Search: “deployment”

arXiv:2609.37801v1 Announce Type: new Abstract: The ByteTrack algorithm is a widely used and computationally efficient multi-object tracking architecture. Its core innovation lies in the combination o

arXiv:2609.37800v1 Announce Type: cross Abstract: Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two chal

arXiv:2609.35883v1 Announce Type: cross Abstract: Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the se

arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s

Warehouse robotics software startup Destro AI Inc. has raised 8 million in new funding to bring its platform for coordinating mixed robot fleets to more enterprise warehouses, using the funds partly t

arXiv:2609.36520v1 Announce Type: cross Abstract: RGB-only end-to-end visual navigation policies remain vulnerable to collisions in real-world dynamic environments, motivating a dedicated safety layer

arXiv:2609.37551v1 Announce Type: cross Abstract: Emerging optical-network applications increasingly use received data for inference and control rather than exact source reproduction, creating an oppo

arXiv:2609.35793v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained with reinforcement learning from verifiable rewards (RLVR). An exact verifier can also support tes

arXiv:2609.38154v1 Announce Type: new Abstract: Video diffusion models are increasingly developed into specialized models for diverse downstream tasks, and this development often includes a distillati

arXiv:2609.37670v1 Announce Type: new Abstract: MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tun

Chris Metinko / Axios: Metaview, which uses AI agents to automate recruiting workflows, raised a 60M Series C led by Insight Partners, bringing its total funding to 110M — Metaview, an agentic recruit

arXiv:2609.36374v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research grou

arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such

arXiv:2609.36107v1 Announce Type: new Abstract: While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these

arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent S

arXiv:2609.37334v1 Announce Type: new Abstract: Vision-language-action (VLA) policies often fail when a robot's executed motion deviates from their commanded action. Such execution errors arise from t

arXiv:2609.35910v1 Announce Type: cross Abstract: Adaptive perception spends extra computation on inputs where perception is expected to improve. When perception feeds a downstream decision system, a

Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact

arXiv:2609.37602v1 Announce Type: cross Abstract: Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where envir

arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de

arXiv:2609.32752v1 Announce Type: cross Abstract: Reward shaping has a theorem: a potential-based term can be removed without changing the optimal policy. The same practice on the action channel, an o

NVIDIA TensorRT Model Connect is an open‑source library that delivers AI model reference implementations in C++ built on top of NVIDIA TensorRT, designed to make the inference stack accessible to deve

arXiv:2609.33993v1 Announce Type: new Abstract: Dynamic topology reconfiguration is central to the reliability and efficiency of large satellite constellations, yet many existing approaches rely on id

arXiv:2609.33980v1 Announce Type: new Abstract: Dynamic graph anomaly detection requires repeated decisions as graph structure and class prevalence drift, yet detector benchmarks usually score a fixed

arXiv:2609.33962v1 Announce Type: cross Abstract: Subject-independent motor-imagery (MI) EEG decoding can exhibit subject-level failures even when average performance appears acceptable: under subject

arXiv:2609.31915v1 Announce Type: new Abstract: Hybrid quantum methods have received limited study for resource-constrained facial biometrics. We present a hybrid quantum-classical facial recognition

arXiv:2609.34175v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are typically adapted using successful demonstrations, which provide direct action supervision but rarely cover fa

arXiv:2609.33887v1 Announce Type: cross Abstract: Block-diffusion language models are served at hand-picked operating points, such as acceptance thresholds, buffer depth, schedule, checkpoint and prec

arXiv:2609.34488v1 Announce Type: new Abstract: Looped architectures scale computation by reusing the same parameters across recurrent steps, and recent work shows that they substantially improve deep

Gentle reminder that Hugging Face was declined help from Anthropic & OpenAI models when they were being hacked by OpenAI models Self-hosted GLM 5.2 helped them protect themselves when the closed labs

Graph engineering is the design work: breaking a task into nodes, connecting them with edges, and deciding where code, models, or people control the next step. The Agent Development Kit (ADK)'s Workfl

arXiv:2609.33965v1 Announce Type: cross Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between input (pre

arXiv:2601.22988v2 Announce Type: replace Abstract: Real-world robotic manipulation requires visuomotor policies capable of robust 3D scene reasoning under varying camera viewpoints. While recent 3D-a

arXiv:2609.33306v1 Announce Type: new Abstract: Current Transformer-based tracking methods typically stack multiple Transformer blocks with separate parameters to model interactions between the target

NVIDIA released VSS Blueprint 3.3, a framework that stitches together vision‑language models (Cosmos), LLMs (Nemotron) and retrieval‑augmented generation to convert live or recorded video into natural

arXiv:2603.15033v4 Announce Type: replace Abstract: Machine unlearning for vision models is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove

arXiv:2609.34867v1 Announce Type: new Abstract: Vision language models have achieved strong performance across a wide range of multimodal applications, yet their substantial computational and memory c

arXiv:2609.34795v1 Announce Type: new Abstract: Underwater image enhancement is crucial for improving visual perception in marine applications. Existing underwater image enhancement studies mainly foc

arXiv:2609.33269v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly generate video and robot actions through iterative diffusion and perform strongly in robotic manipulation. However,

arXiv:2609.33687v1 Announce Type: new Abstract: Onboard satellite models often require frequent updates, but the weights adapted to earlier data distributions can quickly become outdated. However, upd

arXiv:2609.33872v1 Announce Type: cross Abstract: Robotic manipulation policies are advancing rapidly with increasing reliance on vision-language models for end-to-end decision making. However, reliab

arXiv:2609.33669v1 Announce Type: cross Abstract: Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide

arXiv:2609.35110v1 Announce Type: cross Abstract: Video diffusion models are rapidly scaling and exhibiting enhanced generation capabilities. Among these recent advancements, MiniMax-H3 stands out as

arXiv:2609.33125v1 Announce Type: new Abstract: Co-training offers a straightforward way to build a multi-task vision-language-action (VLA) policy, but can fall short of the performance achieved by tr

arXiv:2609.31197v1 Announce Type: new Abstract: Machine learning for scientific discovery is almost systematically data bound. Producing relevant high quality data, under budget constraints, is amongs

arXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked