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…
Monday 19 October
- PaperNeighborhood-Aware Unlearning for Generative Recommendation
Generative recommendation predicts items by autoregressively generating semantic identifiers (SIDs), whose tokens are shared across semantically related items. With this
- PaperMagnolia: A Persistent-Memory Agent Framework for Computational Chemistry
Chemistry has recently entered a high-data regime as molecular databases from high-throughput platforms or computational studies have become available. Increasing automat
- PaperWhich Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams
Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and
- PaperSparse RL Relaxation for LLM Reasoning
Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated
- PaperDeep catastrophic-risk-aware reinforcement learning
Estimating extreme risk in reinforcement learning becomes increasingly difficult as the confidence level increases, since only a small number of observations contribute t
- PaperProfile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests with rich, user-specific facts. This paradigm expose
- PaperA Theoretical Analysis of Environment-Aware Out-of-Distribution Detection for Vision-Language Models
Continual vision-language models (VLMs) encounter a stream of environments and must also reject inputs that do not belong to the environment at hand. Class information fr
- PaperYou Are the Trigger: Speaker-Activated Backdoors
Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attacker to introduce tri
- PaperLanguage Guidance for Supervised Vision Training: An Empirical Study of Generalization
Deep neural networks have achieved remarkable success on vision benchmarks, yet they continue to struggle with many generalization challenges. Supervised vision training
- PaperDiffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates
We study the sample complexity of estimating Ornstein--Uhlenbeck diffusion scores in $\mathbb R^d$ using denoising score matching (DSM) with finite-width shallow ReLU net
- PaperLoWAgent: A Low-Resource Multilingual Benchmark for Web Agents
Web agents are typically evaluated on English-language interfaces, leaving their ability to operate across the world's multilingual websites largely unexplored. This gap
- PaperLSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning
Class-Incremental Learning (CIL) enables models to recognize new classes over time while retaining prior knowledge, but many real-world problems are compositional, where
- PaperThe Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMs
Large Language Models (LLMs) increasingly operate across culturally diverse settings, yet existing evaluations largely measure cultural behavior at the output level. We i
- PaperPreference-Aware Pareto Steering for Multi-Task Speech LLMs
Speech large language models (LLMs) perform multiple tasks, including automatic speech recognition (ASR), timestamp prediction (TS), and speech translation (ST). Joint tr
- PaperWhich Depth Estimator for Jetson AGX Orin? A 2026 Benchmark of Monocular and Stereo Methods
The Jetson AGX Orin is a common computer for robots and vehicles, yet measured accuracy, speed and energy of current depth estimators on it are hard to find. We benchmark
- PaperLow Residuals, Wrong Value: Learning the Viscosity Solution of Hamilton-Jacobi-Isaacs Equations with PINNs
Physics-informed neural networks (PINNs) and other residual-trained solvers judge a candidate solution by the size of its sampled PDE residual. For first-order Hamilton-J
- PaperCARLAR Influence: A Structured Hallucination Risk in Multimodal Cheque Extraction and an Exploratory Compressed-Image Countermeasure
Multimodal large language models (LLMs) are increasingly used for structured extraction from financial documents, but their behavior under visual ambiguity is poorly unde
- PaperOn the Fragility of Tasks under Composition: Implicit Budgeting in Language Models
Modern language models are increasingly asked to handle several tasks within a single prompt. Doing so requires solving each task correctly while integrating the resultin
- PaperMeta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments
Learning latent dynamics is central to assessing the current states and forecasting the future trajectories of high-dimensional time series. For locally-stationary latent
- PaperSITO: Sifting a Commercial Text-Safety API for Missed Harm and False Flags in English, Ukrainian and Surzhyk
Platforms that host young users screen messages with commercial text-safety APIs, but independent evidence on how often such systems miss harm or flag harmless text is sc
- PaperVisual Task Modeling and Automated Planning for Humanoid Robots in Education of Individuals with Autism Spectrum Disorder
In robot-assisted education, a robot must understand how to complete a task in order to effectively guide a student through it. We present a novel method that enables a s
- PaperLearned Control Variates for Rare Grid-Outage Estimation at Electric Vehicle Charging Stations
Public charging of electric vehicles (EVs) adds a large and synchronized load to the distribution feeders. In most networks, it is rare to overload a feeder at the same t
- PaperUnderstanding the Benefits of Scaffolds through Computational Separations
Inference-time harnesses, i.e., external procedures that call a model many times and keep state across calls, can substantially improve model capabilities. In this paper,
- PaperMoSAIK: Motion Search with Artificial Intelligence in K-space
Object: Motion artefacts remain a major limitation of routine two-dimensional T2-weighted turbo spin-echo (TSE) brain MRI, reducing diagnostic confidence and often necess
- PaperA Hybrid TFT-NBEATS Framework for Robust Multi-Horizon Photovoltaic Power Forecasting
Accurate multi-horizon photovoltaic (PV) power forecasting is essential for grid stability, energy scheduling, and the efficient operation of PVbatterygrid systems. Howev
- PaperModel Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices
Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to cloud-based deploy
- PaperCross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases
As two most prevalent neurodegenerative diseases (NDDs), Alzheimer's disease (AD) and Parkinson's disease (PD) shared commonalities both in symptomology and pathophysiolo
- PaperGRID: Modeling Health Influencer Discourse as Argument Networks for Credibility Assessment
Health-related discussions on social media are increasingly shaped by influencers who offer diverse, and often competing perspectives on the same issue. Yet, such content
- PaperPRIMFLOW: Learning Trajectory Primitives for Few-Step Distillation
Few-step trajectory distillation aims to learn accurate global updates from dense local supervision along a teacher's sampling trajectory. Existing approaches construct w
- PaperICLHerd: Herding-Based Data Selection for LLMs with In-Context Learning as a Proxy
Data selection plays a central role in modern large language model training, as the quality of training data strongly influences downstream performance. A common approach
- PaperTowards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing
Reliable contact establishment remains a critical challenge for autonomous on-orbit servicing (OOS), particularly when interacting with non-cooperative targets. Gecko-ins
- PaperRepresenting short-term movement to reveal animal identity and learning progress
How learning progresses over time and varies across individuals is a longstanding question in cognitive and behavioral science. However, a major challenge is identifying
- PaperOntic state recovery through prediction
We encounter a system through its responses, yet its state concerns how the system is. Predicting further responses promises knowledge beyond what is immediately observed
- PaperAmmonia-Hydrogen Phase Equilibria in Planetary Envelopes from First-Principles-Based Machine-Learning Molecular Dynamics
Ammonia and hydrogen are major constituents of planets within and beyond the solar system, yet how they interact in planetary envelopes is poorly known. We perform large-
- PaperMind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack
With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privacy protection. However, when edge devices are compr
- PaperGlass-Box Deep Reinforcement Learning for High-Speed Flow Control
Deep reinforcement learning (DRL) is challenging long-held assumptions in active flow control. By learning directly from interaction with a flow, DRL agents can find actu
- PaperReconstruction-Optimized Expert Pruning for Mixture-of-Experts Language Models
Mixture-of-Experts (MoE) models reduce computation through sparse expert activation, but deployment still requires storing a large number of expert parameters. We study p
- PaperEDMA: Entropy-Driven Multimodal Answering
Multimodal question answering (MMQA) is based on integrating heterogeneous data sources, selectively leveraging relevant modalities, and ignoring distractors. Existing ap
- PaperPORA: Learning When More Reasoning Pays Off for LLM Agents
LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the
- PaperPROVISO: Provenance-Informed Action Selection for Secure LLM Agents
LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed act
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.