arXiv subjects

Bohan Li

Publications and source records attributed to Bohan Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency

Neural speech codecs excel in reconstructing clean speech signals; however, their efficacy in complex acoustic environments and downstream signal processing tasks remains underexplored. In this study, we introduce a novel benchmark named Environment-Resilient Speech Codec Benchmark (ERSB) to systematically evaluate whether neural speech codecs are environment-resilient. Specifically, we assess two key capabilities: (1) robust reconstruction, which measures the preservation of both speech and non-speech acoustic details, and (2) downstream task consistency, which ensures minimal deviation in downstream signal processing tasks when using reconstructed speech instead of the original. Our comprehensive experiments reveal that complex acoustic environments significantly degrade signal reconstruction and downstream task consistency. This work highlights the limitations of current speech codecs and raises a future direction that improves them for greater environmental resilience.

cs.SD↗

arXiv2025

Challenger: Affordable Adversarial Driving Video Generation

Generating photorealistic driving videos has seen significant progress recently, but current methods largely focus on ordinary, non-adversarial scenarios. Meanwhile, efforts to generate adversarial driving scenarios often operate on abstract trajectory or BEV representations, falling short of delivering realistic sensor data that can truly stress-test autonomous driving (AD) systems. In this work, we introduce Challenger, a framework that produces physically plausible yet photorealistic adversarial driving videos. Generating such videos poses a fundamental challenge: it requires jointly optimizing over the space of traffic interactions and high-fidelity sensor observations. Challenger makes this affordable through two techniques: (1) a physics-aware multi-round trajectory refinement process that narrows down candidate adversarial maneuvers, and (2) a tailored trajectory scoring function that encourages realistic yet adversarial behavior while maintaining compatibility with downstream video synthesis. As tested on the nuScenes dataset, Challenger generates a diverse range of aggressive driving scenarios-including cut-ins, sudden lane changes, tailgating, and blind spot intrusions-and renders them into multiview photorealistic videos. Extensive evaluations show that these scenarios significantly increase the collision rate of state-of-the-art end-to-end AD models (UniAD, VAD, SparseDrive, and DiffusionDrive), and importantly, adversarial behaviors discovered for one model often transfer to others.

cs.CV↗

arXiv2025

TAPTRv2: Attention-based Position Update Improves Tracking Any Point

In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-like algorithms. TAPTRv2 improves TAPTR by addressing a critical issue regarding its reliance on cost-volume,which contaminates the point queryś content feature and negatively impacts both visibility prediction and cost-volume computation. In TAPTRv2, we propose a novel attention-based position update (APU) operation and use key-aware deformable attention to realize. For each query, this operation uses key-aware attention weights to combine their corresponding deformable sampling positions to predict a new query position. This design is based on the observation that local attention is essentially the same as cost-volume, both of which are computed by dot-production between a query and its surrounding features. By introducing this new operation, TAPTRv2 not only removes the extra burden of cost-volume computation, but also leads to a substantial performance improvement. TAPTRv2 surpasses TAPTR and achieves state-of-the-art performance on many challenging datasets, demonstrating the superiority

cs.CV↗

arXiv2025

Efficient and wavelength-tunable second-harmonic generation towards the green gap

Achieving compact and efficient visible laser sources is crucial for a wide range of applications. However traditional semiconductor laser technology faces difficulties in producing high-brightness green light, leaving a green gap in wavelength coverage. Second-harmonic generation (SHG) offers a promising alternative by converting near-infrared sources to visible wavelengths with high efficiency and spectral purity. Here, we demonstrate efficient and tunable SHG within the green spectrum using a high-Q Si3N4 microresonator. A space-charge grating induced by the photogalvanic effect realizes reconfigurable grating numbers and flexible wavelength tuning. Additionally, grating formation dynamics and competition is observed. These findings underscore the potential of silicon nitride as a robust, integrative platform for on-chip, tunable green light sources.

physics.optics↗

arXiv2025

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an efficient and generalizable geometric representation that seamlessly connects temporal and spatial synthesis. To address this, we propose DiST-4D, the first disentangled spatiotemporal diffusion framework for 4D driving scene generation, which leverages metric depth as the core geometric representation. DiST-4D decomposes the problem into two diffusion processes: DiST-T, which predicts future metric depth and multi-view RGB sequences directly from past observations, and DiST-S, which enables spatial NVS by training only on existing viewpoints while enforcing cycle consistency. This cycle consistency mechanism introduces a forward-backward rendering constraint, reducing the generalization gap between observed and unseen viewpoints. Metric depth is essential for both accurate reliable forecasting and accurate spatial NVS, as it provides a view-consistent geometric representation that generalizes well to unseen perspectives. Experiments demonstrate that DiST-4D achieves state-of-the-art performance in both temporal prediction and NVS tasks, while also delivering competitive performance in planning-related evaluations.

cs.CV↗

arXiv2025

MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction

Recent breakthroughs in radiance fields have significantly advanced 3D scene reconstruction and novel view synthesis (NVS) in autonomous driving. Nevertheless, critical limitations persist: reconstruction-based methods exhibit substantial performance deterioration under significant viewpoint deviations from training trajectories, while generation-based techniques struggle with temporal coherence and precise scene controllability. To overcome these challenges, we present MuDG, an innovative framework that integrates Multi-modal Diffusion model with Gaussian Splatting (GS) for Urban Scene Reconstruction. MuDG leverages aggregated LiDAR point clouds with RGB and geometric priors to condition a multi-modal video diffusion model, synthesizing photorealistic RGB, depth, and semantic outputs for novel viewpoints. This synthesis pipeline enables feed-forward NVS without computationally intensive per-scene optimization, providing comprehensive supervision signals to refine 3DGS representations for rendering robustness enhancement under extreme viewpoint changes. Experiments on the Open Waymo Dataset demonstrate that MuDG outperforms existing methods in both reconstruction and synthesis quality.

cs.CV↗

arXiv2025

UniScene: Unified Occupancy-centric Driving Scene Generation

Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coarse scene layout, which not only fails to output rich data forms required for diverse downstream tasks but also struggles to model the direct layout-to-data distribution. In this paper, we introduce UniScene, the first unified framework for generating three key data forms - semantic occupancy, video, and LiDAR - in driving scenes. UniScene employs a progressive generation process that decomposes the complex task of scene generation into two hierarchical steps: (a) first generating semantic occupancy from a customized scene layout as a meta scene representation rich in both semantic and geometric information, and then (b) conditioned on occupancy, generating video and LiDAR data, respectively, with two novel transfer strategies of Gaussian-based Joint Rendering and Prior-guided Sparse Modeling. This occupancy-centric approach reduces the generation burden, especially for intricate scenes, while providing detailed intermediate representations for the subsequent generation stages. Extensive experiments demonstrate that UniScene outperforms previous SOTAs in the occupancy, video, and LiDAR generation, which also indeed benefits downstream driving tasks. Project page: https://arlo0o.github.io/uniscene/

cs.CV↗

arXiv2025

Joint Beamforming and Compressed Sensing for Uplink Grant-Free Access

Compressed sensing (CS)-based techniques have been widely applied in the grant-free non-orthogonal multiple access (NOMA) to a single-antenna base station (BS). In this paper, we consider the multi-antenna reception at the BS for uplink grant-free access for the massive machine type communication (mMTC) with limited channel resources. To enhance the overloading performance of the BS, we develop a general framework for the synergistic amalgamation of the spatial division multiple access (SDMA) technique with the CS-based grant-free NOMA. We derive a closed-form statistical beamforming and a dynamic beamforming scheme for the inter-cluster interference suppression when applying SDMA. Based on this, we further develop a joint adaptive beamforming and subspace pursuit (JABF-SP) algorithm for the multiuser detection and data recovery, with a novel sparsity level decision method without the accurate knowledge of the noise level. To further improve the data recovery performance, we propose an interference cancellation based J-ABF-SP scheme (J-ABF-SP-IC) by using the initial signal estimates generated from the J-ABF-SP algorithm. Illustrative simulations verify the superior user detection and signal recovery performance of our proposed algorithms in comparison with existing CS-based grant-free NOMA techniques.

eess.SP↗

arXiv2025

U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack

Recent advancements in Large Language Models (LLMs) have expanded their context windows to unprecedented lengths, sparking debates about the necessity of Retrieval-Augmented Generation (RAG). To address the fragmented evaluation paradigms and limited cases in existing Needle-in-a-Haystack (NIAH), this paper introduces U-NIAH, a unified framework that systematically compares LLMs and RAG methods in controlled long context settings. Our framework extends beyond traditional NIAH by incorporating multi-needle, long-needle, and needle-in-needle configurations, along with different retrieval settings, while leveraging the synthetic Starlight Academy dataset-a fictional magical universe-to eliminate biases from pre-trained knowledge. Through extensive experiments, we investigate three research questions: (1) performance trade-offs between LLMs and RAG, (2) error patterns in RAG, and (3) RAG's limitations in complex settings. Our findings show that RAG significantly enhances smaller LLMs by mitigating the "lost-in-the-middle" effect and improving robustness, achieving an 82.58% win-rate over LLMs. However, we observe that retrieval noise and reverse chunk ordering degrade performance, while surprisingly, advanced reasoning LLMs exhibit reduced RAG compatibility due to sensitivity to semantic distractors. We identify typical error patterns including omission due to noise, hallucination under high noise critical condition, and self-doubt behaviors. Our work not only highlights the complementary roles of RAG and LLMs, but also provides actionable insights for optimizing deployments. Code: https://github.com/Tongji-KGLLM/U-NIAH.

cs.CL↗

arXiv2025

ReF Decompile: Relabeling and Function Call Enhanced Decompile

The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse engineering applications, such as vulnerability identification, malware analysis, and legacy software migration. The end-to-end decompile method based on large langauge models (LLMs) reduces reliance on additional tools and minimizes manual intervention due to its inherent properties. However, previous end-to-end methods often lose critical information necessary for reconstructing control flow structures and variables when processing binary files, making it challenging to accurately recover the program's logic. To address these issues, we propose the \textbf{ReF Decompile} method, which incorporates the following innovations: (1) The Relabelling strategy replaces jump target addresses with labels, preserving control flow clarity. (2) The Function Call strategy infers variable types and retrieves missing variable information from binary files. Experimental results on the Humaneval-Decompile Benchmark demonstrate that ReF Decompile surpasses comparable baselines and achieves state-of-the-art (SOTA) performance of $61.43\%$.

cs.SE↗

arXiv2025

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding

The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenges in the next-token prediction posed by lengthy sequences of speech tokens. In this work, we introduce VADUSA, one of the first approaches to accelerate auto-regressive TTS through speculative decoding. Our results show that VADUSA not only significantly improves inference speed but also enhances performance by incorporating draft heads to predict future speech content auto-regressively. Furthermore, the inclusion of a tolerance mechanism during sampling accelerates inference without compromising quality. Our approach demonstrates strong generalization across large datasets and various types of speech tokens.

eess.AS↗

arXiv2024

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits

The Myers-Briggs Type Indicator (MBTI) is one of the most influential personality theories reflecting individual differences in thinking, feeling, and behaving. MBTI personality detection has garnered considerable research interest and has evolved significantly over the years. However, this task tends to be overly optimistic, as it currently does not align well with the natural distribution of population personality traits. Specifically, (1) the self-reported labels in existing datasets result in incorrect labeling issues, and (2) the hard labels fail to capture the full range of population personality distributions. In this paper, we optimize the task by constructing MBTIBench, the first manually annotated high-quality MBTI personality detection dataset with soft labels, under the guidance of psychologists. As for the first challenge, MBTIBench effectively solves the incorrect labeling issues, which account for 29.58% of the data. As for the second challenge, we estimate soft labels by deriving the polarity tendency of samples. The obtained soft labels confirm that there are more people with non-extreme personality traits. Experimental results not only highlight the polarized predictions and biases in LLMs as key directions for future research, but also confirm that soft labels can provide more benefits to other psychological tasks than hard labels. The code and data are available at https://github.com/Personality-NLP/MbtiBench.

cs.CL↗

arXiv2024

On some simple orbifold affine VOAs at non-admissible level arising from rank one 4D SCFTs

We study the representations of some simple affine vertex algebras at non-admissible level arising from rank one 4D SCFTs. In particular, we classify the irreducible highest weight modules of $L_{-2}(G_2)$ and $L_{-2}(B_3)$. It is known by the works of Adamović and Perše that these vertex algebras can be conformally embedded into $L_{-2}(D_4)$. We also compute the associated variety of $L_{-2}(G_2)$, and show that it is the orbifold of the associated variety of $L_{-2}(D_4)$ by the symmetric group of degree 3 which is the Dynkin diagram automorphism group of $D_4$. This provides a new interesting example of associated variety satisfying a number of conjectures in the context of orbifold vertex algebras.

math.RT↗

arXiv2024

SMT-Layout: A MaxSMT-based Approach Supporting Real-time Interaction of Real-world GUI Layout

Leveraging the flexible expressive ability of (Max)SMT and the powerful solving ability of SMT solvers, we propose a novel layout model named SMT-Layout. SMT-Layout is the first constraint-based layout model that can support real-time interaction for real-world GUI layout adapting to various screen sizes with only one specification. Previous works neglect the hierarchy information among widgets and thus cannot exploit the reasoning ability of solvers. For the first time, we introduce Boolean variables to encode the hierarchy relationship, boosting the reasoning ability of SMT solvers. The workflow is divided into two stages. At the development end, two novel preprocessing methods are proposed to simplify constraints and extract useful information in advance, easing the solving burden. After deploying constraints to the terminal end, SMT solvers are applied to solve constraints incrementally. Besides mainstream SMT solvers, a local search solver is customized to this scenario. Experiments show that SMT-Layout can support millisecond-level interaction for real-world layouts, even on devices with low computing power and rigorous memory limitations.

cs.LO↗

arXiv2024

Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

Camera-based 3D semantic scene completion (SSC) is pivotal for predicting complicated 3D layouts with limited 2D image observations. The existing mainstream solutions generally leverage temporal information by roughly stacking history frames to supplement the current frame, such straightforward temporal modeling inevitably diminishes valid clues and increases learning difficulty. To address this problem, we present HTCL, a novel Hierarchical Temporal Context Learning paradigm for improving camera-based semantic scene completion. The primary innovation of this work involves decomposing temporal context learning into two hierarchical steps: (a) cross-frame affinity measurement and (b) affinity-based dynamic refinement. Firstly, to separate critical relevant context from redundant information, we introduce the pattern affinity with scale-aware isolation and multiple independent learners for fine-grained contextual correspondence modeling. Subsequently, to dynamically compensate for incomplete observations, we adaptively refine the feature sampling locations based on initially identified locations with high affinity and their neighboring relevant regions. Our method ranks $1^{st}$ on the SemanticKITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU on the OpenOccupancy benchmark. Our code is available on https://github.com/Arlo0o/HTCL.

cs.CV↗

arXiv2024

Room-temperature non-volatile optical manipulation of polar order in a charge density wave

Utilizing ultrafast light-matter interaction to manipulate electronic states of quantum materials is an emerging area of research in condensed matter physics. It has significant implications for the development of future ultrafast electronic devices. However, the ability to induce long-lasting metastable electronic states in a fully reversible manner is a long-standing challenge.Here, by using ultrafast laser excitations, we demonstrate the capability to manipulate the electronic polar states in the charge-density-wavematerial EuTe4 in a non-volatile manner. The process is completely reversible and is achieved at room temperature with an all-optical approach. Each induced non-volatile state brings about modifications to the electrical resistance and second harmonic generation intensity. The results point to layer-specific phase inversion dynamics by which photoexcitation mediates the stacking polar order of the system. Our findings extend the scope of non-volatile all-optical control of electronic states to ambient conditions, and highlight a distinct role of layerdependent phase manipulation in quasi-two-dimensional systems with inherent sublayer stacking orders.

cond-mat.str-el↗

arXiv2024

High Pressure Structural Behavior of Silicon Telluride (Si2Te3) Nanoplates

The high-pressure behavior of silicon telluride (Si2Te3), a two-dimensional (2D) layered material, was investigated using synchrotron X-ray powder diffraction in a diamond anvil cell to 11.5 GPa coupled with first-principles theory. Si2Te3 undergoes a phase transition at < 1 GPa from a trigonal to a hexagonal crystal structure. At higher pressures (> 8.5 GPa), X-ray diffraction showed the appearance of new peaks possibly coincident with a new phase transition, though we suspect Si2Te3 retains a hexagonal structure. Density functional theory calculations of the band structure reveal metallization above 9.1 GPa consistent with previous measurements of the Raman spectra and disappearance of color and transparency at pressure. The theoretical Raman spectra reproduce the prominent features of the experiment, though a deeper analysis suggests that the orientation of Si dimers dramatically influences the vibrational response. Given the complex structure of Si2Te3, simulation of the resulting high-pressure phase is complicated by disordered vacancies and the initial orientations of Si-Si dimers in the crushed layered phase.

cond-mat.mtrl-sci↗

arXiv2024

Connecting Dreams with Visual Brainstorming Instruction

Recent breakthroughs in understanding the human brain have revealed its impressive ability to efficiently process and interpret human thoughts, opening up possibilities for intervening in brain signals. In this paper, we aim to develop a straightforward framework that uses other modalities, such as natural language, to translate the original dreamland. We present DreamConnect, employing a dual-stream diffusion framework to manipulate visually stimulated brain signals. By integrating an asynchronous diffusion strategy, our framework establishes an effective interface with human dreams, progressively refining their final imagery synthesis. Through extensive experiments, we demonstrate the method ability to accurately instruct human brain signals with high fidelity. Our project will be publicly available on https://github.com/Sys-Nexus/DreamConnect

cs.HC↗