arXiv subjects

Sheng Li

Publications and source records attributed to Sheng Li.

At least 73 records · Page 4Linked to original sources

arXiv2026

Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models

Despite their prominent performance on tasks such as ROI classification and segmentation, many pathology foundation models remain constrained by a specific input size e.g. 224 x 224, creating substantial inefficiencies when applied to whole-slide images (WSIs), which span thousands of resolutions. A naive strategy is to either enlarge inputs or downsample the WSIs. However, enlarging inputs results in prohibitive GPU memory consumption, while downsampling alters the microns-per-pixel resolution and obscures critical morphological details. To overcome these limitations, we propose an space- and time- efficient inference strategy that sparsifies attention using spatially aware neighboring blocks and filters out non-informative tokens through global attention scores. This design substantially reduces GPU memory and runtime during high-resolution WSI inference while preserving and even improving the downstream performance, enabling inference at higher resolutions under the same GPU budget. The experimental results show that our method can achieves up to an 7.67% improvement in the ROI classification and compatible results in segmentation.

cs.CV↗

arXiv2025

Observation of robust one-dimensional edge channels in a three-dimensional quantum spin Hall insulator

Topologically protected edge channels show prospects for quantum devices. They have been found experimentally in two-dimensional (2D) quantum spin Hall insulators (QSHIs), weak topological insulators and higher-order topological insulators (HOTIs), but the number of materials realizing these topologies is still quite limited. Here, we provide evidence for topological edge states within a novel topology named three-dimensional (3D) QSHIs. Its topology originates solely from a nonzero $S_z$ spin Chern number for each $k_z$ plane of the crystal and is realized in bulk $α$-Bi$_4$I$_4$ with trivial symmetry indicators, as we show by density functional theory calculations. We experimentally observe the related edge states at each type of monolayer and bilayer step of this material by scanning tunneling microscopy. Consistently, the edge states are neither interrupted, nor backscattered by defects at the step edges corroborating their helical character as expected from the nontrivial topology. Furthermore, two individual edge channels are directly observed at bilayer steps without visible interaction gap opening, demonstrating the robustness of these edge modes against vertical stacking. Our results establish $α$-Bi$_4$I$_4$ as the first material realization of a 3D QSHI whose definition goes beyond the scope of topological symmetry indicators, and provide a pathway for realizing nearly-quantized spin Hall conductivity per unit cell in a bulk crystal.

cond-mat.mes-hall↗

arXiv2025

SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models

We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, designed to assess their voice understanding ability. Moving beyond popular voice understanding metrics such as word error rate (WER), SIQ examines LLM Voice across three cognitive levels motivated by Bloom's Taxonomy: (1) Remembering (i.e., WER for verbatim accuracy); (2) Understanding (i.e., similarity of LLM's interpretations); and (3) Application (i.e., QA accuracy for simulating downstream tasks). We demonstrate that SIQ not only quantifies voice understanding abilities but also provides unified comparisons between cascaded methods (e.g., ASR LLM) and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM Voice. Our framework represents a first-of-its-kind intelligence examination that bridges cognitive principles with voice-oriented benchmarks, while exposing overlooked challenges in multi-modal training. Our code and data will be open source to encourage future studies.

cs.CL↗

arXiv2025

VibraVerse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning

Understanding the physical world requires perceptual models grounded in physical laws rather than mere statistical correlations. However, existing multimodal learning frameworks, focused on vision and language, lack physical consistency and overlook the intrinsic causal relationships among an object's geometry, material, vibration modes, and the sounds it produces. We introduce VibraVerse, a large-scale geometry-acoustics alignment dataset that explicitly bridges the causal chain from 3D geometry -> physical attributes -> modal parameters -> acoustic signals. Each 3D model has explicit physical properties (density, Young's modulus, Poisson's ratio) and volumetric geometry, from which modal eigenfrequencies and eigenvectors are computed for impact sound synthesis under controlled excitations. To establish this coherence, we introduce CLASP, a contrastive learning framework for cross-modal alignment that preserves the causal correspondence between an object's physical structure and its acoustic response. This framework enforces physically consistent alignment across modalities, ensuring that every sample is coherent, traceable to the governing equations, and embedded within a unified representation space spanning shape, image, and sound. Built upon VibraVerse, we define a suite of benchmark tasks for geometry-to-sound prediction, sound-guided shape reconstruction, and cross-modal representation learning. Extensive validations on these tasks demonstrate that models trained on VibraVerse exhibit superior accuracy, interpretability, and generalization across modalities. These results establish VibraVerse as a benchmark for physically consistent and causally interpretable multimodal learning, providing a foundation for sound-guided embodied perception and a deeper understanding of the physical world. The dataset will be open-sourced.

cs.AI↗

arXiv2025

Increase of critical current density in FeSe superconductor by strain effect

Conventional $J_c$-enhancement methods like doping and irradiation often introduce extrinsic elements or defects, altering intrinsic properties. Here, we report a significant $J_c$ enhancement in FeSe single crystals through compressive strain applied using a glass-fiber-reinforced plastic substrate with anisotropic thermal contraction during cooling. Under zero field at 2 K, $J_{\text{c}}$ increases by a factor of $\sim$4 from $\sim 2.3 \times 10^{4}$ to $\sim 8.7 \times 10^{4}$ A cm$^{-2}$; at 5 T, it achieves an order-of-magnitude enhancement, rising from $\sim 1.0 \times 10^{3}$ to $\sim 1.0 \times 10^{4}$ A cm$^{-2}$. Analysis based on the Dew-Hughes model of the $f_{\text{p}}$(h) relationship shows that strain strengthens vortex pinning, and shifts the pinning mechanism from point-like pinning to combined point and surface pinnings. This work offers an effective method to enhance FeSe's current-carrying limitation, deepens understanding of iron-based superconductors' pinning mechanisms, and highlights strain engineering's potential for optimizing superconducting performance.

cond-mat.supr-con↗

arXiv2025

SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editing

The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep learning-based methods rely on training with hand-crafted noise simulation layers, which inherently limit their generalization to unforeseen distortions. In this work, we propose $\textbf{SimuFreeMark}$, a noise-$\underline{\text{simu}}$lation-$\underline{\text{free}}$ water$\underline{\text{mark}}$ing framework that circumvents this limitation by exploiting the inherent stability of image low-frequency components. We first systematically establish that low-frequency components exhibit significant robustness against a wide range of attacks. Building on this foundation, SimuFreeMark embeds watermarks directly into the deep feature space of the low-frequency components, leveraging a pre-trained variational autoencoder (VAE) to bind the watermark with structurally stable image representations. This design completely eliminates the need for noise simulation during training. Extensive experiments demonstrate that SimuFreeMark outperforms state-of-the-art methods across a wide range of conventional and semantic attacks, while maintaining superior visual quality.

cs.CV↗

arXiv2025

Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination

Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.

cs.GR↗

arXiv2025

The Photographer Eye: Teaching Multimodal Large Language Models to Understand Image Aesthetics like Photographers

While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky. Photographer and curator, Szarkowski insightfully revealed one of the notable gaps between general and aesthetic visual understanding: while the former focuses on identifying the factual element in an image (sky), the latter transcends such object identification, viewing it instead as an aesthetic component--a pure color block (blue). Such fundamental distinctions between general (detection, localization, etc.) and aesthetic (color, lighting, composition, etc.) visual understanding present a significant challenge for Multimodal Large Language Models (MLLMs). Although some recent works have made initial explorations, they are often limited to general and basic aesthetic commonsense. As a result, they frequently fall short in real-world scenarios (Fig. 1), which require extensive expertise--including photographic techniques, photo pre/post-processing knowledge, and more, to provide a detailed analysis and description. To fundamentally enhance the aesthetics understanding of MLLMs, we first introduce a novel dataset, PhotoCritique, derived from extensive discussions among professional photographers and enthusiasts, and characterized by the large scale, expertise, and diversity. Then, to better learn visual aesthetics from PhotoCritique, we furthur propose a novel model, PhotoEye, featuring a languageguided multi-view vision fusion mechanism to understand image aesthetics from multiple perspectives. Finally, we present a novel benchmark, PhotoBench, a comprehensive and professional benchmark for aesthetic visual understanding. On existing benchmarks and PhotoBench, our model demonstrates clear advantages over existing models.

cs.CV↗

arXiv2025

NRRS: Neural Russian Roulette and Splitting

We propose a novel framework for Russian Roulette and Splitting (RRS) tailored to wavefront path tracing, a highly parallel rendering architecture that processes path states in batched, stage-wise execution for efficient GPU utilization. Traditional RRS methods, with unpredictable path counts, are fundamentally incompatible with wavefront's preallocated memory and scheduling requirements. To resolve this, we introduce a normalized RRS formulation with a bounded path count, enabling stable and memory-efficient execution. Furthermore, we pioneer the use of neural networks to learn RRS factors, presenting two models: NRRS and AID-NRRS. At a high level, both feature a carefully designed RRSNet that explicitly incorporates RRS normalization, with only subtle differences in their implementation. To balance computational cost and inference accuracy, we introduce Mix-Depth, a path-depth-aware mechanism that adaptively regulates neural evaluation, further improving efficiency. Extensive experiments demonstrate that our method outperforms traditional heuristics and recent RRS techniques in both rendering quality and performance across a variety of complex scenes.

cs.GR↗

arXiv2025

Mobile Gamer Lifetime Value Prediction via Objective Decomposition and Reconstruction

For Internet platforms operating real-time bidding (RTB) advertising service, a comprehensive understanding of user lifetime value (LTV) plays a pivotal role in optimizing advertisement allocation efficiency and maximizing the return on investment (ROI) for advertisement sponsors, thereby facilitating growth of commercialization revenue for the platform. However, the inherent complexity of user LTV distributions induces significant challenges in accurate LTV prediction. Existing state-of-the-art works, which primarily focus on directly learning the LTV distributions through well-designed loss functions, achieve limited success due to their vulnerability to outliers. In this paper, we proposed a novel LTV prediction method to address distribution challenges through an objective decomposition and reconstruction framework. Briefly speaking, based on the in-app purchase characteristics of mobile gamers, our model was designed to first predict the number of transactions at specific prices and then calculate the total payment amount from these intermediate predictions. Our proposed model was evaluated through experiments on real-world industrial dataset, and deployed on the TapTap RTB advertising system for online A/B testing along with the state-of-the-art ZILN model.

cs.IR↗

arXiv2025

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify context management as the central bottleneck -- extended histories cause agents to overlook critical evidence or become distracted by irrelevant information, thus failing to replan or reflect from previous mistakes. To address this, we propose COMPASS (Context-Organized Multi-Agent Planning and Strategy System), a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components: (1) a Main Agent that performs reasoning and tool use, (2) a Meta-Thinker that monitors progress and issues strategic interventions, and (3) a Context Manager that maintains concise, relevant progress briefs for different reasoning stages. Across three challenging benchmarks -- GAIA, BrowseComp, and Humanity's Last Exam -- COMPASS improves accuracy by up to 20% relative to both single- and multi-agent baselines. We further introduce a test-time scaling extension that elevates performance to match established DeepResearch agents, and a post-training pipeline that delegates context management to smaller models for enhanced efficiency.

cs.AI↗

arXiv2025

BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling

Sampling multiple responses is a common way to improve LLM output quality, but it comes at the cost of additional computation. The key challenge is deciding when to stop generating new samples to balance accuracy gains against efficiency. To address this, we introduce BEACON (Bayesian Efficient Adaptive Criterion for Optimal N-stopping), a principled adaptive sampling framework grounded in Sequential Search with Bayesian Learning. BEACON sequentially generates responses from the policy LLM, updates posterior belief over reward distributions in real time without further training, and determines when to stop by weighing expected gains against computational cost. Sampling terminates once the marginal utility of further exploration no longer justifies the expense. We establish both theoretical optimality guarantees and practical tractability, and show empirically that BEACON reduces average sampling by up to 80% while maintaining response quality. We further demonstrate BEACON's utility for cost-efficient preference data generation and outline practical extensions, offering actionable insights for future researchers.

cs.LG↗

arXiv2025

Bridging the Gap: Enhancing Gaze-Performance Link in Children with ASD through Dual-Level Visual Guidance in MR-DMT

Autism Spectrum Disorder (ASD) is marked by action imitation deficits stemming from visuomotor integration impairments, posing challenges to imitation-based learning, such as dance movement therapy in mixed reality (MR-DMT). Previous gaze-guiding interventions in ASD have mainly focused on optimizing gaze in isolation, neglecting the crucial "gaze-performance link". This study investigates enhancing this link in MR-DMT for children with ASD. Initially, we experimentally confirmed the weak link: longer gaze durations didn't translate to better performance. Then, we proposed and validated a novel dual-level visual guidance system that operates on both perceptual and transformational levels: not only directing attention to task-relevant areas but also explicitly scaffolding the translation from gaze perception to performance execution. Our results demonstrate its effectiveness in boosting the gaze-performance link, laying key foundations for more precisely tailored and effective MR-DMT interventions for ASD.

cs.HC↗

arXiv2025

TimeGazer: Temporal Modeling of Predictive Gaze Stabilization for AR Interaction

Gaze stabilization is critical for enabling fluid, accurate, and efficient interaction in immersive augmented reality (AR) environments, particularly during task-oriented visual behaviors. However, fixation sequences captured in active gaze tasks often exhibit irregular dispersion and systematic deviations from target locations, a variability primarily caused by the combined effects of human oculomotor physiology, insufficient AR headset tracking and calibration accuracy, and environmental disturbances, undermining interaction performance and visual engagement. To address this issue, we propose TimeGazer, which reformulates gaze stabilization as a sequence-to-sequence temporal regression problem, predicting idealized fixation trajectories for the target-fixation phase from historical gaze dynamics in the search phase. We present a synthetic data generation and blending strategy that produces spatially concentrated, target-centered fixation references aligned with task objectives, substantially enriching the training space and enhancing model generalization. We train and evaluate TimeGazer on a hybrid dataset of real and augmented gaze sequences collected via Microsoft HoloLens 2 from 54 participants across multiple prediction horizons. Through the user study, statistical results demonstrate that TimeGazer significantly improves interaction accuracy and reduces completion time, confirming that temporal modeling of predictive gaze stabilization can strengthen attentional consistency and responsiveness in task-driven AR interaction. These findings highlight the broader potential of TimeGazer for advancing adaptive gaze-based interfaces and temporal modeling research in immersive systems.

cs.HC↗

arXiv2025

Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement

Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details of the reference speech. To this end, we propose a novel emotional TTS method that enables fine-grained phoneme-level emotion embedding prediction while disentangling intrinsic attributes of the reference speech. The proposed method employs a style disentanglement method to guide two feature extractors, reducing mutual information between timbre and emotion features, and effectively separating distinct style components from the reference speech. Experimental results demonstrate that our method outperforms baseline TTS systems in generating natural and emotionally rich speech. This work highlights the potential of disentangled and fine-grained representations in advancing the quality and flexibility of emotional TTS systems.

cs.SD↗

arXiv2025

The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning

Back in the early 20th century, a horse named Hans appeared to perform arithmetic and other intellectual tasks during exhibitions in Germany, while it actually relied solely on involuntary cues in the body language from the human trainer. Modern machine learning models are no different. These models are known to be sensitive to spurious correlations between non-essential features of the inputs (e.g., background, texture, and secondary objects) and the corresponding labels. Such features and their correlations with the labels are known as "spurious" because they tend to change with shifts in real-world data distributions, which can negatively impact the model's generalization and robustness. In this paper, we provide a comprehensive survey of this emerging issue, along with a fine-grained taxonomy of existing state-of-the-art methods for addressing spurious correlations in machine learning models. Additionally, we summarize existing datasets, benchmarks, and metrics to facilitate future research. The paper concludes with a discussion of the broader impacts, the recent advancements, and future challenges in the era of generative AI, aiming to provide valuable insights for researchers in the related domains of the machine learning community.

cs.LG↗

arXiv2025

Memory in Large Language Models: Mechanisms, Evaluation and Evolution

Under a unified operational definition, we define LLM memory as a persistent state written during pretraining, finetuning, or inference that can later be addressed and that stably influences outputs. We propose a four-part taxonomy (parametric, contextual, external, procedural/episodic) and a memory quadruple (location, persistence, write/access path, controllability). We link mechanism, evaluation, and governance via the chain write -> read -> inhibit/update. To avoid distorted comparisons across heterogeneous setups, we adopt a three-setting protocol (parametric only, offline retrieval, online retrieval) that decouples capability from information availability on the same data and timeline. On this basis we build a layered evaluation: parametric (closed-book recall, edit differential, memorization/privacy), contextual (position curves and the mid-sequence drop), external (answer correctness vs snippet attribution/faithfulness), and procedural/episodic (cross-session consistency and timeline replay, E MARS+). The framework integrates temporal governance and leakage auditing (freshness hits, outdated answers, refusal slices) and uncertainty reporting via inter-rater agreement plus paired tests with multiple-comparison correction. For updating and forgetting, we present DMM Gov: coordinating DAPT/TAPT, PEFT, model editing (ROME, MEND, MEMIT, SERAC), and RAG to form an auditable loop covering admission thresholds, rollout, monitoring, rollback, and change audits, with specs for timeliness, conflict handling, and long-horizon consistency. Finally, we give four testable propositions: minimum identifiability; a minimal evaluation card; causally constrained editing with verifiable forgetting; and when retrieval with small-window replay outperforms ultra-long-context reading. This yields a reproducible, comparable, and governable coordinate system for research and deployment.

cs.AI↗

arXiv2025

Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models

Can large multimodal models have a human-like ability for emotional and social reasoning, and if so, how does it work? Recent research has discovered emergent theory-of-mind (ToM) reasoning capabilities in large language models (LLMs). LLMs can reason about people's mental states by solving various text-based ToM tasks that ask questions about the actors' ToM (e.g., human belief, desire, intention). However, human reasoning in the wild is often grounded in dynamic scenes across time. Thus, we consider videos a new medium for examining spatio-temporal ToM reasoning ability. Specifically, we ask explicit probing questions about videos with abundant social and emotional reasoning content. We develop a pipeline for multimodal LLM for ToM reasoning using video and text. We also enable explicit ToM reasoning by retrieving key frames for answering a ToM question, which reveals how multimodal LLMs reason about ToM.

cs.CV↗