Engineering Sciences

148 items

Google Research Sep 19, 2026
The work introduces and open-sources MilleMiglia, a C++ instance generator serialized with Protocol Buffers that synthesizes middle-mile logistics networks from statistical distributions over spatial placement, demand, and vehicle rotations, embedding hard constraints such as fixed schedules, distribution-center throughput limits, and cross-vehicle synchronization into a single data format, thereby offering reproducible benchmarks from small academic toy problems to continent-wide industrial scale while preserving corporate privacy.
The work introduces and open-sources MilleMiglia, a C++ instance generator serialized with Protocol Buffers that synthesizes middle-mile logistics networks from statistical distributions over spatial placement, demand, and vehicle rotations, embedding hard constraints such as fixed schedules, distribution-center throughput limits, and cross-vehicle synchronization into a single data format, thereby offering reproducible benchmarks from small academic toy problems to continent-wide industrial scale while preserving corporate privacy.
MilleMiglia: A realistic instance generator for middle-mile logistics
The work introduces and open-sources MilleMiglia, a C++ instance generator serialized with Protocol Buffers that synthesizes middle-mile logistics networks from statistical distributions over spatial placement, demand, and vehicle rotations, embedding hard constraints such as fixed schedules, distribution-center throughput limits, and cross-vehicle synchronization into a single data format, thereby offering reproducible benchmarks from small academic toy problems to continent-wide industrial scale while preserving corporate privacy.
The work introduces and open-sources MilleMiglia, a C++ instance generator serialized with Protocol Buffers that synthesizes middle-mile logistics networks from statistical distributions over spatial placement, demand, and vehicle rotations, embedding hard constraints such as fixed schedules, distribution-center throughput limits, and cross-vehicle synchronization into a single data format, thereby offering reproducible benchmarks from small academic toy problems to continent-wide industrial scale while preserving corporate privacy.
bioRxiv Sep 18, 2026
This work builds BoneGraph, a bone-science-specific system delivered as a five-tab web application over a shared substrate of 7,449 documents, 248,629 SPECTER2 passage vectors, and a bone knowledge graph of 1,597 concepts and 1,699 causal relations, reporting MRR 0.928 on a 30-question seven-domain retrieval benchmark, 92.6% accuracy for the bone-region classifier on held-out MURA, and an increase in answer accuracy from 42% to 78% when the correct passage is supplied, with all inference performed locally on a single NVIDIA Jetson AGX Orin and no third-party API calls.
This work builds BoneGraph, a bone-science-specific system delivered as a five-tab web application over a shared substrate of 7,449 documents, 248,629 SPECTER2 passage vectors, and a bone knowledge graph of 1,597 concepts and 1,699 causal relations, reporting MRR 0.928 on a 30-question seven-domain retrieval benchmark, 92.6% accuracy for the bone-region classifier on held-out MURA, and an increase in answer accuracy from 42% to 78% when the correct passage is supplied, with all inference performed locally on a single NVIDIA Jetson AGX Orin and no third-party API calls.
BoneGraph: A Domain-Specialised, Self-Correcting Reasoning System for Bone Science
This work builds BoneGraph, a bone-science-specific system delivered as a five-tab web application over a shared substrate of 7,449 documents, 248,629 SPECTER2 passage vectors, and a bone knowledge graph of 1,597 concepts and 1,699 causal relations, reporting MRR 0.928 on a 30-question seven-domain retrieval benchmark, 92.6% accuracy for the bone-region classifier on held-out MURA, and an increase in answer accuracy from 42% to 78% when the correct passage is supplied, with all inference performed locally on a single NVIDIA Jetson AGX Orin and no third-party API calls.
This work builds BoneGraph, a bone-science-specific system delivered as a five-tab web application over a shared substrate of 7,449 documents, 248,629 SPECTER2 passage vectors, and a bone knowledge graph of 1,597 concepts and 1,699 causal relations, reporting MRR 0.928 on a 30-question seven-domain retrieval benchmark, 92.6% accuracy for the bone-region classifier on held-out MURA, and an increase in answer accuracy from 42% to 78% when the correct passage is supplied, with all inference performed locally on a single NVIDIA Jetson AGX Orin and no third-party API calls.
Pharmaceutical development and technology Sep 18, 2026
This review systematically surveys recent advances in natural biodegradable polymer-based microneedle drug delivery systems in terms of material selection, fabrication strategies, and controlled release mechanisms, and introduces a rational design framework that systematically integrates therapeutic objectives, polymer properties, mechanical performance, and release kinetics, while discussing translational challenges such as mechanical limitations, manufacturing scalability, stability concerns, and regulatory considerations, as well as emerging trends including stimuli-responsive systems, nanocarrier integration, personalized drug delivery, and data-driven strategies such as artificial intelligence and machine learning, arguing for a shift from empirical formulation toward a predictive, en
This review systematically surveys recent advances in natural biodegradable polymer-based microneedle drug delivery systems in terms of material selection, fabrication strategies, and controlled release mechanisms, and introduces a rational design framework that systematically integrates therapeutic objectives, polymer properties, mechanical performance, and release kinetics, while discussing translational challenges such as mechanical limitations, manufacturing scalability, stability concerns, and regulatory considerations, as well as emerging trends including stimuli-responsive systems, nanocarrier integration, personalized drug delivery, and data-driven strategies such as artificial intelligence and machine learning, arguing for a shift from empirical formulation toward a predictive, en
Natural Biodegradable Polymer-Based Microneedles for Controlled Drug Delivery: A Rational Design Framework and Translational Perspectives
This review systematically surveys recent advances in natural biodegradable polymer-based microneedle drug delivery systems in terms of material selection, fabrication strategies, and controlled release mechanisms, and introduces a rational design framework that systematically integrates therapeutic objectives, polymer properties, mechanical performance, and release kinetics, while discussing translational challenges such as mechanical limitations, manufacturing scalability, stability concerns, and regulatory considerations, as well as emerging trends including stimuli-responsive systems, nanocarrier integration, personalized drug delivery, and data-driven strategies such as artificial intelligence and machine learning, arguing for a shift from empirical formulation toward a predictive, en
This review systematically surveys recent advances in natural biodegradable polymer-based microneedle drug delivery systems in terms of material selection, fabrication strategies, and controlled release mechanisms, and introduces a rational design framework that systematically integrates therapeutic objectives, polymer properties, mechanical performance, and release kinetics, while discussing translational challenges such as mechanical limitations, manufacturing scalability, stability concerns, and regulatory considerations, as well as emerging trends including stimuli-responsive systems, nanocarrier integration, personalized drug delivery, and data-driven strategies such as artificial intelligence and machine learning, arguing for a shift from empirical formulation toward a predictive, en
Nanoscale Sep 17, 2026
This review systematically outlines host-guest composites using metal-organic frameworks (MOFs) as hosts and metal halide perovskites as guests, summarizing three synthetic strategies (ship-in-a-bottle, bottle-around-ship, and one-pot synthesis), noting that nanoconfinement, interfacial passivation, and electronic coupling of MOFs inhibit ion migration, defects, and degradation to improve photoluminescence quantum yield and stability, that emission wavelength and exciton dynamics can be tuned via MOF pore size, ligand functionalization, and nucleation kinetics, and outlining applications in photovoltaics, sensing, information encryption, anti-counterfeiting, and light-emitting devices along with integrating artificial intelligence with theoretical simulation for design optimization.
This review systematically outlines host-guest composites using metal-organic frameworks (MOFs) as hosts and metal halide perovskites as guests, summarizing three synthetic strategies (ship-in-a-bottle, bottle-around-ship, and one-pot synthesis), noting that nanoconfinement, interfacial passivation, and electronic coupling of MOFs inhibit ion migration, defects, and degradation to improve photoluminescence quantum yield and stability, that emission wavelength and exciton dynamics can be tuned via MOF pore size, ligand functionalization, and nucleation kinetics, and outlining applications in photovoltaics, sensing, information encryption, anti-counterfeiting, and light-emitting devices along with integrating artificial intelligence with theoretical simulation for design optimization.
Confinement-Guided Performance Enhancement of Perovskites within Metal-Organic Frameworks: A Review
This review systematically outlines host-guest composites using metal-organic frameworks (MOFs) as hosts and metal halide perovskites as guests, summarizing three synthetic strategies (ship-in-a-bottle, bottle-around-ship, and one-pot synthesis), noting that nanoconfinement, interfacial passivation, and electronic coupling of MOFs inhibit ion migration, defects, and degradation to improve photoluminescence quantum yield and stability, that emission wavelength and exciton dynamics can be tuned via MOF pore size, ligand functionalization, and nucleation kinetics, and outlining applications in photovoltaics, sensing, information encryption, anti-counterfeiting, and light-emitting devices along with integrating artificial intelligence with theoretical simulation for design optimization.
This review systematically outlines host-guest composites using metal-organic frameworks (MOFs) as hosts and metal halide perovskites as guests, summarizing three synthetic strategies (ship-in-a-bottle, bottle-around-ship, and one-pot synthesis), noting that nanoconfinement, interfacial passivation, and electronic coupling of MOFs inhibit ion migration, defects, and degradation to improve photoluminescence quantum yield and stability, that emission wavelength and exciton dynamics can be tuned via MOF pore size, ligand functionalization, and nucleation kinetics, and outlining applications in photovoltaics, sensing, information encryption, anti-counterfeiting, and light-emitting devices along with integrating artificial intelligence with theoretical simulation for design optimization.
Nanoscale Sep 17, 2026
This review surveys the design principles and functional architectures of stimuli-responsive nanoprobes, noting that they can achieve context-responsive activation and signal modulation in response to endogenous tumor cues (acidic pH around 6.5-6.8, glutathione at 2-10 mM, enzymatic overexpression, hypoxia below 2% O2, and redox gradients) and exogenous triggers (near-infrared light at 700-1000 nm, magnetic fields, and ultrasound), yielding 5-20-fold signal amplification, and that they can be integrated with multimodal imaging and artificial intelligence for real-time data interpretation and adaptive diagnostics.
This review surveys the design principles and functional architectures of stimuli-responsive nanoprobes, noting that they can achieve context-responsive activation and signal modulation in response to endogenous tumor cues (acidic pH around 6.5-6.8, glutathione at 2-10 mM, enzymatic overexpression, hypoxia below 2% O2, and redox gradients) and exogenous triggers (near-infrared light at 700-1000 nm, magnetic fields, and ultrasound), yielding 5-20-fold signal amplification, and that they can be integrated with multimodal imaging and artificial intelligence for real-time data interpretation and adaptive diagnostics.
Programmable nanoprobes for molecular imaging of cancer: toward adaptive and context-responsive diagnostics
This review surveys the design principles and functional architectures of stimuli-responsive nanoprobes, noting that they can achieve context-responsive activation and signal modulation in response to endogenous tumor cues (acidic pH around 6.5-6.8, glutathione at 2-10 mM, enzymatic overexpression, hypoxia below 2% O2, and redox gradients) and exogenous triggers (near-infrared light at 700-1000 nm, magnetic fields, and ultrasound), yielding 5-20-fold signal amplification, and that they can be integrated with multimodal imaging and artificial intelligence for real-time data interpretation and adaptive diagnostics.
This review surveys the design principles and functional architectures of stimuli-responsive nanoprobes, noting that they can achieve context-responsive activation and signal modulation in response to endogenous tumor cues (acidic pH around 6.5-6.8, glutathione at 2-10 mM, enzymatic overexpression, hypoxia below 2% O2, and redox gradients) and exogenous triggers (near-infrared light at 700-1000 nm, magnetic fields, and ultrasound), yielding 5-20-fold signal amplification, and that they can be integrated with multimodal imaging and artificial intelligence for real-time data interpretation and adaptive diagnostics.
arXiv Sep 17, 2026
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
In-Context Robot Learning with General-Purpose VLM Agents: The GPT-Policy Framework
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
This work introduces GPT-Policy, a framework that connects an off-the-shelf general-purpose vision-language model (VLM) to robot tools through a shared context-to-action closed loop, and evaluates its in-context learning on real robots across five context families (human videos, robot videos with actions, goal images, self-interaction history, and online human-robot interaction), finding that task-relevant context can improve success while reducing decisions and execution time, yet better task understanding does not ensure precise contact, reliable outcome verification, or physical safety.
arXiv Sep 17, 2026
This work presents EarStreAM, a closed-loop earable system built on OpenEarable 2.0 and a companion smartphone app that continuously monitors in-ear PPG to derive heart rate and heart rate variability as stress proxies, triggers an LLM-generated personalized guided meditation that adapts in real time to the user's physiological state, and terminates it once stress returns to baseline, demonstrated in two modes: a biosignal-adaptive mode with optional stress induction and a meditation-only mode.
This work presents EarStreAM, a closed-loop earable system built on OpenEarable 2.0 and a companion smartphone app that continuously monitors in-ear PPG to derive heart rate and heart rate variability as stress proxies, triggers an LLM-generated personalized guided meditation that adapts in real time to the user's physiological state, and terminates it once stress returns to baseline, demonstrated in two modes: a biosignal-adaptive mode with optional stress induction and a meditation-only mode.
EarStreAM: A Closed-Loop Earable System for Personalized Stress-Adaptive Meditation
This work presents EarStreAM, a closed-loop earable system built on OpenEarable 2.0 and a companion smartphone app that continuously monitors in-ear PPG to derive heart rate and heart rate variability as stress proxies, triggers an LLM-generated personalized guided meditation that adapts in real time to the user's physiological state, and terminates it once stress returns to baseline, demonstrated in two modes: a biosignal-adaptive mode with optional stress induction and a meditation-only mode.
This work presents EarStreAM, a closed-loop earable system built on OpenEarable 2.0 and a companion smartphone app that continuously monitors in-ear PPG to derive heart rate and heart rate variability as stress proxies, triggers an LLM-generated personalized guided meditation that adapts in real time to the user's physiological state, and terminates it once stress returns to baseline, demonstrated in two modes: a biosignal-adaptive mode with optional stress induction and a meditation-only mode.
arXiv Sep 17, 2026
This work presents a unified reinforcement-learning whole-body controller that takes a single 6-DoF end-effector target as the sole task-level command and directly outputs coordinated actions for a bipedal base and a six-joint arm across 14 joints, reaching 88.30% task success in simulation (2.85 cm mean position error, 5.38 cm P95), and on a real bipedal platform reusing the same controller across VR teleoperation, a learned diffusion policy, and scripted trajectories while extending vertical reach from roughly 38-163 cm for a floating-base plus inverse-kinematics baseline to roughly 3-191 cm.
This work presents a unified reinforcement-learning whole-body controller that takes a single 6-DoF end-effector target as the sole task-level command and directly outputs coordinated actions for a bipedal base and a six-joint arm across 14 joints, reaching 88.30% task success in simulation (2.85 cm mean position error, 5.38 cm P95), and on a real bipedal platform reusing the same controller across VR teleoperation, a learned diffusion policy, and scripted trajectories while extending vertical reach from roughly 38-163 cm for a floating-base plus inverse-kinematics baseline to roughly 3-191 cm.
Learning Holistic Whole-Body Loco-Manipulation with a Bipedal Mobile Manipulator
This work presents a unified reinforcement-learning whole-body controller that takes a single 6-DoF end-effector target as the sole task-level command and directly outputs coordinated actions for a bipedal base and a six-joint arm across 14 joints, reaching 88.30% task success in simulation (2.85 cm mean position error, 5.38 cm P95), and on a real bipedal platform reusing the same controller across VR teleoperation, a learned diffusion policy, and scripted trajectories while extending vertical reach from roughly 38-163 cm for a floating-base plus inverse-kinematics baseline to roughly 3-191 cm.
This work presents a unified reinforcement-learning whole-body controller that takes a single 6-DoF end-effector target as the sole task-level command and directly outputs coordinated actions for a bipedal base and a six-joint arm across 14 joints, reaching 88.30% task success in simulation (2.85 cm mean position error, 5.38 cm P95), and on a real bipedal platform reusing the same controller across VR teleoperation, a learned diffusion policy, and scripted trajectories while extending vertical reach from roughly 38-163 cm for a floating-base plus inverse-kinematics baseline to roughly 3-191 cm.
arXiv Sep 17, 2026
PhysVGGT formulates physical property estimation as dense per-pixel prediction: a visual geometry transformer extracts geometry-aware tokens, a dense branch predicts per-pixel maps of friction coefficient, Shore hardness, Young's modulus and density, and a global branch predicts object-level mass, all from a single RGB image in one forward pass, achieving state-of-the-art mass estimation on ABO-500 and state-of-the-art friction and hardness on the out-of-distribution NeRF2Physics benchmark with 0.13 s inference latency, 27 times faster than the previous state of the art.
PhysVGGT formulates physical property estimation as dense per-pixel prediction: a visual geometry transformer extracts geometry-aware tokens, a dense branch predicts per-pixel maps of friction coefficient, Shore hardness, Young's modulus and density, and a global branch predicts object-level mass, all from a single RGB image in one forward pass, achieving state-of-the-art mass estimation on ABO-500 and state-of-the-art friction and hardness on the out-of-distribution NeRF2Physics benchmark with 0.13 s inference latency, 27 times faster than the previous state of the art.
PhysVGGT: Feed-Forward Dense Physical Property Estimation from a Single Image
PhysVGGT formulates physical property estimation as dense per-pixel prediction: a visual geometry transformer extracts geometry-aware tokens, a dense branch predicts per-pixel maps of friction coefficient, Shore hardness, Young's modulus and density, and a global branch predicts object-level mass, all from a single RGB image in one forward pass, achieving state-of-the-art mass estimation on ABO-500 and state-of-the-art friction and hardness on the out-of-distribution NeRF2Physics benchmark with 0.13 s inference latency, 27 times faster than the previous state of the art.
PhysVGGT formulates physical property estimation as dense per-pixel prediction: a visual geometry transformer extracts geometry-aware tokens, a dense branch predicts per-pixel maps of friction coefficient, Shore hardness, Young's modulus and density, and a global branch predicts object-level mass, all from a single RGB image in one forward pass, achieving state-of-the-art mass estimation on ABO-500 and state-of-the-art friction and hardness on the out-of-distribution NeRF2Physics benchmark with 0.13 s inference latency, 27 times faster than the previous state of the art.
NVIDIA Technical Blog Sep 17, 2026
The work built a multi-agent AI skill that translates GPU tile kernels written in cuTile Python and Triton-TileIR into cuTile Rust, and used it to port all 24 public TileGym operators (roughly 40 kernels, spanning element-wise operations through flash-attention decode, MLA, and MoE), measuring a geometric mean of 0.995 by CUPTI device time on NVIDIA DGX B200, i.e. 99.5% of cuTile Python performance on average, with every stage gated by machine-checkable verdicts and Tile IR diffs.
The work built a multi-agent AI skill that translates GPU tile kernels written in cuTile Python and Triton-TileIR into cuTile Rust, and used it to port all 24 public TileGym operators (roughly 40 kernels, spanning element-wise operations through flash-attention decode, MLA, and MoE), measuring a geometric mean of 0.995 by CUPTI device time on NVIDIA DGX B200, i.e. 99.5% of cuTile Python performance on average, with every stage gated by machine-checkable verdicts and Tile IR diffs.
A multi-agent skill ported all 24 TileGym operators from cuTile Python/Triton-TileIR to cuTile Rust, averaging 99.5% of reference performance
The work built a multi-agent AI skill that translates GPU tile kernels written in cuTile Python and Triton-TileIR into cuTile Rust, and used it to port all 24 public TileGym operators (roughly 40 kernels, spanning element-wise operations through flash-attention decode, MLA, and MoE), measuring a geometric mean of 0.995 by CUPTI device time on NVIDIA DGX B200, i.e. 99.5% of cuTile Python performance on average, with every stage gated by machine-checkable verdicts and Tile IR diffs.
The work built a multi-agent AI skill that translates GPU tile kernels written in cuTile Python and Triton-TileIR into cuTile Rust, and used it to port all 24 public TileGym operators (roughly 40 kernels, spanning element-wise operations through flash-attention decode, MLA, and MoE), measuring a geometric mean of 0.995 by CUPTI device time on NVIDIA DGX B200, i.e. 99.5% of cuTile Python performance on average, with every stage gated by machine-checkable verdicts and Tile IR diffs.

Page 13 · showing 10