arXiv subjects

Yansong Xu

Publications and source records attributed to Yansong Xu.

10 recordsLinked to original sources

arXiv2026

Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair

RTL program repair remains a critical bottleneck in hardware design and verification. Traditional automatic program repair (APR) methods rely on predefined templates and synthesis, limiting their bug coverage. Large language models (LLMs) and coding agents based on them offer flexibility but suffer from randomness and context corruption when handling long RTL code and waveforms. We present Clover, a neural-symbolic agentic harness that orchestrates RTL repair as a structured search over code manipulations to explore a validated solution for the bug. Recognizing that different repair operations favor distinct strategies, Clover dynamically dispatches tasks to specialized LLM agents or symbolic solvers. At its core, Clover introduces stochastic tree-of-thoughts, a test-time scaling mechanism that manages the main agent's context as a search tree, balancing exploration and exploitation for reliable outcomes. An RTL-specific toolbox further empowers agents to interact with the debugging environment. Evaluated on the RTL-repair benchmark, Clover fixes 96.8% of bugs within a fixed time limit, covering 94% and 63% more bugs than both pure traditional and LLM-based baselines, respectively, while achieving an average pass@1 rate of 87.5%, demonstrating high reliability and effectiveness.

cs.AR↗

arXiv2026

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely unaddressed, constraining the full potential of agentic systems. At the algorithm level, allocating additional inference-time computation can enhance workflow capacity but introduces cross-path redundancy: overlapping computations across multiple reasoning branches. At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism. However, existing infrastructures' scheduling is unaware of the existence of multiple agents, missing opportunities to optimize resource allocation. We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling. Hive features a description frontend that captures per-agent behavior and supports test-time scaling algorithms. Leveraging this specification, our backend introduces two key mechanisms: Logits Cache that reuses intermediate logits across redundant sampling paths to mitigate cross-path redundancy at the algorithm level, and Agent-Aware Scheduling that efficiently allocates compute and KV-cache resources according to agent contributions at the task level. Experiments show that Logits Cache achieves an average speedup of $1.11\times$-$1.76\times$ for re-sampling, and Agent-Aware Scheduling reduces the hotspot miss rate by $33\%$-$51\%$.

cs.AI↗

arXiv2026

Aquas: Enhancing Domain Specialization through Holistic Hardware-Software Co-Optimization based on MLIR

Application-Specific Instruction-Set Processors (ASIPs) built on the RISC-V architecture offer specialization opportunities for various applications. Existing frameworks are largely designed around fixed instruction extension interfaces and rely on manual software adaptation. However, as emerging domains scale up in complexity, two major challenges arise. First, memory access remains a primary bottleneck as existing design flows lack architectural awareness of memory interfaces, leading to suboptimal interface selection and orchestration. Second, the semantic complexity of custom instruction extensions, characterized by non-trivial control logic and irregular memory behaviors, hinders the ability of conventional compilers to perform automated and comprehensive offloading. We present Aquas, a holistic hardware-software co-design framework built upon MLIR. Aquas proposes a memory interface model that jointly considers interface characteristics and cache effects, along with an interface-aware synthesis flow guided by this model that progressively optimizes the input specification and generates efficient hardware implementations. We also propose an e-graph-based retargetable compiler approach with a novel matching engine for efficient instruction mapping and offloading, enabling robust and effective utilization of custom instruction capabilities. Case studies across four diverse domains show that Aquas delivers substantial acceleration, achieving up to 15.61x speedup with 14.5% area overhead and zero frequency degradation, proving highly competitive in domain acceleration against more powerful general-purpose cores and vector extensions.

cs.AR↗

arXiv2025

FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion

3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling real-time positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterative convergence and resulting in redundant or insufficient gaussian representations. To address this, we introduce a novel adaptive densification method based on Fourier frequency domain analysis to establish gaussian priors for rapid convergence. Additionally, we propose constructing independent and unified sparse and dense maps, where a sparse map supports efficient tracking via Generalized Iterative Closest Point (GICP) and a dense map creates high-fidelity visual representations. This is the first SLAM system leveraging frequency domain analysis to achieve high-quality gaussian mapping in real-time. Experimental results demonstrate an average frame rate of 36 FPS on Replica and TUM RGB-D datasets, achieving competitive accuracy in both localization and mapping.

cs.CV↗

arXiv2024

A Powered Prosthetic Hand with Vision System for Enhancing the Anthropopathic Grasp

The anthropomorphism of grasping process significantly benefits the experience and grasping efficiency of prosthetic hand wearers. Currently, prosthetic hands controlled by signals such as brain-computer interfaces (BCI) and electromyography (EMG) face difficulties in precisely recognizing the amputees' grasping gestures and executing anthropomorphic grasp processes. Although prosthetic hands equipped with vision systems enables the objects' feature recognition, they lack perception of human grasping intention. Therefore, this paper explores the estimation of grasping gestures solely through visual data to accomplish anthropopathic grasping control and the determination of grasping intention within a multi-object environment. To address this, we propose the Spatial Geometry-based Gesture Mapping (SG-GM) method, which constructs gesture functions based on the geometric features of the human hand grasping processes. It's subsequently implemented on the prosthetic hand. Furthermore, we propose the Motion Trajectory Regression-based Grasping Intent Estimation (MTR-GIE) algorithm. This algorithm predicts pre-grasping object utilizing regression prediction and prior spatial segmentation estimation derived from the prosthetic hand's position and trajectory. The experiments were conducted to grasp 8 common daily objects including cup, fork, etc. The experimental results presented a similarity coefficient $R^{2}$ of grasping process of 0.911, a Root Mean Squared Error ($RMSE$) of 2.47\degree, a success rate of grasping of 95.43$\%$, and an average duration of grasping process of 3.07$\pm$0.41 s. Furthermore, grasping experiments in a multi-object environment were conducted. The average accuracy of intent estimation reached 94.35$\%$. Our methodologies offer a groundbreaking approach to enhance the prosthetic hand's functionality and provides valuable insights for future research.

cs.RO↗

arXiv2024

DEFA: Efficient Deformable Attention Acceleration via Pruning-Assisted Grid-Sampling and Multi-Scale Parallel Processing

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE underutilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9x speedup and 20.3-37.7x energy efficiency boost compared to powerful GPUs. It also rivals the related accelerators by 2.2-3.7x energy efficiency improvement while providing pioneering support for MSDeformAttn.

cs.AR↗

arXiv2022

Intersection Numbers and Split of Minor Roots

There are two main parts in this manuscript. First, for a Jacobian pair $(f, g)$, with the concept of final major roots and final minor roots, we obtain equations and inequalities for intersection numbers ${\rm I}(f_ξ, g)$ and ${\rm I}(f_ξ, f_y)$ respectively, here, $ξ$ is a generic element of the base field and $f_ξ=f-ξ$ and discuss usage of them in some special cases. Second, we discuss all possibilities of the splits of principle minor roots for the case of degree (99, 66) with help of Abhyankar-Moh planar semigroup, find an unknown possible split and suggest case (99, 66) is open.

math.AG↗

arXiv2020

Erase-hidden and Drivability-improved Magnetic Non-Volatile Flip-Flops with NAND-SPIN Devices

Non-volatile flip-flops (NVFFs) using power gating techniques promise to overcome the soaring leakage power consumption issue with the scaling of CMOS technology. Magnetic tunnel junction (MTJ) is a good candidate for constructing the NVFF thanks to its low power, high speed, good CMOS compatibility, etc. In this paper, we propose a novel magnetic NVFF based on an emerging memory device called NAND-SPIN. The data writing of NAND-SPIN is achieved by successively applying two unidirectional currents, which respectively generate the spin orbit torque (SOT) and spin transfer torque (STT) for erase and programming operations. This characteristic allows us to design an erase-hidden and drivability-improved magnetic NVFF. Furthermore, more design flexibility could be obtained since the backup operation of the proposed NVFF is not limited by the inherent slave latch. Simulation results show that our proposed NVFF achieves performance improvement in terms of power, delay and area, compared with conventional slave-latch-driven SOT-NVFF designs.

cs.ET↗

arXiv2019

Inward-growth plating of lithium driven by solid-solution based alloy phase for highly reversible lithium metal anode

Lithium metal batteries (LMB) are vital devices for high-energy-density energy storage, but Li metal anode is highly reactive with electrolyte and forms uncontrolled dendrite that can cause undesirable parasitic reactions thus poor cycling stability and raise safety concerns. Despite remarkable progress made to partly solve these issues, the Li metal still plate at the electrode/electrolyte interface where the parasitic reactions and dendrite formation invariably occur. Here we demonstrate the inward-growth plating of Li into a metal foil while avoiding surface deposition, which is driven by the reversible solid-solution based alloy phase change. Lithiation of the solid solution alloy phase facilitates the freshly generated Li atoms at the surface to sink into the foil, while the reversible alloy phase change is companied by the dealloying reaction during delithiation, which extracts Li atoms from inside of the foil. The yielded dendrite free Li anode produces an enhanced Coulombic efficiency of 99.5 plus or minus 0.2% with a reversible capacity of 1660 mA h $g^{-1}$ (3.3 mA h cm$^{-2}$).

physics.chem-ph↗

arXiv2014

A Strong Abhyankar-Moh Theorem and Criterion of Embedded Line

The condition of plane polynomial curve to be a line in well-known Abhyankar-Moh Theorem is replaced by weaker ones. A criterion of embedded line is obtained from this strong theorem: Two polynomials can generate the entire polynomial ring iff their derivatives can be generated.

math.AG↗