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…
Tuesday 20 October
- PaperDecoupled Representation Learning for Face Presentation Attack Detection under Smart Glass Capture
Face presentation attack detection is typically studied under fixed camera or handheld acquisition, whereas smart glass capture introduces a more challenging setting with
- PaperToward Agentic AI for the 6G Physical Layer: From Algorithm Discovery to Verified Baseband Silicon
6G will be designed faster than it can be built: AI-driven search already proposes physical-layer algorithms at machine speed, while carrying a single one onto embedded b
- PaperTerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction
Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations in Earth system models
- PaperAre Linguistic and Arithmetic Circuits Dissociated in LLMs?
Large language models (LLMs) exhibit both knowledge of language, rendered by, for example, grammatical judgment ability, and abilities to perform tasks through language,
- PaperFoundations of the Scaling Law
Empirical scaling laws relate validation loss to model size, training exposure and compute, providing a quantitative basis for allocating resources. This technical note e
- PaperSLM-SS: Token-Based Speech Separation with Speech Language Models
Speech separation (SS) has witnessed substantial progress in recent years with the advent of neural network-based methods, achieving notable improvements on signal-level
- PaperRELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic Repair
Vulnerability benchmarks and software engineering research depend on rebuilding historical software. Yet builds rely on external resources, such as base images and packag
- PaperRoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions.
- PaperGRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus
Training LLM agents for policy-constrained tool environments, such as an airline backend with booking, refund, and cancellation policies, requires tasks that exercise the
- PaperRITE: Evaluating End-to-End Resilience to Silent Tool Errors in E-Commerce Agentic Systems
Tool-using LLM agents increasingly answer e-commerce queries through multi-step tool interactions. The expected output of a tool call can shift between agent development
- PaperGeometry Regularization for Vanilla NeRF via Self-Supervised Cross-Ray Consistency
Neural Radiance Fields (NeRF) achieve high-quality novel-view synthesis by representing a scene as a continuous volumetric radiance field. However, the geometry encoded b
- PaperRadar-Based 3D Human Pose Estimation via Motion-Aware Pose Initialization and Observation-Guided Refinement
3D Human Pose Estimation (3D HPE) is used in indoor environments, such as smart homes, to analyze human movement and monitor human states. Millimeter-wave (mmWave) radar
- PaperHow Much Do $\ell_1$ Attacks Need Concentrated Perturbations?
A global $\ell_1$ budget limits how much an adversary may change an image, not how that change is distributed. We ask how much of an $\ell_1$ attack's observed success re
- PaperEngram Memory Network: Brain-Inspired Prototype Explanations
Artificial intelligence systems are increasingly deployed in high-stakes decision-making. In response, prototype-based models in explainable AI have attracted growing att
- PaperFoundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting
The rapid growth of distributed photovoltaic (PV) generation is increasing the demand for accurate forecasting across large numbers of geographically dispersed stations.
- PaperCrystalAR: Autoregressive Modeling for Symmetric Crystal Generation
Deep generative modeling has achieved remarkable progress in crystal generation. Given the rich symmetries inherent in crystalline structures, recent work has sought to e
- PaperPixelSR: Pixel-Space Orthogonal Flow Decoupling for Real-World Image Super-Resolution
Latent diffusion models have recently achieved remarkable progress in Real-world Image Super-Resolution (Real-SR). However, existing methods consistently exhibit a persis
- PaperAC/DC on a Budget - Alternating Sparse Phases
State-of-the-art neural network sparsification relies on alternating dense and sparse training phases. While computationally expensive, dense phases are critical for perf
- PaperRevealing Inter-Channel Modality Discriminability: Channel Selective Interaction Fusion Network for Optical-SAR Object Detection
Synthetic aperture radar (SAR) and optical imagery provide complementary structural and appearance information for remote sensing object detection. However, substantial c
- PaperGive the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language Models
Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cr
- PaperDetection of Memorization in Diffusion Models Through Thermodynamic Singularity
In diffusion models, proper distributional learning entails reversing a diffusion process over underlying density functions, whereas a key failure is memorization, in whi
- PaperConstant Step Sizes for Muon-Type Spectral Optimizers on Strongly Convex Quadratics
Muon and related optimizers update a weight matrix with a spectrally transformed gradient. In this work, we study such spectral optimizers with a constant step size on st
- PaperS$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents
Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS,
- PaperHearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates
Large language models (LLMs) are increasingly used as judgment assistants and as stand-in participants in psychology experiments, yet little is known about how much their
- PaperEEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural Networks
Guided Imagery (GI) is a mind-based relaxation technique widely used in clinical and therapeutic settings. Objectively assessing whether a patient has entered a relaxed s
- PaperRSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?
Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has recei
- PaperCILA: Confusion-based Instance-wise Logit Adjustment for Long-Tailed Recognition
Real-world datasets are inherently class-imbalanced, leading models to favor majority classes and struggle with minority ones. Existing logit adjustment methods address t
- PaperAnytime-Valid Runtime Monitoring of Learned Barrier Certificates
Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the u
- PaperWorld2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation
Long-horizon human-object-scene interaction (HOSI) is central to embodied AI, animation, and game development. Existing human-object interaction (HOI) and human-scene int
- PaperHow Language Models Organize Task Information
Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure read
- PaperTracing Recurrent and Emergent Hallucination Patterns in Decomposed Text-to-SQL Generation
Large language models can achieve strong Text-to-SQL benchmark performance while still producing schema and query-logic errors. Most evaluations characterize such failure
- PaperPush-Pull Attentional Anchoring for Diffusion Concept Erasure
Rapid advances in diffusion models have raised concerns about privacy, harmful content, and copyright violations. Concept erasure methods aim to address these risks by re
- PaperWhen Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines
When does experience memory help a closed-loop LLM driving agent? Published gains cannot say, because the two factors we find to matter most, which warmup experiences the
- PaperRLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within li
- PaperHow Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence (\textsc{s2s}) on binary hall
- PaperPrivacy Accounting for Empirical Denoisers
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (
- PaperVEOcc++: Learning Persistent Voxel Feature Maps for Embodied Online Semantic Occupancy Mapping and Offline Refinement
Semantic occupancy mapping supports embodied perception during exploration and detailed scene understanding afterward, giving rise to two complementary requirements: onli
- PaperMulti-Objective Evolutionary Semi-Supervised Learning for Resource-Aware Smart City Classification
Smart-city applications often combine scarce labeled data with abundant unlabeled observations. Semi-supervised learning (SSL) exploits both labeled and unlabeled data to
- PaperBeyond Calibration: Temporal LLM Confidence Assessment Across Languages and Local Settings
Large language models are expected to estimate their own uncertainty, with confidence signals used to guide retrieval, adaptive compute allocation, routing, and selective
- PaperUnderstanding Data Augmentation under Label Noise
Data augmentation (DA) has become a fundamental component of modern machine learning systems and is widely regarded as an effective strategy for improving robustness and
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.