AI is already implicated in violent deaths and nearly started world war three. Those bad things? They only happen to other people Sam Altman, the chief executive of OpenAI, has some words for you about his company and the future of artificial intelligence. “One of the differences between us and some of the stricter AI safety people is that we believe that the world should accept some bad things happening for the benefits of this technology and people having the agency [to use it],” Altman told Politico’s new technology podcast and newsletter Decoded. Moustafa Bayoumi is the author of the award-winning books How Does It Feel to Be a Problem?: Being Young and Arab in America and This Muslim American Life: Dispatches from the War on Terror. He is professor of English at Brooklyn College, Cit…

Have an idea for a lesson illustration, a project chart, or a comic for your next presentation? Nano Banana 2.1 lets you explore these formats with text prompts, making it easier to try different visual styles without switching between tools. In this article, we test Nano Banana 2.1 across four practical tasks: a clay illustration, […] The post Nano Banana 2.1 Review appeared first on Analytics Vidhya.

Whistleblower says recording and analysis of all probate calls is ‘oppressive and dystopian’ The Co-op has become the latest employer to place workers under AI surveillance with an automated listening technology that rates every phone call some of them make to customers. In a system described as “oppressive and dystopian” by a whistleblower, Co-op Legal Services is using AI models to record, analyse and award a percentage score for interactions between agents and customers seeking advice about probate, wills and estates. Continue reading...

Refugee gig workers for tech companies don’t know how much they’ll be paid – if AI hasn’t already taken their jobs In a portable building in Kakuma, a refugee camp near Kenya’s northern border with South Sudan, Grace used ChatGPT to research translations of Christian hymns in languages she doesn’t speak. She didn’t know the client, the purpose of her work or whether she would be paid, but as a refugee unable to legally work in Kenya, she needed any opportunity she could get. Grace, who requested anonymity due to a nondisclosure agreement, prompted ChatGPT to translate the hymn’s English text into the assigned east Asian language. She then used the translation to search for existing versions and find information about its translator, author and Christian denomination. She fed those details…

Architect Financial Technologies has launched Liquid Inference, an LLM router that runs a live auction for every request. Liquid Inference is an LLM inference marketplace from Architect where providers bid to serve each prompt. The buyer pays the lowest offer that meets its rules. For developers, it is quite simple message: swap a base URL, […] The post Architect Launches Liquid Inference, a Real-Time Auction for LLM Inference appeared first on MarkTechPost.

Discussion | Link

NVIDIA researchers introduced PivotOPD, an on-policy distillation method that trains multi-turn LLM agents to avoid early pivotal mistakes and recover from them, posting the best average against 13 baselines on 3 agent benchmarks. The post NVIDIA PivotOPD Teaches Multi-Turn AI Agents to Recover From Pivotal Mistakes appeared first on MarkTechPost.

yay small models

Sparse neural retrieval finally started getting more and more attention (SPARSEUP, MILCO, sparse encoders in Sentence Transformers…). Well, amazing, we like attention! Our miniCOIL v1 sparse neural retriever article ended with a promise: to keep working on this sparse neural retriever in-depth, improving the model’s quality, and in-width, “extending it to other dense encoders and to languages beyond English.” Here is the next “in-width” step of the miniCOIL saga: to try and cross the language barrier, that is, make the model suitable for multilingual retrieval. It’s a fun challenge, as sparse retrievers are hard to adapt to this scenario: exact matching in cross-lingual text search usually means translation.

When Redis changed its licensing in 2024, replacing its permissive BSD license with proprietary, source-available alternatives, it prompted a major The post Redis by proxy: Percona targets the last major hurdle to Valkey adoption appeared first on The New Stack.

Discussion | Link

Perplexity's pplx-embed-v2-late comes in 2 sizes: a 0.6B model built to run on edge devices, and a 9B model for building high-quality indexes. Its best score is 92.4% on MADQA, and its weakest is 61.2% on ViDoRe v3 Markdown. Both are MIT-licensed and ready to self-host. The post Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA appeared first on MarkTechPost.

Discussion | Link

Discussion | Link

arXiv:2610.08970v1 Announce Type: new Abstract: Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking. We present HULK, a whole-body control framework for forceful loco-manipulation. Using model predictive control (MPC) to guide reinforcement learning with predictions of the loaded dynamics, we train two teachers: one tracks arm motions under wrist forces, and the other locomotes while holding large objects against the body. A capture-point control barrier function augments the wrist-force teacher during training to improve balance under load. We distill both teachers into a single policy. Eval…

arXiv:2610.08933v1 Announce Type: new Abstract: Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew observations or at locations that are unsafe, costly, or unavailable for crew inspection. We present an evidence-driven architecture for human-agent-robot teaming in Earth-independent anomaly triage. Agentic AI is treated as a stateful coordinator over bounded, inspectable services rather than as a fully autonomous vehicle controller. A triage state manager maintains hypotheses, evidence provenance, uncertainty, operational context, and tool status; a crew-facing embodied agent elicits observations and explains assessment changes; and a mobile robot acquires targeted…

arXiv:2610.08870v1 Announce Type: new Abstract: Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device rat…

arXiv:2610.08863v1 Announce Type: new Abstract: A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable trajectories by conditioning on task goal constraints. However, trajectory-based methods rely on costly supervision, scale poorly with sequence length, and often generalize poorly to unseen constraints such as novel start-goal pairs. We propose an alternative to learn the underlying state-space manifold and use the geometry of the manifold for trajectory planning. This approach requires only state observations and enables generalization to unseen constraints by con- structing trajectories on the learned manifold of the state space. Experiments on Maze2D and robotic motion…

arXiv:2610.08862v1 Announce Type: new Abstract: Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution. We formulate continual instruction reconciliation and propose CIRRA (Continual Instruction Reconciliation for Robot Agents), a dual-level framework combining LLM-based semantic reasoning with rule-constrained structural integration. CIRRA first grounds incoming instructions to unique executable skills and resolves underspecified actions and execution locations. It then preserves the ongoing subtask sequence as an execution backbone and generates integration candidates by inserting incoming subtasks…

arXiv:2610.08852v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms. A critical instance is autonomous droplet transport on an open surface, where contact-angle hysteresis, capillary pinning, and surface heterogeneity produce partially observable dynamics that pose significant challenges for classical model-based controllers. We introduce the first robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning. A two-axis tilting board coated with a thin silicone oil film drives the droplet, while…

arXiv:2610.08812v1 Announce Type: new Abstract: We present Go2-DrivoR, a goal-conditioned adaptation of the end-to-end autonomous driving trajectory planning framework DrivoR for urban navigation with quadrupedal robots. By conditioning trajectory generation on a local-frame subgoal through a goal token and adapting the vehicle-centric scoring formulation, the method extends DrivoR to short-horizon goal-conditioned local planning without redesigning its core decoders. Specifically, we redefine drivable-area compliance for sidewalk-oriented navigation and reformulate the original ego progress term as goal-conditioned ego progress. Trained exclusively on TartanGround simulation data, Go2-DrivoR improves waypoint-conditioned planning performance on unseen simulation environments and transfer…

arXiv:2610.08807v1 Announce Type: new Abstract: Precision pesticide spraying is essential for optimizing application efficiency and ensuring uniform chemical distribution. Spraying performance is influenced by multiple factors, including environmental conditions such as temperature and wind speed, pesticide type, and the robot's capability to accurately perceive crops and target spray locations. Existing approaches predominantly emphasize crop detection and rely on predefined spraying parameters, whereas human operators dynamically adjust their spraying strategies by considering environmental conditions, region-specific crop characteristics, and the type of pesticide being applied. In this study, we propose a context-aware adaptive spraying framework based on Vision-Language Models (VLMs)…

arXiv:2610.08802v1 Announce Type: new Abstract: Manipulating fragile objects remains challenging as robots must understand the state of what they grasp, such as slip or fracture, to respond appropriately, especially when material properties are unknown. In this paper, we present SAFE: a low-cost, general-purpose sensing approach that detects both slip and fracture in real time using two passive polyvinylidene fluoride (PVDF) acoustic sensors and motor proprioception, without relying on vision or prior material knowledge. The sensors are mounted on a compliant Fin Ray gripper, and a unified HistGradientBoosting classifier reports the state (normal, slip, or fracture) from a 79-dimensional feature vector. Under leave-one-grasp-out cross-validation, SAFE achieves an Alert-F1 of 0.884 with ne…

arXiv:2610.08800v1 Announce Type: new Abstract: Models based on graphs have emerged in robotics as a powerful foundation for internal world representations, where factor and scene graphs are among the most prominent model types found in the related literature and in successful robotic solutions. Initially, many of these models were assuming static environments as a simplification. Herein, factor graphs mainly provide uncertainty-aware geometric estimations while scene graphs enable a structured semantic abstraction. However, real-world robotic environments are often dynamic, posing severe challenges for purely static world representations. Therefore, this review presents a comprehensive view on how dynamic aspects of real-world environments can be addressed in such graph-based world model…

arXiv:2610.08983v1 Announce Type: new Abstract: Generative inpainting of brain MRI volumes is essential for synthesizing healthy tissue in pathological regions, improving the accuracy and reliability of automated downstream brain analysis applications such as image registration, brain extraction, and segmentation. However, standard 3D approaches are computationally prohibitive, while efficient 2D slice-wise methods suffer from severe inter-slice discontinuities. Furthermore, traditional models rely on conditional training, requiring task-specific learning of masked inputs. We propose a zero-shot brain MRI inpainting framework utilizing 2.5D unconditional flow priors to capture spatial context along the superior-inferior axis without the overhead of full 3D convolutions. During training, o…

arXiv:2610.08978v1 Announce Type: new Abstract: Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evidence and remain renderable as observations arrive. Latent spatial tokens offer a promising representation for this purpose, but constructing them from an image collection leaves open how to maintain them online, where each observation may both revisit known regions and reveal new content. We introduce S2Tok, a feed-forward framework that maintains a size-adaptive, persistent scene state from uncalibrated image streams. Its central idea is to distinguish updates to the existing representation from selective expansion. A spatially informed transformer integrates each incoming observation with the…

arXiv:2610.08954v1 Announce Type: new Abstract: Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames. However, frame selection for long videos remains challenging, as it requires retrieving relevant frames distributed across segments from a large candidate pool given complex queries. This paper investigates dominant approaches to long-video frame selection from a task-decomposition perspective, identifying two key challenges: the Query Comprehension Gap in similarity-based methods and the Interpretation--Selection Gap in judgment-based methods. To address them, we propose RACER, a training-free reflective agentic framework that decomposes long-video frame selection into query interpretation driven by a lightweight Vid-LLM and evide…

arXiv:2610.08944v1 Announce Type: new Abstract: Scanner variation changes how pathology foundation models represent the same tissue. We introduce SlideRuler, which uses regions within a slide as internal controls to estimate and correct acquisition-induced shifts in other regions. A transfer map learned from paired rescans enables calibration from a single scan at inference while keeping the foundation model fixed. Across two encoders and five SCORPION scanners, learned transfer reduces mean target-to-source embedding distance by 16.3-38.5% relative to raw embeddings. Comparisons with unrelated same-scanner controls reveal a positive same-slide contribution across all four evaluation settings, including scanner holdout. A source-anchored variant reduces source-feature displacement by 47.7…

arXiv:2610.08941v1 Announce Type: new Abstract: Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene exploration, virtual reality experiences, and embodied agent training. Existing panoramic generators follow predefined trajectories, and interactive world models act through low-level actions in perspective views. We propose SPW-Nav, a streaming panoramic world model that understands movement instructions and streams one minute of 2K 360-degree video in real time from a single panorama. SPW-Nav interprets each instruction in the previously generated panorama as camera motion. Spherical rotation decoupling applies rotation exactly on the sphere, pose-aligned conditioning keeps translation inputs bounded over long streams, and a mu…

arXiv:2610.08936v1 Announce Type: new Abstract: Robustness of image classification has several benchmarks, but their video counterparts are absent. In video classification temporal dimension introduces additional degrees of freedom for adversarial attacks, defenses, and preprocessing. Temporal sampling, perturbation budgets, and metric aggregation also interact in ways with no direct analogue in the image setting. Therefore, robustness for video classifiers is studied across scattered, incompatible implementations, making reported numbers hard to reproduce and analyze. We introduce VCR-Bench, a modular open-source benchmark framework that standardizes video loading, wrappers for classifiers, adversarial attacks and defenses, perceptual metrics, configuration presets, and result logging. V…