arXiv subjects

Yubo Han

Publications and source records attributed to Yubo Han.

5 recordsLinked to original sources

arXiv2026

Provenance Before Prose: Claim-Locked Reporting

Large language models (LLMs) can fluently verbalize statistical evidence, yet statistical reports can still drift numerical values, invert effect directions, or restate thresholded contrasts as categorical effects. We frame these failures as a control problem: the evidence-bearing content of a scientific report should be fixed by structured statistical results rather than sampled during prose generation. We therefore use cross-run reproducibility to stress-test whether report-visible numbers and claims are bound before prose generation. Existing controls operate at the text or slot level; a deterministic hybrid template reproduces only 61.1% of report-visible numerical content across seeds because the LLM still selects which findings and numbers the template renders. We propose claim-locked reporting, a provenance-before-prose protocol that fixes the evidence source, numbers, direction, and allowed language strength of each reportable claim before the LLM writes only connective prose. Across fMRI functional-connectivity reporting and randomized controlled trial reporting on Evidence Inference 2.0, claim-locked reporting improves reproducibility over the hybrid template by 37.4 and 20.5 points, respectively. Blinded human audits support the observed direction-preservation and governance trends. In an fMRI cost analysis with DeepSeek, claim-locked reporting also yields the lowest observed token use and median generation latency.

cs.CL↗

arXiv2026

Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding

Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, yet reliable recognition across unseen participants remains difficult because scalp EEG is noisy and internally generated stroke sequences vary across individuals. The Multimodal Brain-Computer Interface Grand Challenge provides synchronized EEG and fNIRS for four-class subject-independent handwriting-trajectory classification. We propose FRED, a task-adapted system that models imagined handwriting as a multi-second motor sequence and trains a compact multi-scale temporal network on three complementary EEG frequency views. With three seeds per view, cross-band members produce substantially less-correlated errors than same-band replicas, yielding a clean nine-member ensemble accuracy of 0.8076/0.7242/0.7492 on the public/private/overall test partitions without test-set adaptation or output constraints. The submitted pipeline further incorporates transductive pseudo-label training, three EEG-Conformer members, posterior aggregation, and a paradigm-aware decoder. Because every 12-trial randomization block contains three instances of each class, the final predictions are obtained by Hungarian assignment under the known block quota. On one fixed posterior pool, independent, session-constrained, and block-constrained decoding achieve 0.7600, 0.7758, and 0.7952 overall accuracy, respectively. The complete system reaches 0.8498/0.7718/0.7952, ranking fourth on the private split. A modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025. These results identify frequency-diverse temporal EEG modeling and protocol-matched structured inference as the principal sources of performance in this sparse-montage EEG--fNIRS setting. The source code is available at https://github.com/XiuFan719/EEG-fNIRS-fuse-method-for-MM-challenge.

cs.CV↗

arXiv2025

Transmit Weights, Not Features: Orthogonal-Basis Aided Wireless Point-Cloud Transmission

The widespread adoption of depth sensors has substantially lowered the barrier to point-cloud acquisition. This letter proposes a semantic wireless transmission framework for three dimension (3D) point clouds built on Deep Joint Source - Channel Coding (DeepJSCC). Instead of sending raw features, the transmitter predicts combination weights over a receiver-side semantic orthogonal feature pool, enabling compact representations and robust reconstruction. A folding-based decoder deforms a 2D grid into 3D, enforcing manifold continuity while preserving geometric fidelity. Trained with Chamfer Distance (CD) and an orthogonality regularizer, the system is evaluated on ModelNet40 across varying Signal-to-Noise Ratios (SNRs) and bandwidths. Results show performance on par with SEmantic Point cloud Transmission (SEPT) at high bandwidth and clear gains in bandwidth-constrained regimes, with consistent improvements in both Peak Signal-to-Noise Ratio (PSNR) and CD. Ablation experiments confirm the benefits of orthogonalization and the folding prior.

cs.LG↗

arXiv2024

End-to-End Multi-Track Reconstruction using Graph Neural Networks at Belle II

We present the study of an end-to-end multi-track reconstruction algorithm for the central drift chamber of the Belle II experiment at the SuperKEKB collider using Graph Neural Networks for an unknown number of particles. The algorithm uses detector hits as inputs without pre-filtering to simultaneously predict the number of track candidates in an event and their kinematic properties. In a second step, we cluster detector hits for each track candidate to pass to a track fitting algorithm. Using a realistic full detector simulation including beam-induced backgrounds and detector noise taken from actual collision data, we find significant improvements in track finding efficiencies for tracks in a variety of different event topologies compared to the existing baseline algorithm used in Belle II. For events with a hypothetical long-lived massive particle with a mass in the GeV-range decaying uniformly along its flight direction into two charged particles, the GNN achieves a combined track finding and fitting efficiency of 85.4% with a fake rate of 2.5%, compared to 52.2% and 4.1% for the baseline algorithm. This is the first end-to-end multi-track machine learning algorithm for a drift chamber detector that has been utilized in a realistic particle physics environment.

physics.ins-det↗

arXiv2022

Topmetal-M: a novel pixel sensor for compact tracking applications

The Topmetal-M is a large area pixel sensor (18 mm * 23 mm) prototype fabricated in a new 130 nm high-resistivity CMOS process in 2019. It contains 400 rows * 512 columns square pixels with the pitch of 40 {\mu}m. In Topmetal-M, a novel charge collection method combing the Monolithic Active Pixel Sensor (MAPS) and the Topmetal sensor has been proposed for the first time. Both the ionized charge deposited by the particle in the sensor and along the track over the sensor can be collected. The in-pixel circuit mainly consists of a low-noise charge sensitive amplifier to establish the signal for the energy reconstruction, and a discriminator with a Time-to-Amplitude Converter (TAC) for the Time of Arrival (TOA) measurement. With this mechanism, the trajectory, particle hit position, energy and arrival time of the particle can be measured. The analog signal from each pixel is accessible through time-shared multiplexing over the entire pixel array. This paper will discuss the design and preliminary test results of the Topmetal-M sensor.

physics.ins-det↗