AI News Archive: June 8, 2026 — Part 24
Sourced from 500+ daily AI sources, scored by relevance.
- EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
Estimating full-hand grasp pressure from egocentric video is critical for immersive VR and robotic manipulation, yet dense tactile sensing often relies on intrusive hardware. Existing vision-based methods predominantly rely on planar surfaces or fingertip contacts, failing to generalize to complex 3...
- Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline
Source detection in modern observational astronomy is a cornerstone for localizing and identifying stellar sources accurately. It is crucial for studies such as stellar population synthesis and cosmological parameter estimation. However, the characteristics of astronomical images, including high den...
- Minimal Solvers for Full-DoF Motion Estimation from Asynchronous Differential SfM
As a bio-inspired intelligent sensor, event cameras have introduced a new paradigm in the intelligent perception of spatiotemporal information and visual motion estimation, characterized by their high temporal resolution, low latency, and minimal power consumption. However, their asynchronous data s...
- In-Context Learning for Latent Space Bayesian Optimization
Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins. In parallel, tabular foundation models such as TabPFN and TabICL now achieve state-of-the-art regression performanc...
- On Choosing the $μ$ Parameter in Gaussian Differential Privacy
Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide principled mappings from pure-DP $\varepsilon$ to GDP $μ$ by matching the worst-case success of a strong-adversary membership inference attack in terms...
- Integrating gene regulatory priors into Transformer attention with scTransformer for interpretable scRNA-seq analysis
Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells. However, most existing approaches treat genes as independent features, and largely ignore prior biological knowl...
- Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy
Single-Molecule Force Spectroscopy (SMFS) provides unprecedented insights into biomolecular mechanics, yet the high-throughput generation of force-extension trajectories creates a severe data curation bottleneck. Identifying rare molecular unbinding events within thousands of noise-dominated curves ...
- Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth
Spatio-temporal graph neural networks (STGNNs) have become the dominant approach for traffic prediction, yet their computational requirements pose challenges for practical deployment in intelligent transportation systems (ITS). While recent work has proposed efficient alternatives to STGNNs, a funda...
- BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference
Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Transformer blocks, but existing methods (i) provide limited control under user-specific compute budgets and (ii) typically fix the routing path, fail...
- Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction
Molecular systems involve interactions across multiple spatial scales, from local coordination and short-range perturbations to long-range electrostatic and solvent-mediated effects. However, most molecular representation learning methods rely on manually predefined scales, and the task-optimal mode...
- Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families
On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models (LLMs) for transferring knowledge from domain experts to student models. However, existing OPD distillation methods require teacher and student models to share the same tokenizer, restricting the a...
- Operator learning for solving Fokker-Planck equations with various initial conditions
The Fokker-Planck equation (FPE) plays a pivotal role in describing the time evolution of probability density functions (PDFs) for systems governed by stochastic dynamics. In this work, we propose a conditional normalizing flow-based physics-informed neural network (PINN) framework for efficiently a...
- Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies. Graph neural networks (GNNs) provide a natural representation but typically rely on autoregressive rollouts and treat spatial and temporal dynamics separately, leading to error ...
- Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the se...
- SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths
Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via ...
- Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. However, its practical effectiveness remains unclear, partly due to LLM pretraining, where overlaps and interdependencies with adaptation data can unde...
- Distilling Safe LLM Systems via Soft Prompts for On Device Settings
Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-d...
- Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
Formal neural network verification -- proving that a network satisfies safety properties for \emph{all} inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $α$-CROWN) require weight and relaxation-coefficient mat...
- CortexDB
Single-file AI memory and knowledge graph for agents
- Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search
Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurement cost with learned cost models, yet they usually evaluate each candidate as a static code snapshot, ignoring the schedule trajectory that produce...
- PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images. However, real-world clients may not share a common modality basis: a visual-search client may contain image--interaction graphs but no seller descriptions, while a catalog clien...
- Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
Contextual queueing bandits provide a framework for learning to schedule heterogeneous jobs under unknown context-dependent service rates. Under stochastic contexts, existing algorithms achieve $\widetilde{\mathcal{O}}(T^{-1/4})$ queue length regret, defined as the expected difference between the le...
- A Unifying Framework for Concept-Based Representational Similarity
Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions. However, concept alignment remains poorly defined: existing approaches optimize different objectives under the same terminology, obscuring what is...
- Assessing Sample Quality in Conditional Generation under Compositional Shift
Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors. In many applications, especially in scientific domains, such models are attractive to explore conditions for ...
- Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting
Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted. We show that the simplest possible conformal interval - a last-value point forecast wrapped in a finite-sample split-conformal residual quantile, with no parameters and no train...
- Dense Force Estimation with an Event-based Optical Tactile Sensor
Humans rely on spatially dense, geometry and force-aware tactile feedback at high temporal resolution for dexterous manipulation. While vision-based tactile sensors enable dense force estimation, they are limited by camera frame rates, motion blur, and data bandwidth. Event-based optical tactile sen...
- Thresholded Local Hyper-Flow Diffusion
Local Hyper-Flow Diffusion (HFD) gives an edge-size-independent Cheeger-type guarantee for seeded clustering in general submodular hypergraphs, but existing HFD solvers do not keep intermediate computation local at every iteration. We introduce Thresholded Local HFD (TL-HFD), a first-order method th...
- Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding
Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a de...
- A Universal Dense Football Event Representation Based on TabTransformer
Football event data constitute a rich spatiotemporal source for quantitative analysis of player actions in team sports. These datasets contain heterogeneous features, combining continuous location coordinates with categorical variables such as action type, action outcome, and body part. Such data ha...
- Machine-Learning Emulation of Satellite Greenhouse Gas Retrievals: Stability over Time
Retrieval algorithms are used to estimate atmospheric concentrations of greenhouse gases (GHGs), such as carbon dioxide (CO2) and methane (CH4), by solving inverse problems from high-spectral-resolution satellite radiance measurements. However, these algorithms are computationally expensive, which m...
- Goal Sets, Not Goal States: Queryable Robot Goals through Goal-Set Hindsight Relabeling
Hindsight relabeling usually turns achieved future states into exact goals, which can overconstrain offline robot learning when task success depends only on a subset of the state. We propose Goal-Set Hindsight Relabeling (GS-HER), a predicate-level generalization of HER in which achieved states cert...
- ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration
Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the demonstrated trajectory can quickly compound into failure, while collecting substantial online interaction data is costly. We propose ReGIL, a retr...
- TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation
Vision-Language-Action (VLA) models have become a powerful framework for robotic manipulation, and recent studies have introduced tactile or force feedback into VLAs to address contact-rich tasks. However, these models are typically deployed as offline policies. When contact conditions shift from th...
- Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
Autonomous Racing has seen remarkable progress through deep Reinforcement Learning (RL), primarily for four-wheeled vehicles. However, motorbikes introduce substantially greater complexity due to the need to manage balance and lean angle, in addition to more reactive steering and throttle control, a...
- From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still relies on manually curated dictionaries that are brittle and do not generalize across assets. We investigate whether large ...
- Autonomous FPV Flight with Translational Optical Flow and Uncertainty Mask
Autonomous FPV quadrotor flight in complex environments using a monocular RGB camera as the sole exteroceptive sensor remains a fundamental challenge. Recent research has shown that using optical flow as the input of a neural network can achieve end-to-end autonomous flight in cluttered scenes. Howe...
- Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics
Accurate dynamics models are essential for model-based robotic control, yet nominal Euler--Lagrange models often become inaccurate in the presence of payload variation, unmodeled coupling, friction, aerodynamic effects, and changing operating conditions. Most learning-based correction methods improv...
- $ω$-EVA: Envision, Verify, and Act with Latent Interactive World Models
Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictive supervision, representations, or external simulation, but rarely let a policy inspect the imagined consequence of its own proposal before acting. ...
- MosaicIMU: Composing Carrier Experts for Generalizable Neural Inertial Odometry
Robust inertial odometry is essential for various carriers when external sensing is unreliable. Learning-based methods reduce integration drift by capturing local motion priors, but these methods often remain tied to a particular carrier, limiting generalization across heterogeneous platforms. We pr...
- KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
Generating high-quality dexterous grasps remains challenging for learning-based methods, which often depend on carefully tuned contact losses or costly contact-based test-time refinement. We present KPGrasp, a flow-matching framework that learns dexterous grasp priors from large-scale data rather th...
- VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands
Humanoid robots hold immense potential for real-world assistance, yet agile interaction with objects in unstructured environments demands tightly coupled whole-body coordination. Despite recent advancements, current controllers face a critical deployment gap. They rely heavily on dense reference tra...
- VGP-Nav: Metric-Aware Visual Geometric Perception for Robot Navigation
Reliable robotic navigation necessitates the seamless integration of accurate global localization and dense, metric-consistent obstacle perception. A common strategy to achieve these capabilities involves integrating diverse sensing modalities: cameras offer rich visual features for localization, wh...
- Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection
Vision-language-action (VLA) policies can deviate from nominal trajectories during manipulation, even when tasks remain physically feasible. Recovering from these deviations is challenging, as they push the policy into unfamiliar state spaces where direct re-planning frequently destabilizes action s...
- MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation
World Action Models (WAMs) couple a video dynamics prior to the policy and have shown encouraging results on tabletop manipulation, but iterative denoising over high-dimensional video-action latents leaves them too slow for real-time humanoid loco-manipulation. The problem is compounded by the domin...
- Autonomous Obstacle Removal for Excavators through Policy Learning with Particle Simulation
Autonomous obstacle removal from the ground is an important earthwork task, but this is difficult to automate because an excavator must adapt its excavation trajectories over repeated cycles as soil-obstacle conditions change. Learning such state-dependent behavior requires a training environment th...
- Bridged SBI: Correcting Biased Low-Fidelity Posteriors for Cost-Efficient High-Fidelity Inference
Accurate calibration of particle-based simulators is crucial for robotic earthwork simulation, but analytical calibration is challenging due to this task's highly nonlinear particle dynamics and the black-box nature of conventional simulators. Although simulation-based inference (SBI) can estimate p...
- RAM: Reachability Across Morphologies
Many stages of the robotic lifecycle, from morphology synthesis to operation, rely fundamentally on the reachable workspace. However, current methods for approximating workspaces are slow, imprecise, or tied to a single morphology. We introduce Reachability Across Morphologies (RAM): a morphology-co...
- LAEI: Layered Autonomous Edge Intelligence Framework for Robust UAV Swarm Operations
Autonomous UAV swarms require scalable coordination mechanisms that maintain mission performance under limited communication, environmental uncertainty, and component failures. Centralized approaches provide global coordination but suffer from communication bottlenecks and single-node vulnerabilitie...
- ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models
Latent world models are increasingly used for control and goal-conditioned planning, yet assessing whether their learned representations are useful for planning usually requires slow, planner-coupled simulator evaluation with CEM or similar planners. Such evaluation is black-box and model-complexity...
- SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning
Vision-and-Language Navigation in continuous environments requires agents to understand the spatial structure of previously unseen environments in order to follow language instructions. Although foundation models have opened a promising path toward zero-shot navigation without task-specific policy t...