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…
Thursday 15 October
- PaperOptimal approximation of smooth functions by ReLU neural networks
We study uniform approximation of the Hölder ball $\mathcal H_1^s([0,1]^D)$ by fully connected ReLU networks. Except in the one-dimensional Lipschitz case, existing const
- PaperQuantum-Classical Neural Networks for Solving Lindblad Master Equations
Variational quantum algorithms have emerged as a promising approach for simulating open quantum systems, yet their expressive power and trainability remain poorly underst
- PaperExplore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
Large language model agents must discover relevant tools from large libraries, e.g., thousands of tools, as new needs arise during task execution. When several candidates
- PaperMultimodal Filesystem Memory For Long-Horizon Embodied Agents
Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions. If the entire history of an interact
- PaperAlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model
- PaperFlexUMM: Flexible Representation Learning for Unified Multimodal Models
Unified multimodal models (UMMs) can integrate understanding and generation within a single backbone. However, it is commonly known that these two capabilities can cause
- PaperEgoP$^{2}$C: Internalizing Plan-Perceive-Compose for Spatial Reasoning in Egocentric Video
Answering complex spatial reasoning questions from egocentric video requires determining what evidence is needed, acquiring targeted observations, and combining them thro
- PaperDeep Learning for Deepfake Image Detection: Comparative Model Evaluation and Gradient-Based Visual Attribution
Synthetic facial imagery has made the distinction between authentic and generated content increasingly important for digital forensics and online trust. This study examin
- PaperNot All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation
Modern mobile GUI agents can perceive visible screens and execute local actions, but they still lack persistent app-specific navigation knowledge: where functions live, w
- PaperMemoProAgent: Toward Memory-Driven Proactive Assistance
As assistants move from reactive answering toward proactive intervention, memory changes role: it no longer only supplies the answer to a query, it determines whether and
- PaperFrom Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents
Long-term memory enables LLM agents to reuse past experiences, yet retrieving relevant memories does not necessarily provide sufficient evidence for answering a query. Es
- PaperDiverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for Enhancing RL Exploration
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for improving the reasoning capabilities of LLMs. However, the role of supervised
- PaperEdit Discovery in Human-AI Interactions
Human-AI interactions are becoming a rich source of data for improving AI systems: while many model responses are already satisfactory, others expose failures that could
- PaperExploring The Empirical Privacy Landscape of Synthetic Data
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we pres
- PaperSecondhand Stress: How Stressful Disclosures Affect Psychosocial Wellbeing in Online Graduate Admissions Communities
Online communities provide spaces for individuals navigating stressful life transitions to disclose difficulties and seek peer support. Yet encountering others' distress
- PaperIs a Linear Probe Evidence of a Linear Representation?
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a sta
- PaperAn Anatomy-Aware Staged Pipeline for Vessel-Specific Intracranial Aneurysm Segmentation in CT and MR Angiography
The TopAneu 2026 challenge requires intracranial aneurysms to be segmented at the voxel level and assigned to one of more than fifty vessel-specific classes, on CT and MR
- PaperEvidence-Gated Bilingual RAG for Reliable Consumer Banking Search
Consumers often describe what they need rather than use the terminology found on a banking website. For example, a natural-language request ("a card for travel") may not
- PaperThe Ephemeral Cost of Switching Optimizers Across LLM Training Stages
Recent work suggests that switching optimizers between pretraining and subsequent training stages incurs a performance cost, but systematic investigation of this phenomen
- PaperLGGS: Longitudinal MRI Reconstruction via Guided Group Sparsity
Serial MRI is routinely performed in current clinical practice for disease surveillance and applications such as MR-guided radiotherapy. However, long MRI scan times incr
- PaperSAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors
Model-editing backdoors aim to induce harmful responses under a trigger while preserving ordinary behavior on untriggered input. Recent model-editing approaches target af
- PaperInductive Learning of Concept Embeddings from Cross-Linguistic Colexification Patterns with Textual Attributes
The advent of distributional semantics as a framework for computational semantics marked a paradigm shift in the nature of representations, by which meanings are represen
- PaperHard Instances on Demand
The conclusions of an experimental study of algorithms are only as good as the instances they are run on. Benchmark libraries for well-studied problems took decades to cu
- PaperMeasuring Mechanistic Uncertainty in Large Language Models via Causal Robustness
Large language models (LLMs) are increasingly used in critical domains, where their susceptibility to hallucinations makes reliable and interpretable uncertainty quantifi
- PaperAlert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction
Preprocessing is an under-measured reliability risk in clinical prediction: a model can keep a similar AUROC and still change who receives an alert. Imputation quality is
- PaperToMStories: Interpreting Theory-of-Mind in Synthetic Narratives
Understanding people often requires inferring what they feel or want from how they behave rather than from what they state outright. We ask whether language models can ma
- PaperA Plausible Explanation Is Enough to Mislead Multimodal Judges
Multimodal large language models (MLLMs) increasingly serve as judges in training and evaluation pipelines, often assessing answers together with explanations. Although A
- PaperNetwork-Wide Freeway Speed Nowcasting and Forecasting from Sparse Fixed Sensors with a Probe-Supervised Graph Convolutional Recurrent Network
Traffic agencies need current and near-future speeds on every link of their network, but their fixed sensors cover only part of it. We study joint nowcasting and next-hou
- PaperStratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mec
- PaperUnderstanding Stability of Outer Nesterov Momentum on Stochastic Pseudo-Gradients
Large neural networks are commonly trained across many workers, and communication between them is a major cost. Workers therefore take several local optimization steps be
- PaperNoise-shaped Sampling and Annealing for Scalable On-the-edge Training of Binary and Ternary AI Models
The training loss of binary and ternary neural networks, expanded as a multilinear polynomial over the discrete weights, is structurally equivalent to the energy of a hie
- PaperTrajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification
Large language models rely on spurious features in clinical classification: swapping a single gender token in clinical notes alters gender-irrelevant diagnoses in up to 5
- PaperWhen Does Uncertainty Measure RAG Hallucination Risk?
Uncertainty can measure hallucination risk in retrieval-augmented generation (RAG), but only when retrieved evidence constrains the answer. When evidence is present, unsu
- PaperShift-Reliance Alignment: Ranking Vision-Language Models by the Cues They Trust
Vision-language models (VLMs) are usually chosen from leaderboards, which give one ranking for every application. On questions about objects that a scene suggests but doe
- PaperProactGen: Learning Proactive Clarification for Video Generation
Recent advances in video generation let users create high-quality videos from natural language descriptions, yet obtaining results that match user intent remains time-con
- PaperThree LiDARs, Twenty-Five Datasets: Cross-Source Generalization in Tree-Species Recognition
FOR-species20K is the largest public LiDAR benchmark for tree-species classification, pooling 25 independently collected terrestrial, mobile, and airborne laser-scanning
- PaperBeyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation
Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately
- PaperRarity of Singletons Matters & Supplementary Materials
Estimating missing-mass and unseen-species counts from finite samples relies heavily on rare-event occupancy statistics, particularly singletons. In small-sample regimes,
- PaperAt the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier
Recent breakthroughs in AI for mathematics---ranging from Olympiad medal performances to resolving long-standing open conjectures---have rapidly expanded what automated s
- PaperStuck on Shuffle: On Attribute-Object Binding in Vision-Language Models
Retrieval is a fundamental task in multimodal systems: given an image or text query, the goal is to find the most relevant images or texts in a collection, often using a
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.