Engineering Sciences

140 items

发表出处待核验 Sep 29, 2026
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
Punching Bag local testbed shows six IPv6 target generation algorithms differ on scan budgets, aliased-prefix recognition, and response-rate adaptation
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
The authors present and release the IPv6 Punching Bag, a single-machine, low-memory local environment that answers ICMPv6 echo requests with per-prefix configurable response rates and address types, and use it to evaluate six dynamic target generation algorithms (6Hit, 6Sense, 6Scan, 6Tree, AddrMiner-S, and DET), finding that they only partially adhere to scanning budgets while generally respecting rate limits, that all but 6Sense fail to recognize aliased prefixes, and that 6Scan does not adapt to differing response behavior within prefixes.
Microsystems & Nanoengineering Sep 29, 2026
Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.
Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.
A flexible wireless stethoscope built on a 25-element AlN PMUT array captures cardiopulmonary sounds from 10 Hz to 10 kHz and classifies five respiratory states with 98.7% accuracy
Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.
Researchers developed a flexible wireless wearable stethoscope based on a 25-element circular aluminum nitride (AlN) piezoelectric micromachined ultrasonic transducer (PMUT) array that achieves a packaged sensitivity of −167.5 dB, an operating bandwidth of 10 Hz–10 kHz, and a frequency-response flatness of ±0.5 dB; across multiple participants it acquired heart sounds at five standard auscultation sites with temporal correspondence to reference ECG and chest-motion signals, tracked heart rate continuously during dynamic activities such as walking and stair climbing, and, coupled with a residual neural network, classified five respiratory states (awake, asleep, apnea, rhonchi, and wheeze) with 98.7% accuracy.
arXiv Sep 29, 2026
Rolling-WAM introduces a rolling world action model that keeps a sliding window of video-action chunks at staggered noise levels, fully denoising only the imminent action chunk each replanning cycle while partially refining farther-future chunks, thereby distributing joint denoising computation across control cycles; it achieves competitive manipulation success on LIBERO, RoboTwin 2.0, and real-world Unitree G1 humanoid tasks while delivering a 4.5x steady-state replanning speedup over standard joint WAMs.
Rolling-WAM introduces a rolling world action model that keeps a sliding window of video-action chunks at staggered noise levels, fully denoising only the imminent action chunk each replanning cycle while partially refining farther-future chunks, thereby distributing joint denoising computation across control cycles; it achieves competitive manipulation success on LIBERO, RoboTwin 2.0, and real-world Unitree G1 humanoid tasks while delivering a 4.5x steady-state replanning speedup over standard joint WAMs.
Rolling-WAM spreads joint denoising across replanning cycles, reaching 98.1% on LIBERO and 93.3% on RoboTwin 2.0 with a 4.5x steady-state replanning speedup over standard joint WAMs
Rolling-WAM introduces a rolling world action model that keeps a sliding window of video-action chunks at staggered noise levels, fully denoising only the imminent action chunk each replanning cycle while partially refining farther-future chunks, thereby distributing joint denoising computation across control cycles; it achieves competitive manipulation success on LIBERO, RoboTwin 2.0, and real-world Unitree G1 humanoid tasks while delivering a 4.5x steady-state replanning speedup over standard joint WAMs.
Rolling-WAM introduces a rolling world action model that keeps a sliding window of video-action chunks at staggered noise levels, fully denoising only the imminent action chunk each replanning cycle while partially refining farther-future chunks, thereby distributing joint denoising computation across control cycles; it achieves competitive manipulation success on LIBERO, RoboTwin 2.0, and real-world Unitree G1 humanoid tasks while delivering a 4.5x steady-state replanning speedup over standard joint WAMs.
arXiv Sep 29, 2026
Drawing on 1,729,171 pull requests across 103 software ecosystems, the authors built WideSWE, 120 real tasks (60 bug fixes, 60 features) that require coordinated changes across multiple repositories, and evaluated seven coding-agent configurations: full task success ranges from 10.83% to 42.50%, with Codex CLI paired with GPT-5.6-sol highest, while joint and per-repository independent execution each help in different ways.
Drawing on 1,729,171 pull requests across 103 software ecosystems, the authors built WideSWE, 120 real tasks (60 bug fixes, 60 features) that require coordinated changes across multiple repositories, and evaluated seven coding-agent configurations: full task success ranges from 10.83% to 42.50%, with Codex CLI paired with GPT-5.6-sol highest, while joint and per-repository independent execution each help in different ways.
WideSWE tests coding agents on 120 cross-repository tasks: best configuration solves only 42.50%, and joint execution beats independent runs on requests
Drawing on 1,729,171 pull requests across 103 software ecosystems, the authors built WideSWE, 120 real tasks (60 bug fixes, 60 features) that require coordinated changes across multiple repositories, and evaluated seven coding-agent configurations: full task success ranges from 10.83% to 42.50%, with Codex CLI paired with GPT-5.6-sol highest, while joint and per-repository independent execution each help in different ways.
Drawing on 1,729,171 pull requests across 103 software ecosystems, the authors built WideSWE, 120 real tasks (60 bug fixes, 60 features) that require coordinated changes across multiple repositories, and evaluated seven coding-agent configurations: full task success ranges from 10.83% to 42.50%, with Codex CLI paired with GPT-5.6-sol highest, while joint and per-repository independent execution each help in different ways.
arXiv Sep 29, 2026
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
DroneWAM cuts drone visual-navigation inference to 483 ms with JEPA latent prediction and adaptive rollout, lifting closed-loop progress from 0.510 to 0.774
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
arXiv Sep 29, 2026
The work proposes Physical Coding, representing physical world state (Code as World) and execution procedure (Code as Policy) as executable programs, and builds the physical coding agent HexaAnything, which treats VLA/WAM policies as callable action tools while a Harness owns state bookkeeping, verification, and recovery; on RoboCasa365 with XR-1 as the action model it raises Composite-Unseen success from 34.3% to 38.3% and overall success from 56.6% to 61.1%, a HexaModel v0.1 fine-tuned on Harness-collected traces beats its base model on every split in the same Harness, PhyBench simulated physics experiments are completed with mean relative errors below 5%, and on a dual-arm AgileX robot five of seven tabletop tasks succeed in all three trials.
The work proposes Physical Coding, representing physical world state (Code as World) and execution procedure (Code as Policy) as executable programs, and builds the physical coding agent HexaAnything, which treats VLA/WAM policies as callable action tools while a Harness owns state bookkeeping, verification, and recovery; on RoboCasa365 with XR-1 as the action model it raises Composite-Unseen success from 34.3% to 38.3% and overall success from 56.6% to 61.1%, a HexaModel v0.1 fine-tuned on Harness-collected traces beats its base model on every split in the same Harness, PhyBench simulated physics experiments are completed with mean relative errors below 5%, and on a dual-arm AgileX robot five of seven tabletop tasks succeed in all three trials.
Writing robot tasks as code: HexaAnything lifts RoboCasa365 Composite-Unseen success from 34.3% to 38.3% and turns Harness traces into a stronger HexaModel
The work proposes Physical Coding, representing physical world state (Code as World) and execution procedure (Code as Policy) as executable programs, and builds the physical coding agent HexaAnything, which treats VLA/WAM policies as callable action tools while a Harness owns state bookkeeping, verification, and recovery; on RoboCasa365 with XR-1 as the action model it raises Composite-Unseen success from 34.3% to 38.3% and overall success from 56.6% to 61.1%, a HexaModel v0.1 fine-tuned on Harness-collected traces beats its base model on every split in the same Harness, PhyBench simulated physics experiments are completed with mean relative errors below 5%, and on a dual-arm AgileX robot five of seven tabletop tasks succeed in all three trials.
The work proposes Physical Coding, representing physical world state (Code as World) and execution procedure (Code as Policy) as executable programs, and builds the physical coding agent HexaAnything, which treats VLA/WAM policies as callable action tools while a Harness owns state bookkeeping, verification, and recovery; on RoboCasa365 with XR-1 as the action model it raises Composite-Unseen success from 34.3% to 38.3% and overall success from 56.6% to 61.1%, a HexaModel v0.1 fine-tuned on Harness-collected traces beats its base model on every split in the same Harness, PhyBench simulated physics experiments are completed with mean relative errors below 5%, and on a dual-arm AgileX robot five of seven tabletop tasks succeed in all three trials.
arXiv Sep 29, 2026
Relic lets multi-agent organizations turn recurring collaboration failures into organization-owned, executable, revisable protocols, raising complete-contract delivery on mainline from 14.06% to 19.76% (+5.71 percentage points) across 360 controlled runs over ten software workloads and three models, and raising behavioral correctness under fresh-member transfer from 25.4% with no inherited protocol and 34.6% with text-only rules to 41.2% with executable bindings.
Relic lets multi-agent organizations turn recurring collaboration failures into organization-owned, executable, revisable protocols, raising complete-contract delivery on mainline from 14.06% to 19.76% (+5.71 percentage points) across 360 controlled runs over ten software workloads and three models, and raising behavioral correctness under fresh-member transfer from 25.4% with no inherited protocol and 34.6% with text-only rules to 41.2% with executable bindings.
Relic turns recurring collaboration failures into executable protocols, lifting complete-contract delivery from 14.06% to 19.76% across 360 controlled runs
Relic lets multi-agent organizations turn recurring collaboration failures into organization-owned, executable, revisable protocols, raising complete-contract delivery on mainline from 14.06% to 19.76% (+5.71 percentage points) across 360 controlled runs over ten software workloads and three models, and raising behavioral correctness under fresh-member transfer from 25.4% with no inherited protocol and 34.6% with text-only rules to 41.2% with executable bindings.
Relic lets multi-agent organizations turn recurring collaboration failures into organization-owned, executable, revisable protocols, raising complete-contract delivery on mainline from 14.06% to 19.76% (+5.71 percentage points) across 360 controlled runs over ten software workloads and three models, and raising behavioral correctness under fresh-member transfer from 25.4% with no inherited protocol and 34.6% with text-only rules to 41.2% with executable bindings.
arXiv Sep 29, 2026
RoboFoundry proposes a Self-Evolving System-as-Policy framework that treats the entire supporting system around a foundation model—its context system and hierarchical skill system—rather than model parameters as the policy to evolve, diagnosing capability gaps from execution traces, converting them into validated task-specific system updates, and promoting recurring improvements into general system capabilities; it achieves state-of-the-art results on EmbodiedBench (improving GPT-5.5 by 27.8% and bringing Qwen3.7-Plus to 70.3% versus GPT-5.5's 72.7%), outperforms all baselines on RoboMemArena long-horizon memory by at least 39.0%, beats Cap-Agent0 on LIBERO-PRO by 243.8%–679.7%, and demonstrates zero-shot transfer and online evolution on real robots.
RoboFoundry proposes a Self-Evolving System-as-Policy framework that treats the entire supporting system around a foundation model—its context system and hierarchical skill system—rather than model parameters as the policy to evolve, diagnosing capability gaps from execution traces, converting them into validated task-specific system updates, and promoting recurring improvements into general system capabilities; it achieves state-of-the-art results on EmbodiedBench (improving GPT-5.5 by 27.8% and bringing Qwen3.7-Plus to 70.3% versus GPT-5.5's 72.7%), outperforms all baselines on RoboMemArena long-horizon memory by at least 39.0%, beats Cap-Agent0 on LIBERO-PRO by 243.8%–679.7%, and demonstrates zero-shot transfer and online evolution on real robots.
RoboFoundry treats the agent system itself as the policy to evolve, lifting GPT-5.5 by 27.8% on EmbodiedBench and transferring zero-shot to real robots
RoboFoundry proposes a Self-Evolving System-as-Policy framework that treats the entire supporting system around a foundation model—its context system and hierarchical skill system—rather than model parameters as the policy to evolve, diagnosing capability gaps from execution traces, converting them into validated task-specific system updates, and promoting recurring improvements into general system capabilities; it achieves state-of-the-art results on EmbodiedBench (improving GPT-5.5 by 27.8% and bringing Qwen3.7-Plus to 70.3% versus GPT-5.5's 72.7%), outperforms all baselines on RoboMemArena long-horizon memory by at least 39.0%, beats Cap-Agent0 on LIBERO-PRO by 243.8%–679.7%, and demonstrates zero-shot transfer and online evolution on real robots.
RoboFoundry proposes a Self-Evolving System-as-Policy framework that treats the entire supporting system around a foundation model—its context system and hierarchical skill system—rather than model parameters as the policy to evolve, diagnosing capability gaps from execution traces, converting them into validated task-specific system updates, and promoting recurring improvements into general system capabilities; it achieves state-of-the-art results on EmbodiedBench (improving GPT-5.5 by 27.8% and bringing Qwen3.7-Plus to 70.3% versus GPT-5.5's 72.7%), outperforms all baselines on RoboMemArena long-horizon memory by at least 39.0%, beats Cap-Agent0 on LIBERO-PRO by 243.8%–679.7%, and demonstrates zero-shot transfer and online evolution on real robots.
arXiv Sep 29, 2026
The work casts quadrilateral block decomposition as a Markov decision process over a half-edge mesh, uses the vertex-irregularity lower bound implied by the discrete Gauss–Bonnet identity (called par) as both reward target and termination test, and trains via behaviour cloning on trivially constructible optimal meshes followed by PPO, producing an all-quadrilateral mesh on all 96 held-out domains, a usable one on 95.7 on average and a provably optimal one on 90, whereas Gmsh's strongest configuration at the same element count completes 51, is usable on 38 and optimal on none.
The work casts quadrilateral block decomposition as a Markov decision process over a half-edge mesh, uses the vertex-irregularity lower bound implied by the discrete Gauss–Bonnet identity (called par) as both reward target and termination test, and trains via behaviour cloning on trivially constructible optimal meshes followed by PPO, producing an all-quadrilateral mesh on all 96 held-out domains, a usable one on 95.7 on average and a provably optimal one on 90, whereas Gmsh's strongest configuration at the same element count completes 51, is usable on 38 and optimal on none.
A reinforcement learning agent produced all-quadrilateral meshes on all 96 held-out domains, reaching the provable irregularity floor on 90
The work casts quadrilateral block decomposition as a Markov decision process over a half-edge mesh, uses the vertex-irregularity lower bound implied by the discrete Gauss–Bonnet identity (called par) as both reward target and termination test, and trains via behaviour cloning on trivially constructible optimal meshes followed by PPO, producing an all-quadrilateral mesh on all 96 held-out domains, a usable one on 95.7 on average and a provably optimal one on 90, whereas Gmsh's strongest configuration at the same element count completes 51, is usable on 38 and optimal on none.
The work casts quadrilateral block decomposition as a Markov decision process over a half-edge mesh, uses the vertex-irregularity lower bound implied by the discrete Gauss–Bonnet identity (called par) as both reward target and termination test, and trains via behaviour cloning on trivially constructible optimal meshes followed by PPO, producing an all-quadrilateral mesh on all 96 held-out domains, a usable one on 95.7 on average and a provably optimal one on 90, whereas Gmsh's strongest configuration at the same element count completes 51, is usable on 38 and optimal on none.
arXiv Sep 29, 2026
KernelZero introduces a co-evolution framework in which a Proposer generates Torch modules at the Coder's current capability frontier and the Coder is trained with CA-GRPO so that performance is optimized only after correctness becomes reliable; both models start from Qwen2.5-Coder-7B and reach 75.8/69.6 pass@1 on KernelBench CUDA Level 1/2 and 77.2/72.5 on Triton, surpassing Claude-4.5-Sonnet on CUDA and DeepSeek-V4-Pro on Triton.
KernelZero introduces a co-evolution framework in which a Proposer generates Torch modules at the Coder's current capability frontier and the Coder is trained with CA-GRPO so that performance is optimized only after correctness becomes reliable; both models start from Qwen2.5-Coder-7B and reach 75.8/69.6 pass@1 on KernelBench CUDA Level 1/2 and 77.2/72.5 on Triton, surpassing Claude-4.5-Sonnet on CUDA and DeepSeek-V4-Pro on Triton.
KernelZero's 7B Proposer–Coder co-evolution reaches 75.8 CUDA and 77.2 Triton pass@1 on KernelBench
KernelZero introduces a co-evolution framework in which a Proposer generates Torch modules at the Coder's current capability frontier and the Coder is trained with CA-GRPO so that performance is optimized only after correctness becomes reliable; both models start from Qwen2.5-Coder-7B and reach 75.8/69.6 pass@1 on KernelBench CUDA Level 1/2 and 77.2/72.5 on Triton, surpassing Claude-4.5-Sonnet on CUDA and DeepSeek-V4-Pro on Triton.
KernelZero introduces a co-evolution framework in which a Proposer generates Torch modules at the Coder's current capability frontier and the Coder is trained with CA-GRPO so that performance is optimized only after correctness becomes reliable; both models start from Qwen2.5-Coder-7B and reach 75.8/69.6 pass@1 on KernelBench CUDA Level 1/2 and 77.2/72.5 on Triton, surpassing Claude-4.5-Sonnet on CUDA and DeepSeek-V4-Pro on Triton.

Page 4 · showing 10