priors or task-specific deep learning models, often requiring carefully designed architectures or e
- PaperSpectral Adaptive Graph Transformer for Efficient and Scalable Traffic Forecasting
Traffic forecasting models based on spectral graph convolution offer an interpretable account of how information is mixed between sensors, but they rely on an eigendecomp
- PaperReflection-Guided Dynamics Rectification for Text-to-Image Generation
Fine-grained rectification of existing generations under a limited additional budget remains a key problem in test-time optimization (TTO) for image generation. As for pr
- PaperHullProbe: Measuring Interventional Part Reliance in Maritime Vessel Classifiers
Recognizing a vessel's type from an image supports maritime surveillance and sanctions monitoring, but a classifier can reach high accuracy by leaning on the generic hull
- PaperTIRE: Top-Down Formula Instantiation with Reliable Execution for Physics Problem Synthesis
Advancing physics reasoning in large language models requires scalable training data that connect physical laws, concrete problem scenarios, and verifiable numerical answ
- PaperMany Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use
Cryptographic API misuse in large language model-generated code can compromise software security. While many existing approaches improve code security by modifying model
- PaperDecision-Target Reversal under Informative Label Missingness
Informative label missingness can improve classification efficiency because the pattern of label availability may itself contain information about the discriminant struct
- PaperMemBubble: Benchmarking How Agent Memory Shapes LLM Response Diversity
Memory serves as the core component of LLM-based agents, enabling personalized responses via extracting and using user preferences from past interactions. However, its us
- PaperTrackable Skill Library Lifecycle Management for Agentic Reinforcement Learning
Skill-augmented agentic RL has emerged as an effective approach to improving LLM agents on long-horizon tasks. Despite this progress, individual skills may follow distinc
- PaperThe Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering
Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has str
- PaperBeyond Policy Discrepancy: Capability-Aware Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) integrates domain specialists into a shared student, but determining how strongly each teacher should supervise remains challe
- PaperMemories That Outlive Their Reasons: Dependency-Tethered Memory for Tool-Using LLM Agents
Agents now act on the Web, publishing packages, models and datasets through registry APIs, and remembering past verifications spares them the work. But a verdict rests on
- PaperBehave Like Experts: Fusing Data with Semantic Knowledge for Effective and Efficient Semantic Map Construction
Semantic map models (SMMs) construct a graph that reflects conceptual similarity by comparing cross-lingual form-meaning mappings. Experts build such models not only by o
- PaperClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer
Offline sepsis treatment aims to learn treatment policies from retrospective ICU trajectories. Decision Transformer-based methods provide a natural sequence modeling fram
- PaperLC-TSRNet: A Land-Cover-Guided Two-Stage Network for Annual MODIS Surface Reflectance Time Series Reconstruction
MODIS surface reflectance (SR) products often suffer from data gaps due to cloud contamination and sensor malfunctions, limiting their applications in long-term and large
- PaperMemory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents
Large language model (LLM) agents increasingly rely on external memory to accumulate past experiences for continual adaptation. However, effectively reusing memory requir
- PaperPolynomial Learning of Positive ReLU Networks under Gaussian Inputs
We study positive, bias-free, one-hidden-layer ReLU networks under standard Gaussian inputs. We obtain algorithms with polynomial sample and real-arithmetic complexity, w
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.