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
- PaperAtoms, Not Knowledge: What Production-Scale Addressed-Memory Writes Deposit
Deterministic hash-addressed conditional memory permits local post-hoc knowledge injection. Extending arXiv:2610.21553's bounded-feasibility audit rejecting under-specifi
- PaperSENRI: Understanding the Space-Event Nexus in Real-Life Videos
Human memories are organized in a way that connects events with their corresponding spatial contexts. An AI assistant should also be able to memorize and recall the nexus
- PaperShared-Private Cross-Modal Discrepancy Learning for Imbalanced Multi-Source Audio-Visual Deepfake Detection
Audio-visual deepfake detectors are often trained under a single dataset or manipulation regime, but multi-source training collections may contain heterogeneous attacks a
- PaperLearning When to Abort in Transformer Planning: A Mechanistic Study
Planning does not by itself imply the ability to recognise errors, but recognising errors can improve planning capacity. In this paper, we study this phenomenon in Transf
- PaperAligning Language Models with Indigenous Community Cosmovision through Constitutional AI
Large language models (LLMs) are predominantly trained on corpora that reflect Western, anglophone worldviews. This asymmetry is not neutral: when a model answers questio
- PaperWorld Model Interpretability: From Decoding Representations to Understanding Latent Worlds
Emerging Joint-Embedding Predictive Architectures (JEPAs) are moving beyond representation learning towards latent world models that support prediction, planning, and con
- PaperMotionShift: Environment-Compatible Motion Transfer via Planner-Evaluator Synergistic Adaptation
Existing motion transfer methods excel at exact, rigid motion replication from reference videos to target scenes, whereas they often fail to account for the compatibility
- PaperThe Explainability Illusion: Must ViTs Exhibit Patch-Decoding Interpretability?
Transformers are widely assumed to exhibit token-decoding explainability. In particular, in vision transformer (ViT) classifiers, decoding individual patch tokens has bec
- PaperVision as Proprioception: Estimating Humanoid Robot Pose from Video
Estimating a humanoid robot's internal state from video has a wide range of real-world applications but remains unexplored. During interactions with a robot, its onboard
- PaperA discrete-continuous-time stochastic framework for attention-deficit/hyperactivity disorder-related symptom modeling and pharmacological intervention via methylphenidate
This paper presents an original mathematical and computational framework for modeling the efficacy of methylphenidate as an optimal control policy acting on the nonlinear
- PaperLearning Lane-Structured Conditioning Fields for Online HD Mapping
High-definition maps provide critical structural information for downstream autonomous driving tasks. Recent methods increasingly rely on external priors to improve predi
- PaperData-driven forecasting of tropical cloud forest phenology: A dynamical systems and machine learning hybrid approach
Forecasting how species and ecosystems respond to climate change is a critical challenge in ecology, particularly in hyper-diverse tropical biomes. While traditional phen
- PaperBridging Concepts: Multi-Agent Reasoning over Scientific Concept Graphs for High-Impact Research Prediction
Within a research community, new topics often emerge when previously unconnected concepts are first studied together. We construct scientific concept graphs (SCGs)--domai
- PaperHolo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible.
- PaperGeoART: Geometry-Aware Refinement via Test-Time Scaling for Camera-Conditioned Video Diffusion
Camera-conditioned video diffusion models often suffer from inaccurate camera control and geometric inconsisten- cies because camera constraints and estimated geometry ar
- PaperEG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents
LLM-based search agents demonstrate strong capabilities in long-horizon information seeking and reasoning, typically trained via reinforcement learning. However, existing
- PaperSPARC: Spoken Profile Authorship Recognition Corpus
Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwis
- PaperFederated Learning for Malware Image Classification under Data Heterogeneity
Malware image classification (MIC), in which binary files are converted into visual representations and deep neural networks are trained to identify malware families, has
- PaperEasyResearch: Honest Regression, Forecasting and Signal Classification for Researchers Who Do Not Program
EasyClassifier showed that researchers who do not program can obtain honest classification results when the correct evaluation is the default. Most applied studies, howev
- PaperEmergent Sparsity: How Many Effective Variables Survive Coarse-Graining in AlphaEarth Embeddings?
AlphaEarth encodes each 10 m land pixel as a 64-component vector intended to support diverse global mapping tasks. Yet many scientific applications work at coarser spatia
- PaperPanoDent-KD: From Generalist Knowledge Distillation to Cross-Dataset Specialist Detection and Embedded Deployment in Panoramic Radiographs
Reliable panoramic-radiograph detection requires consistency across datasets with different class definitions and deployment software. We present PanoDent-KD, an auditabl
- PaperBatchParScale: Sparse Batch-Mixing for Sequence Models
Recent test-time scaling methods improve model performance by increasing inference-time compute. One practical form of this is parallel scaling, where a model samples mul
- PaperPersistent Representational Misalignment Induces Vision-Language Model Failures
Vision-language models (VLMs) fail at some tasks that are simple for humans---but why? We hypothesize that many such failures stem from VLMs' difficulties translating bet
- PaperImproving the Expressive Power of Hybrid Sequence Models via Multi-Hop Retrieval
Hybrid architectures offer a promising approach to efficient language modeling by combining a small number of full-attention layers with a larger number of efficient sequ
- PaperVisual Scaffolding: Toward Native Multimodal Reasoning
The success of chain-of-thought (CoT) in complex reasoning can be attributed to a textual scaffolding effect: explicit intermediate results can be examined, reused, and c
- PaperEstimating Causal Bounds from Observational Data With Neural Generative Models
Identifying causal bounds from discrete observational data is a fundamental problem in causal inference. While exact analytical bounds exist for certain graphs, this is n
- PaperGeoV2V: Geometry-Grounded Video Diffusion Model for Driving Scene Generation
Novel view synthesis under trajectory changes is essential for autonomous driving simulation, yet existing methods struggle to generate consistent videos when extrapolati
- PaperAssessing the Empirical Evidence for Loss of Control from Agentic General-Purpose AI
Theoretical literature warns that advanced generalist agentic systems might pursue instrumental goals that are misaligned with human preferences, thus posing risks of irr
- PaperEvaluating Cloud and Self-Hosted OCR Systems for Arabic, English, and French Documents: Bounding Box Detection, Text Recognition, and Mathematical Expression Recognition
Choosing an OCR system for a multilingual archive requires balancing accuracy against deployment constraints. This study compares cloud and self-hosted systems on three t
- PaperMap2Vid: Embodied Navigation Video Generation with Human-Friendly Motion Control
Controllable video generation has recently achieved impressive visual quality, yet existing control paradigms remain poorly suited to embodied navigation. Text prompts ar
- PaperDROD: Dual-Ratio Ordered Dropout for Federated Continual Learning on Heterogeneous Devices
Federated learning for capacity-heterogeneous clients and federated continual learning are each well studied on their own, but their intersection -- clients holding diffe
- PaperHidden Cartographer: Hidden State Guided Data Selection for Dual Budgeted Instruction Tuning
Given the high cost of expert annotation and limited fine-tuning resources, effective data selection from large unlabeled pools under strict budgets has become a crucial
- PaperDo LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness
In this paper, we investigate the issue of difference awareness in LLMs, defined as a model's ability to recognize and acknowledge meaningful differences between social g
- PaperLiftDiff: Guided Discrete Diffusion for Quantum Code Construction
The realization of fault-tolerant quantum computation relies on Quantum Error-Correcting Codes (QECC). Of particular interest are codes that combine a high encoding rate
- PaperCalibration-Free Early Stopping for Chain-of-Thought Reasoning via E-processes
Reasoning large language models (LLMs) benefit from test-time scaling, motivating adaptive policies that spend tokens when they help and stop early otherwise. Existing ru
- PaperNeuroAct: Advancing EEG Analysis and Decoding via Dual-Loop Autonomous Research
EEG analysis and decoding underpin brain-computer interfaces, cognitive assessment, and sleep monitoring. Fixed pipelines and reward-driven search do not explicitly deter
- PaperBrandEval: A Two-Track Multi-Agent Benchmark for Risk-Sensitive LLM Crisis Communication
Evaluating LLMs for crisis communication requires more than judging isolated responses, because public feedback and competitor actions can reshape trust over time. Existi
- PaperA Thousand Faces: A Persuasion Benchmark with Experience-Grounded Persuadees Informed by Psychology and Pragmatics
People can express the same beliefs and desires yet need different reasons to change their minds. What makes an argument relevant depends on how those views arose: experi
- PaperDynamic System Inspired Continuous Large Language Model for AI4Science Tasks
Scientific foundation models increasingly operate on continuous phenomena, yet still use discrete residual computation. We ask whether pretrained residual transformations
- 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
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.