Searcharxiv⌕ Search

arXiv subjects

Jiahao Lin

Publications and source records attributed to Jiahao Lin.

At least 19 recordsLinked to original sources

Uniform Inference for Two-Way Clustered Data

We establish uniformly asymptotically exact inference for the population mean of two-way clustered data, allowing the data-generating process to vary with sample size. This finding does not contradict the well-known impossibility result of Menzel (2021), which places a fundamental limit on uniform estimation of the asymptotic distribution of the normalized full-array mean. We estimate the same population mean by averaging the sample means from random matchings. A closed-form standard error makes the resulting confidence interval straightforward to implement. The variance estimator is positive semidefinite and the studentized matching estimator is uniformly asymptotically standard normal. The cost of uniform validity is a slower convergence rate under degeneracy. We extend the result to smooth functions of GMM parameters, allowing the different moment components to exhibit different dependence regimes. In simulations, the proposed confidence intervals achieve coverage close to the nominal level across the dependence regimes considered.

econ.EM↗

Specification Testing for Dyadic Regression Models

Of the 88 empirical papers on dyadic or other relational data that we reviewed in the top five economics journals, 55 (62.5\%) use a linear specification. To assess whether such a specification describes the conditional mean, we develop Kolmogorov-Smirnov and Cramér-von Mises tests for undirected dyadic data that also accommodate smooth nonlinear specifications. To our knowledge, this paper is the first to develop omnibus specification tests for undirected dyadic regression models. A corrected first-order multiplier bootstrap is asymptotically exact in two standard Gaussian cases: the first-order nondegenerate case and independent dyads case. For a general class of such processes, we establish that a second-order multiplier bootstrap consistently approximates the limiting law uniformly over the indexing function class, even when the indexing functions are estimated. For the specification tests, we augment this bootstrap to account for two additional sources of non-Gaussianity: parameter estimation and the curvature of the regression function. We then construct an envelope test that is asymptotically exact in both Gaussian cases and controls size in the other degenerate cases. Simulations illustrate the size and power of the tests. In an application to housing sales, we reject a common mean price gap within distance bands but do not reject separate linear relationships by metro access.

econ.EM↗

PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review

Large language models (LLMs) can generate fluent peer reviews but often miss sparse, subtle, and document-level scientific errors. We introduce PaperAudit-Bench, a benchmark for evaluating paper-level error detection and error-aware automated review. It comprises (1) PaperAudit-Dataset, 220 high-quality AI/ML papers containing more than 2,200 controlled synthetic errors across eight categories, and (2) PaperAudit-Review, an evidence-aware framework that links structured error detection to review generation. Experiments across models, error categories, paper sections, and analysis depths show that sparse long-context auditing remains challenging for current LLMs. Conditioning review generation on explicit, manuscript-grounded error evidence produces more conservative and discriminative assessments that align more closely with human judgments than representative automated-review baselines. The dataset also supports post-training compact detectors through SFT and RL; Qwen3-14B achieves 55.8% F1 at Detection@1 under a fixed held-out protocol. A PubPeer transfer study and deployment in ScienceOne, a scientific foundation-model platform led by the Chinese Academy of Sciences, further illustrate practical applicability. Code and Dataset Page: https://github.com/TU2021/PaperAudit ScienceOne Manuscript Review: https://www.scienceone.cn/lit/#/assistant

cs.CL↗

GMM for Panel Data Quantile Regression

This paper develops a smoothed generalized method of moments (GMM) framework for panel quantile models with individual-specific fixed-effects and endogenous regressors. By smoothing the indicator in the quantile moment conditions and profiling out the individual effects through smoothed individual quantile restrictions, the proposed estimator can be implemented using standard GMM algorithms. We establish consistency, asymptotic normality, and feasible inference under weak time dependence as both panel dimensions diverge. This dependence structure accommodates dynamic panel specifications, serially dependent disturbances, lagged instruments, and within-individual heteroskedasticity and autocorrelation consistent inference. Monte Carlo simulations show that the estimator is nearly unbiased under endogeneity and yields generally accurate inference while remaining computationally tractable. An application to OECD inflation dynamics suggests asymmetric inflation propagation: under the structural IVQR interpretation, the response of current inflation to lagged inflation is substantially larger at the lower structural quantile than at the upper structural quantile.

econ.EM↗

Robust Inference for Dyadic Data with Spatially Dependent Nodes

We develop inference for complete dyadic samples with spatial dependence governed by geographic distances between nodes, covering settings beyond the scope of existing dyadic inference theory. We propose spatial variance and corrected block jackknife estimators consistent in nondegenerate and degenerate Gaussian cases. Under degeneracy, spatial subsampling consistently estimates possibly non-Gaussian limits. Combining the jackknife with subsampling yields the max jackknifes-ubsampling (MJS) interval, which provides pointwise asymptotically exact coverage in both Gaussian cases and conservative coverage in the specified non-Gaussian case. Fixed-effect extensions show that estimating node effects can change the fast limiting distribution. Simulations and an empirical illustration are provided.

econ.EM↗

HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads

Hybrid Transformer-Mamba large language models (LLMs) enhance long-context efficiency, but their heterogeneous computation and communication patterns complicate efficient hardware acceleration. Chiplet-based architectures offer a scalable solution by integrating specialized compute and memory units. However, the design space spanning static architectural configurations and dynamic runtime policies is prohibitively large to explore exhaustively. To address this challenge, we present HYDRA, a comprehensive design space exploration framework for hybrid LLM serving on heterogeneous chiplet systems. HYDRA jointly explores chiplet composition, placement, inter-chiplet bandwidth provisioning, dynamic batching, and runtime scheduling. It integrates communication-aware placement, dynamic batching, elastic task scheduling, and a fast Markov-based performance estimator that captures multi-tenant runtime dynamics for efficient and accurate exploration. Across all workloads, HYDRA delivers 1.55x the throughput and 43.7 percent lower time-to-first-token on average, with throughput gains reaching up to 2.3x compared to state-of-the-art baselines. These results highlight that co-designing architecture and runtime policies is critical for efficient large-scale LLM serving on heterogeneous chiplet systems.

cs.AR↗

Two-way Clustering Robust Variance Estimator in Quantile Regression Models

We study inference for linear quantile regression with two-way clustered data. Using a separately exchangeable array framework and a projection decomposition of the quantile score, we characterize regime-dependent convergence rates and establish a self-normalized Gaussian approximation. We propose a two-way cluster-robust sandwich variance estimator with a kernel-based density ``bread'' and a projection-matched ``meat'', and prove consistency and validity of inference in Gaussian regimes. We also show an impossibility result for uniform inference in a non-Gaussian interaction regime.

econ.EM↗

Estimation and Inference for the $τ$-Quantile of Individual Heterogeneous Coefficient

This paper proposes estimation and inference procedures for quantiles of the heterogeneous individual-specific coefficients in panel data. Unlike conventional panel quantile regression, which focuses on outcome heterogeneity, our approach targets the $τ$-quantile of the cross-sectional distribution of individual-specific slopes. We establish the asymptotic theory under both stochastic and deterministic designs, with convergence rates $\sqrt{N}$ and $\sqrt{N\sqrt{T}}$, respectively. We also develop two corresponding bootstrap procedures for practical inference, and formally establish their validity. The suggested methods are of practical interest since they require weaker sample size growth conditions than standard fixed-effect quantile regression, and accommodate large $N$ settings. Numerical simulations and an empirical application illustrate the empirical effectiveness of the methods under both designs.

econ.EM↗

Bootstrap Inference under General Two-way Clustering with Serially and Spatially Dependent Common Effects

This paper develops bootstrap procedures for inference in linear regression models with two-way clustered data. We characterize the estimator's asymptotic behavior in five mutually exclusive and exhaustive regimes: three Gaussian and two non-Gaussian. We establish four impossibility results: heterogeneous score components preclude uniform consistency; uniform consistency also fails in one non-Gaussian (infeasible) regime; the infeasible regime is not uniformly distinguishable from a feasible one; and uniform validity over all feasible regimes rules out uniform conservativeness over the infeasible regime. To address the feasible regimes, we propose a data-driven regime classifier and a projection-based wild bootstrap procedure. The procedure delivers uniformly valid inference across the four feasible regimes while allowing serial dependence along the second clustering dimension and spatial dependence along the first. This combination of regime adaptivity and flexible dependence is new to the two-way clustering literature. Monte Carlo simulations confirm the accuracy and flexibility of the proposed methods in settings with complex clustering structures.

math.ST↗

DUET: Disaggregated Hybrid Mamba-Transformer LLMs with Prefill and Decode-Specific Packages

Large language models operate in distinct compute-bound prefill followed by memory bandwidth-bound decode phases. Hybrid Mamba-Transformer models inherit this asymmetry while adding state space model (SSM) recurrences and element-wise operations that map poorly to matmul-centric accelerators. This mismatch causes performance bottlenecks, showing that a homogeneous architecture cannot satisfy all requirements. We introduce DUET, a disaggregated accelerator that assigns prefill and decode phases to specialized packages. The Prefill package utilizes systolic array chiplets with off-package memory for efficient large matrix multiplications and long-sequence SSMs. The Decode package utilizes vector-unit arrays with high-bandwidth in-package memory to accelerate token-by-token SSM and vector-matrix multiplications. Both architectures are runtime-configurable to support hybrid models with mixed Mamba and attention layers. Evaluations on Nemotron-H-56B, Zamba2-7B, and Llama3-8B across four workloads show that DUET achieves 4x faster time to first token, 1.4x higher throughput, and 1.5x lower time between tokens over the B200 GPU.

cs.AR↗

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency, particularly for simple problems. To address this over-thinking problem, we explore how to equip LRMs with adaptive thinking capabilities: enabling them to dynamically decide whether or not to engage in explicit reasoning based on problem complexity. Building on R1-style distilled models, we observe that inserting a simple ellipsis ("...") into the prompt can stochastically trigger either a thinking or no-thinking mode, revealing a latent controllability in the reasoning behavior. Leveraging this property, we propose AutoThink, a multi-stage reinforcement learning (RL) framework that progressively optimizes reasoning policies via stage-wise reward shaping. AutoThink learns to invoke explicit reasoning only when necessary, while defaulting to succinct responses for simpler tasks. Experiments on five mainstream mathematical benchmarks demonstrate that AutoThink achieves favorable accuracy-efficiency trade-offs compared to recent prompting and RL-based pruning methods. It can be seamlessly integrated into any R1-style model, including both distilled and further fine-tuned variants. Notably, AutoThink improves relative accuracy by 6.4 percent while reducing token usage by 52 percent on DeepSeek-R1-Distill-Qwen-1.5B, establishing a scalable and adaptive reasoning paradigm for LRMs. Project Page: https://github.com/ScienceOne-AI/AutoThink.

cs.CL↗

eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing

State Space Model (SSM)-based machine learning architectures have recently gained significant attention for processing sequential data. Mamba, a recent sequence-to-sequence SSM, offers competitive accuracy with superior computational efficiency compared to state-of-the-art transformer models. While this advantage makes Mamba particularly promising for resource-constrained edge devices, no hardware acceleration frameworks are currently optimized for deploying it in such environments. This paper presents eMamba, a comprehensive end-to-end hardware acceleration framework explicitly designed for deploying Mamba models on edge platforms. eMamba maximizes computational efficiency by replacing complex normalization layers with lightweight hardware-aware alternatives and approximating expensive operations, such as SiLU activation and exponentiation, considering the target applications. Then, it performs an approximation-aware neural architecture search (NAS) to tune the learnable parameters used during approximation. Evaluations with Fashion-MNIST, CIFAR-10, and MARS, an open-source human pose estimation dataset, show eMamba achieves comparable accuracy to state-of-the-art techniques using 1.63-19.9$\times$ fewer parameters. In addition, it generalizes well to large-scale natural language tasks, demonstrating stable perplexity across varying sequence lengths on the WikiText2 dataset. We also quantize and implement the entire eMamba pipeline on an AMD ZCU102 FPGA and ASIC using GlobalFoundries (GF) 22 nm technology. Experimental results show 4.95-5.62$\times$ lower latency and 2.22-9.95$\times$ higher throughput, with 4.77$\times$ smaller area, 9.84$\times$ lower power, and 48.6$\times$ lower energy consumption than baseline solutions while maintaining competitive accuracy.

cs.LG↗

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with RL-based approaches have led to growing interest in alternative paradigms, such as Direct Preference Optimization (DPO). In this study, we investigate the effectiveness of DPO in facilitating self-improvement for LLMs through iterative preference-based learning. We demonstrate that a single round of DPO with coarse filtering significantly enhances mathematical reasoning performance, particularly for strong base model. Furthermore, we design an iterative enhancement framework for both the generator and the reward model (RM), enabling their mutual improvement through online interaction across multiple rounds of DPO. Finally, with simple verifiable rewards, our model DPO-VP achieves RL-level performance with significantly lower computational overhead. These findings highlight DPO as a scalable and cost-effective alternative to RL, offering a practical solution for enhancing LLM reasoning in resource-constrained situations.

cs.CL↗

K-PACT: Kernel Planning for Adaptive Context Switching -- A Framework for Clustering, Placement, and Prefetching in Spectrum Sensing

Efficient wideband spectrum sensing requires rapid evaluation and re-evaluation of signal presence and type across multiple subchannels. These tasks involve multiple hypothesis testing, where each hypothesis is implemented as a decision tree workflow containing compute-intensive kernels, including FFT, matrix operations, and signal-specific analyses. Given dynamic nature of the spectrum environment, ability to quickly switch between hypotheses is essential for maintaining low-latency, high-throughput operation. This work assumes a coarse-grained reconfigurable architecture consisting of an array of processing elements (PEs), each equipped with a local instruction memory (IMEM) capable of storing and executing kernels used in spectrum sensing applications. We propose a planner tool that efficiently maps hypothesis workflows onto this architecture to enable fast runtime context switching with minimal overhead. The planner performs two key tasks: clustering temporally non-overlapping kernels to share IMEM resources within a PE sub-array, and placing these clusters onto hardware to ensure efficient scheduling and data movement. By preloading kernels that are not simultaneously active into same IMEM, our tool enables low-latency reconfiguration without runtime conflicts. It models the planning process as a multi-objective optimization, balancing trade-offs among context switch overhead, scheduling latency, and dataflow efficiency. We evaluate the proposed tool in simulated spectrum sensing scenario with 48 concurrent subchannels. Results show that our approach reduces off-chip binary fetches by 207.81x, lowers average switching time by 98.24x, and improves per-subband execution time by 132.92x over baseline without preloading. These improvements demonstrate that intelligent planning is critical for adapting to fast-changing spectrum environments in next-generation radio frequency systems.

cs.ET↗

BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos

Recent advances in deep generative models have led to significant progress in video generation, yet the fidelity of AI-generated videos remains limited. Synthesized content often exhibits visual artifacts such as temporally inconsistent motion, physically implausible trajectories, unnatural object deformations, and local blurring that undermine realism and user trust. Accurate detection and spatial localization of these artifacts are crucial for both automated quality control and for guiding the development of improved generative models. However, the research community currently lacks a comprehensive benchmark specifically designed for artifact localization in AI generated videos. Existing datasets either restrict themselves to video or frame level detection or lack the fine-grained spatial annotations necessary for evaluating localization methods. To address this gap, we introduce BrokenVideos, a benchmark dataset of 3,254 AI-generated videos with meticulously annotated, pixel-level masks highlighting regions of visual corruption. Each annotation is validated through detailed human inspection to ensure high quality ground truth. Our experiments show that training state of the art artifact detection models and multi modal large language models (MLLMs) on BrokenVideos significantly improves their ability to localize corrupted regions. Through extensive evaluation, we demonstrate that BrokenVideos establishes a critical foundation for benchmarking and advancing research on artifact localization in generative video models. The dataset is available at: https://broken-video-detection-datetsets.github.io/Broken-Video-Detection-Datasets.github.io/.

cs.CV↗

Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of inside-space generalization. In this study, we propose Bidirectional Distillation (BiDist), a novel mixed-play framework, to overcome this limitation in MARL. BiDist leverages knowledge distillation in two alternating directions: forward distillation, which emulates the historical policies' space and creates an implicit self-play, and reverse distillation, which systematically drives agents towards novel distributions outside the known policy space in a non-self-play manner. In addition, BiDist operates as a concise and efficient solution without the need for the complex and costly storage of past policies. We provide both theoretical analysis and empirical evidence to support BiDist's effectiveness. Our results highlight its remarkable generalization ability across a variety of cooperative, competitive, and social dilemma tasks, and reveal that BiDist significantly diversifies the policy distribution space. We also present comprehensive ablation studies to reinforce BiDist's effectiveness and key success factors. Source codes are available in the supplementary material.

cs.LG↗

GHuNeRF: Generalizable Human NeRF from a Monocular Video

In this paper, we tackle the challenging task of learning a generalizable human NeRF model from a monocular video. Although existing generalizable human NeRFs have achieved impressive results, they require muti-view images or videos which might not be always available. On the other hand, some works on free-viewpoint rendering of human from monocular videos cannot be generalized to unseen identities. In view of these limitations, we propose GHuNeRF to learn a generalizable human NeRF model from a monocular video of the human performer. We first introduce a visibility-aware aggregation scheme to compute vertex-wise features, which is used to construct a 3D feature volume. The feature volume can only represent the overall geometry of the human performer with insufficient accuracy due to the limited resolution. To solve this, we further enhance the volume feature with temporally aligned point-wise features using an attention mechanism. Finally, the enhanced feature is used for predicting density and color for each sampled point. A surface-guided sampling strategy is also adopted to improve the efficiency for both training and inference. We validate our approach on the widely-used ZJU-MoCap dataset, where we achieve comparable performance with existing multi-view video based approaches. We also test on the monocular People-Snapshot dataset and achieve better performance than existing works when only monocular video is used. Our code is available at the project website.

cs.CV↗

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

Vectorized high-definition (HD) map is essential for autonomous driving, providing detailed and precise environmental information for advanced perception and planning. However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations. To address these limitations, we propose integrating the philosophy of rasterization into map vectorization. Specifically, we introduce a new rasterization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios. Furthermore, we propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiable rasterization to vectorized outputs and then performs precise and geometry-aware supervision on rasterized HD maps. Notably, MapVR designs tailored rasterization strategies for various geometric shapes, enabling effective adaptation to a wide range of map elements. Experiments show that incorporating rasterization into map vectorization greatly enhances performance with no extra computational cost during inference, leading to more accurate map perception and ultimately promoting safer autonomous driving.

cs.CV↗