arXiv subjects

Yihang Zhu

Publications and source records attributed to Yihang Zhu.

16 recordsLinked to original sources

arXiv2026

MCHA: A Memory-Centric Hierarchical Architecture for Parallel-Sequential Computing

Emerging workloads, such as Multi-Agent Reinforcement Learning (MARL), large-scale neuromorphic computing, and probabilistic graphical models, intrinsically exhibit parallel-sequential computing patterns. While these tasks demand massive parallelism to achieve high throughput, they are severely bottlenecked by irregular data access patterns centralized to main memory. Consequently, conventional architectures face fundamental limitations when executing these workloads, primarily manifesting as global buffer saturation and memory-bound bottlenecks. To address these challenges, we propose the Memory-Centric Hierarchical Architecture (MCHA), a reconfigurable hardware solution tailored for parallel-sequential execution. MCHA leverages a hierarchical communication strategy that facilitates distributed, inter-core data routing, thereby significantly reducing the bandwidth burden on the global memory. Complementing the hardware, MCHA introduces a novel parallel-sequential programming model that utilizes event-driven conditional triggers to effectively hide data transmission latency within the execution pipeline. We benchmark MCHA against a diverse suite of parallel-sequential tasks, including MARL, motor variable control, and Markov random fields. Validated through our open-source, cycle-accurate simulator, MCHA demonstrates performance speedups ranging from 153.06$\times$ to 2456.96$\times$ over NVIDIA A100 GPUs on MARL workloads, while maintaining robust programming flexibility across other application domains. Furthermore, the architecture successfully reduces main memory access from 96% to 5.44%. When synthesized in a 28 nm process, the MCHA implementation occupies an area footprint of 2.92mm$^2$ and consumes 115.36 mW of power at 200 MHz. MCHA is open-sourced at https://github.com/carabdis/MCHA.

cs.AR↗

arXiv2026

Hypergraph Minority Game with Local Hyperedge Payoffs

We provide a theoretical derivation of the Hypergraph Minority Game with Local Hyperedge Payoffs (HMG-L), in which $N$ adaptive agents compete simultaneously in multiple overlapping groups modeled as hyperedges of a static hypergraph $\Hyper=(\Vset,\Eset)$. Each hyperedge constitutes an independent local minority game, and agents accumulate payoffs across all groups to which they belong. We derive the continuum-time limit of the score dynamics, from which we obtain a set of coupled nonlinear stochastic differential equations for the agents' strategy polarization variables. The deterministic drift is shown to derive from a global cost function that generalizes the standard Minority Game Hamiltonian to hypergraph-structured interactions. We perform a sparse-annealed replica analysis of the stationary state for the case of a $k$-uniform, $d$-regular random hypergraph, obtaining the saddle-point equations within the replica-symmetric ansatz, an explicit replicon stability criterion, and Bethe/cavity equations for sparse corrections. The leading sparse-regime transition occurs on a critical surface $\alphacrit(k,d)$, while the globally coupled MG value $\alphacrit\simeq0.3374$ is recovered only in the separate single-hyperedge limit. We derive expressions for the order parameters -- global volatility $\sigma^2$, predictability $\theta$, hyperedge frustration $F_e$, and frozen fraction $\phi$ -- and discuss their scaling behavior near criticality. The Fokker-Planck equation governing finite-$N$ fluctuations is presented, and the noise covariance matrix is computed from the hypergraph structure. Limiting cases ($k\to N$, $k\to2$, $d\to\infty$) are analyzed in detail, establishing connections to the standard MG, networked MG, and parallel MG models.

physics.soc-ph↗

arXiv2026

Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding

Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in modeling action understanding, the influence of the agent's intention on the action is often overlooked. Motivated by these issues, we propose a novel framework called the State-Specific Model (SSM), designed to unify and enhance both action detection and anticipation tasks. In the proposed framework, the Critical State-Based Memory Compression module compresses frame sequences into critical states, reducing information redundancy. The Action Pattern Learning module constructs a state-transition graph with multi-dimensional edges to model action dynamics in complex scenarios, on the basis of which potential future cues can be generated to represent intention. Furthermore, our Cross-Temporal Interaction module models the mutual influence between intentions and past as well as current information through cross-temporal interactions, thereby refining present and future features and ultimately realizing simultaneous action detection and anticipation. Extensive experiments on multiple benchmark datasets -- including EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour (PDMB) dataset -- demonstrate the superior performance of our proposed framework compared to other state-of-the-art approaches. These results highlight the importance of action dynamics learning and cross-temporal interactions, laying a foundation for future action understanding research.

cs.CV↗

arXiv2025

Learning Semantic Atomic Skills for Multi-Task Robotic Manipulation

Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality, and destructive interference across tasks. While skill-based methods offer a promising direction by decomposing behaviors into reusable abstractions, existing approaches often learn skills that are either biased toward linguistic structure or lack semantic alignment across tasks, limiting generalization. In this work, we propose AtomSkill, a novel framework that learns a semantically aligned Atomic Skill Space from demonstrations and enables robust long-horizon execution through keypose imagination. Our method introduces: (1) semantic contrastive skill alignment, which partitions demonstrations into variable-length atomic skills and employs a contrastive objective to jointly enforce semantic consistency and temporal coherence, yielding a compact and reusable skill library; and (2) action decoding with keypose imagining, where the policy predicts both a skill's terminal keypose and immediate actions, thereby supporting progress-aware skill transitions. During inference, an atomic skill diffusion sampler generates plausible skill sequences, while predicted keyposes autonomously trigger smooth skill chaining. Extensive experiments in simulation and real-world settings show that AtomSkill consistently outperforms state-of-the-art imitation learning and skill-based baselines. Project page: https://atom-skill.github.io.

cs.RO↗

arXiv2025

SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding

3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world applications since eliminating scene-specific training requirements. However, existing zero-shot methods face challenges of spatial-limited reasoning due to reliance on single-view localization, and contextual omissions or detail degradation. To address these issues, we propose SeqVLM, a novel zero-shot 3DVG framework that leverages multi-view real-world scene images with spatial information for target object reasoning. Specifically, SeqVLM first generates 3D instance proposals via a 3D semantic segmentation network and refines them through semantic filtering, retaining only semantic-relevant candidates. A proposal-guided multi-view projection strategy then projects these candidate proposals onto real scene image sequences, preserving spatial relationships and contextual details in the conversion process of 3D point cloud to images. Furthermore, to mitigate VLM computational overload, we implement a dynamic scheduling mechanism that iteratively processes sequances-query prompts, leveraging VLM's cross-modal reasoning capabilities to identify textually specified objects. Experiments on the ScanRefer and Nr3D benchmarks demonstrate state-of-the-art performance, achieving Acc@0.25 scores of 55.6% and 53.2%, surpassing previous zero-shot methods by 4.0% and 5.2%, respectively, which advance 3DVG toward greater generalization and real-world applicability. The code is available at https://github.com/JiawLin/SeqVLM.

cs.CV↗

arXiv2025

Multi-modal Multi-platform Person Re-Identification: Benchmark and Method

Conventional person re-identification (ReID) research is often limited to single-modality sensor data from static cameras, which fails to address the complexities of real-world scenarios where multi-modal signals are increasingly prevalent. For instance, consider an urban ReID system integrating stationary RGB cameras, nighttime infrared sensors, and UAVs equipped with dynamic tracking capabilities. Such systems face significant challenges due to variations in camera perspectives, lighting conditions, and sensor modalities, hindering effective person ReID. To address these challenges, we introduce the MP-ReID benchmark, a novel dataset designed specifically for multi-modality and multi-platform ReID. This benchmark uniquely compiles data from 1,930 identities across diverse modalities, including RGB, infrared, and thermal imaging, captured by both UAVs and ground-based cameras in indoor and outdoor environments. Building on this benchmark, we introduce Uni-Prompt ReID, a framework with specific-designed prompts, tailored for cross-modality and cross-platform scenarios. Our method consistently outperforms state-of-the-art approaches, establishing a robust foundation for future research in complex and dynamic ReID environments. Our dataset are available at:https://mp-reid.github.io/.

cs.CV↗

arXiv2025

AffordDP: Generalizable Diffusion Policy with Transferable Affordance

Diffusion-based policies have shown impressive performance in robotic manipulation tasks while struggling with out-of-domain distributions. Recent efforts attempted to enhance generalization by improving the visual feature encoding for diffusion policy. However, their generalization is typically limited to the same category with similar appearances. Our key insight is that leveraging affordances--manipulation priors that define "where" and "how" an agent interacts with an object--can substantially enhance generalization to entirely unseen object instances and categories. We introduce the Diffusion Policy with transferable Affordance (AffordDP), designed for generalizable manipulation across novel categories. AffordDP models affordances through 3D contact points and post-contact trajectories, capturing the essential static and dynamic information for complex tasks. The transferable affordance from in-domain data to unseen objects is achieved by estimating a 6D transformation matrix using foundational vision models and point cloud registration techniques. More importantly, we incorporate affordance guidance during diffusion sampling that can refine action sequence generation. This guidance directs the generated action to gradually move towards the desired manipulation for unseen objects while keeping the generated action within the manifold of action space. Experimental results from both simulated and real-world environments demonstrate that AffordDP consistently outperforms previous diffusion-based methods, successfully generalizing to unseen instances and categories where others fail.

cs.RO↗

arXiv2025

Non-Binary LDPC Arithmetic Error Correction For Processing-in-Memory

Processing-in-memory (PIM) based on emerging devices such as memristors is more vulnerable to noise than traditional memories, due to the physical non-idealities and complex operations in analog domains. To ensure high reliability, efficient error-correcting code (ECC) is highly desired. However, state-of-the-art ECC schemes for PIM suffer drawbacks including dataflow interruptions, low code rates, and limited error correction patterns. In this work, we propose non-binary low-density parity-check (NB-LDPC) error correction running over the Galois field. Such NB-LDPC scheme with a long word length of 1024 bits can correct up to 8-bit errors with a code rate over 88%. Nonbinary GF operations can support both memory mode and PIM mode even with multi-level memory cells. We fabricate a 40nm prototype PIM chip equipped with our proposed NB-LDPC scheme for validation purposes. Experiments show that PIM with NB-LDPC error correction demonstrates up to 59.65 times bit error rate (BER) improvement over the original PIM without such error correction. The test chip delivers 2.978 times power efficiency enhancement over prior works.

cs.AR↗

arXiv2023

The stabilization of the Frobenius--Hecke traces on the intersection cohomology of orthogonal Shimura varieties

We study Shimura varieties associated with special orthogonal groups over the field of rational numbers. We prove a version of Morel's formula for the Frobenius--Hecke traces on the intersection cohomology of the Baily--Borel compactification. Our main result is the stabilization of this formula. As an application, we compute the Hasse--Weil zeta function of the intersection cohomology in some special cases, using the recent work of Arthur and Taïbi on the endoscopic classification of automorphic representations of special orthogonal groups.

math.NT↗

arXiv2023

Fast and reconfigurable sort-in-memory system enabled by memristors

Sorting is fundamental and ubiquitous in modern computing systems. Hardware sorting systems are built based on comparison operations with Von Neumann architecture, but their performance are limited by the bandwidth between memory and comparison units and the performance of complementary metal-oxide-semiconductor (CMOS) based circuitry. Sort-in-memory (SIM) based on emerging memristors is desired but not yet available due to comparison operations that are challenging to be implemented within memristive memory. Here we report fast and reconfigurable SIM system enabled by digit read (DR) on 1-transistor-1-resistor (1T1R) memristor arrays. We develop DR tree node skipping (TNS) that support variable data quantity and data types, and extend TNS with multi-bank, bit-slice and multi-level strategies to enable cross-array TNS (CA-TNS) for practical adoptions. Experimented on benchmark sorting datasets, our memristor-enabled SIM system presents up to 3.32x~7.70x speedup, 6.23x~183.5x energy efficiency improvement and 2.23x~7.43x area reduction compared with state-of-the-art sorting systems. We apply such SIM system for shortest path search with Dijkstra's algorithm and neural network inference with in-situ pruning, demonstrating the capability in solving practical sorting tasks and the compatibility in integrating with other compute-in-memory (CIM) schemes. The comparison-free TNS/CA-TNS SIM enabled by memristors pushes sorting into a new paradigm of sort-in-memory for next-generation sorting systems.

cs.AR↗

arXiv2021

The stable trace formula for Shimura varieties of abelian type

We express the Frobenius-Hecke traces on the compactly supported cohomology of a Shimura variety of abelian type in terms of elliptic parts of stable Arthur-Selberg trace formulas for the endoscopic groups. This confirms predictions of Langlands and Kottwitz at primes where the level is hyperspecial.

math.NT↗

arXiv2021

Stabilizers of irreducible components of affine Deligne--Lusztig varieties

We study the $J_b(F)$-action on the set of top-dimensional irreducible components of affine Deligne--Lusztig varieties in the affine Grassmannian. We show that the stabilizer of any such component is a parahoric subgroup of $J_b(F)$ of maximal volume, verifying a conjecture of X.~Zhu. As an application, we give a description of the set of top-dimensional irreducible components in the basic locus of Shimura varieties.

math.AG↗

arXiv2020

Twisted orbital integrals and irreducible components of affine Deligne-Lusztig varieties

We analyze the asymptotic behavior of certain twisted orbital integrals arising from the study of affine Deligne-Lusztig varieties. The main tools include the Base Change Fundamental Lemma and $q$-analogues of the Kostant partition functions. As an application we prove a conjecture of Miaofen Chen and Xinwen Zhu, relating the set of irreducible components of an affine Deligne-Lusztig variety modulo the action of the $σ$-centralizer group to the Mirkovic-Vilonen basis of a certain weight space of a representation of the Langlands dual group.

math.NT↗

arXiv2020

Fine Deligne-Lusztig varieties and Arithmetic Fundamental Lemmas

We prove a character formula for some closed fine Deligne-Lusztig varieties. We apply it to compute fixed points for fine Deligne-Lusztig varieties arising from the basic loci of Shimura varieties of Coxeter type. As an application, we prove an arithmetic intersection formula for certain diagonal cycles on unitary and GSpin Rapoport-Zink spaces arising from the arithmetic Gan-Gross-Prasad conjectures. In particular, we prove the arithmetic fundamental lemma in the minuscule case, without assumptions on the residual characteristic.

math.NT↗

arXiv2017

Remarks on the arithmetic fundamental lemma

W. Zhang's arithmetic fundamental lemma (AFL) is a conjectural identity between the derivative of an orbital integral on a symmetric space with an arithmetic intersection number on a unitary Rapoport-Zink space. In the minuscule case, Rapoport-Terstiege-Zhang have verified the AFL conjecture via explicit evaluation of both sides of the identity. We present a simpler way for evaluating the arithmetic intersection number, thereby providing a new proof of the AFL conjecture in the minuscule case.

math.NT↗

arXiv2017

Arithmetic intersection on GSpin Rapoport-Zink spaces

We prove an explicit formula for the arithmetic intersection number of diagonal cycles on GSpin Rapoport-Zink spaces in the minuscule case. This is a local problem arising from the arithmetic Gan-Gross-Prasad conjecture for orthogonal Shimura varieties. Our formula can be viewed as an orthogonal counterpart of the arithmetic-geometric side of the arithmetic fundamental lemma proved by Rapoport-Terstiege-Zhang in the minuscule case.

math.NT↗