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…
Friday 16 October
- PaperPanoBench: A Panoptic Occupancy Prediction Benchmark for Autonomous Driving
Panoptic occupancy unifies 3D geometry, semantics, and instance identities, but its development is limited by scarce instance-aware annotations. Existing benchmarks mainl
- PaperPreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing
Recent one-step text-to-image (T2I) models enable efficient image synthesis, opening up new possibilities for interactive Web-based image editing. However, existing one-s
- PaperFrom Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation
Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make t
- PaperReVision: Reprogramming Image Generators for Dense Visual Perception
Recent image generators exhibit rich visual priors that can support dense visual perception. However, existing approaches typically encode multiple perception tasks into
- PaperPONDER: Learning to Generate in the Right Order
We introduce PONDER, a method that learns in which order an image generator should fill in content and which of its earlier predictions to revise. Masked generative model
- PaperEduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them
Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introd
- PaperOut of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed Tasks
In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks from a small set of input-output demonstrations, without parameter updates. Yet existing th
- PaperTruth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods
Large Language Models (LLMs) encode substantial factual knowledge. Yet, estimating confidence in factual claims reliably remains challenging. We study likelihood-based fa
- PaperInterpreting SSL Representations for Spoof Detection: a WavLM Study
Self-supervised speech models such as WavLM achieve strong spoofing detection performance, yet which layers encode the most spoof-relevant information and what acoustic p
- PaperTrapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models
Large language models (LLMs) are known to exhibit sycophancy by adjusting their responses toward users' expressed views. However, real users often justify their opinions
- PaperPerceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs
Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most work uses LLMs as f
- PaperUncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awareness
We present a two-stage AI-enabled framework for enhancing operator situational awareness during compressed hydrogen bunkering in maritime confined spaces. In the event of
- PaperLocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs
Locally deployed large language models (LLMs) can reduce reliance on remote cloud services for natural language smart building automation, but backend-facing processing r
- PaperAdaptive conformal prediction on the Grassmannian
We introduce a conformal prediction framework for regression with Grassmann-valued responses. The proposed method constructs prediction regions in the form of metric ball
- PaperA Topological Signature of Learning under Noisy Labels
How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little informati
- PaperMuninAI: A Self-Hosted Agentic Framework for Independent Research Groups
Research groups that want a language model grounded in their own literature face a choice between hosted services that receive their unpublished work and self-hosted depl
- PaperTowards optimal selection schedules for online active learning
We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query poli
- PaperTAN: A Size- and Form-Adaptive Masked-Convolution Encoder for Tissue Graphs
Tissue graphs represent histology images as graphs over tissue-conforming superpixels, which keeps homogeneous tissue regions intact instead of cutting them into rectangu
- PaperQD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity
Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. W
- PaperWhen Evidence Vanishes: Distilling Visual-Evidence Dependency in Medical Vision-Language Models
Compact medical vision-language models (VLMs) can answer clinical questions correctly without reliably using the image, relying instead on question wording or learned pri
- PaperGraphlet-based Decentralized Finance Transaction Method Classification
Decentralized Finance (DeFi) transactions involve complex interactions among accounts, smart contracts, and tokens. We investigate whether network topology can identify t
- PaperS-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models
Graph Large Language Models (GraphLLMs) enable powerful semantic understanding and reasoning over Text-Attributed Graphs (TAGs), while their semantic reasoning may exhibi
- PaperA low-dimensional dynamical basis for tongue shape control
Speech production involves the control of a high-dimensional articulatory system with many degrees-of-freedom, but a widespread hypothesis is that speakers navigate this
- PaperHydraLLM: Adaptive Width Slicing for Elastic Text and Vision-Language Models
LLMs and LVLMs are increasingly deployed across heterogeneous hardware, ranging from data-center GPUs to resource-constrained edge devices. Their fixed-size architectures
- PaperTriINR: Unsupervised Atmospheric Turbulence Mitigation with Triple Implicit Neural Representations
Atmospheric turbulence degrades image quality in long-range imaging. The degradation is generally modeled with two spatio-temporally varying components, tilt and blur. Re
- PaperPredictable Scaling: Efficient Model Exploration via Scaling-Law Prediction
Evaluating candidate changes (hypotheses) to recommendation models requires full-scale training runs consuming thousands of GPU-hours, severely limiting the hypothesis sp
- PaperGatewayBench: Unified Capability and Security Evaluation Platform for MCP Gateways
AI agents have increasingly interacted with external environments by invoking tools, with Model Context Protocol (MCP) emerging as a standard interface for connecting age
- PaperRegularized free deconvolution for spectral repair of resampling distortion in high-dimensional particle filters
Resampling is the standard remedy for weight degeneracy in particle filters, but in high dimensions it distorts the spectrum of the ensemble covariance in a way that is c
- Paper"You" Is Not Toxic: How LLM Labelers Rewrite the Web's Conversation Laws
What the Web community believes about toxic conversations, such as that toxicity rises in longer and deeper threads, was measured mostly with Google's Perspective API, wh
- PaperRECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this pape
- PaperScoutRoute: Efficient Mixture-of-Experts Routing Using Internal Language Model Signals
Efficient expert routing is a fundamental challenge in Mixture-of-Experts (MoE) systems, particularly for heterogeneous collections of independently trained Large Languag
- PaperShadowCast: On-the-Fly Context-Aware Shadow Augmentation for Remote Sensing Image Segmentation
Shadows cast by elevated objects alter the spectral appearance and obscure the boundaries of objects in remote sensing images, thereby degrading semantic segmentation per
- PaperGenerative Policy Improvement from Observational Data
We study how to improve decision policies from observational data to generate better actions when actions are complex, structured objects, such as text messages or images
- PaperBridging Compressed Communication and Local Steps via Spectral Method in Federated Learning
Federated Learning (FL) enables collaborative training of complex models across large-scale networks of edge devices while keeping data localized. However, data heterogen
- PaperMomentum: Persistent Dynamics for Video World Models
Video world models must capture how a scene evolves beyond the current camera view to generate consistent observations when its content reappears. Existing approaches rel
- PaperResidual Stochastic Concept Bottleneck Models
Concept-based models (CMs) learn human-interpretable intermediate representations that enable users to understand the model's reasoning and steer its predictions through
- PapermmPencil: Toward Writing-Style-Independent In-Air Handwriting Recognition via mmWave Radar and Large Vision-Language Model
In-air handwriting recognition based on radio frequency (RF) signals offers a promising solution for human-computer interaction, yet existing methods are often limited by
- PaperGeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing Segmentation
Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, extending this capab
- PaperCan We Use Saliency Maps for the Evaluation of Generative Image Models?
Evaluating generative image models remains challenging, as commonly used metrics depend on fixed pretrained feature extractors optimized for different tasks that do not a
- PaperFlash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation
The recurrent neural network transducer (RNN-T) remains a practical choice for streaming speech recognition, but training requires large intermediate tensors. We present
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.