arXiv subjects

Yifan Gao

Publications and source records attributed to Yifan Gao.

At least 19 recordsLinked to original sources

arXiv2026

HearInContext: A Benchmark for Implicit Context in Speech Recognition

Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin-English benchmark that pairs shared synthetic speech with assistant replies supporting different interpretations. The benchmark comprises 3,764 semantic test cases built around homophones. Implicit contexts exclude candidate words; explicit contexts name the target. No-context and unrelated-context controls measure the benefit of relevant history and sensitivity to irrelevant history. Context-capable models benefit from implicit cues but achieve higher target recall with explicit hints. Fine-tuning Qwen3-ASR-1.7B improves implicit-context target recall by 11.4 percentage points in both Mandarin and English, while absolute CER/WER changes on AISHELL-1 and LibriSpeech remain below 0.1 percentage points. Gains extend to explicit conditions excluded from fine-tuning and to Mandarin hotword recognition on real recordings. Code and data are available at https://github.com/OPPO-Mente-Lab/HearInContext

cs.CL↗

arXiv2026

MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning

Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers. To address this gap, we introduce MultivationBench, a benchmark designed to rigorously evaluate multimodal motivation reasoning within story-driven visual narratives. The benchmark builds upon established psychological frameworks - Maslow's hierarchy and Reiss's basic desires - and requires models to integrate accumulated multimodal context to infer evolving motivations. Results indicate that MultivationBench presents a significant challenge: all tested models struggle to maintain consistent motivation reasoning across sequential contexts, revealing a critical disconnect between static recognition capabilities and the dynamic reasoning essential for human-like social understanding.

cs.AI↗

arXiv2026

FermatSyn: SAM2-Enhanced Bidirectional Mamba with Isotropic Spiral Scanning for Multi-Modal Medical Image Synthesis

Multi-modal medical image synthesis is pivotal for alleviating clinical data scarcity, yet existing methods fail to reconcile global anatomical consistency with high-fidelity local detail. We propose FermatSyn, which addresses three persistent limitations: (1) SAM2-based Prior Encoder that injects domain-aware anatomical knowledge via LoRA$^{+}$ efficient fine-tuning of a frozen SAM2 Vision Transformer; (2) Hierarchical Residual Downsampling Module (HRDM) coupled with a Cross-scale Integration Network (CIN) that preserves high-frequency lesion details and adaptively fuses global--local representations; and (3) continuity constrained Fermat Spiral Scanning strategy within a Bidirectional Fermat Scan Mamba (BFS-Mamba), constructing an approximately isotropic receptive field that substantially reduces the directional bias of raster or spiral serialization. Experiments on SynthRAD2023, BraTS2019, BraTS-MEN, and BraTS-MET show FermatSyn surpasses state-of-the-art methods in PSNR, SSIM, FID, and 3D structural consistency. Downstream segmentation on synthesized images yields no significant difference from real-image training ($p{>}0.05$), confirming clinical utility. Code is available at https://github.com/gatina-yone/FermatSyn.

eess.IV↗

arXiv2026

DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation

Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.g., sCM) favors diversity, whereas distribution-level distillation (e.g., DMD) favors quality. Targeting extreme two-step video generation, we introduce DUET, which reconciles the two paradigms through a noise-level duet of experts: an sCM expert takes the high-noise step to lay out diverse structure, and a DMD expert takes the low-noise step to refine appearance detail. Since the two experts are trained independently with their native objectives, DUET sidesteps the optimization difficulties of loss-level combinations and delivers quality and diversity jointly rather than trading one for the other. We further identify the relay interface and the high-noise stage as the remaining bottlenecks, and address them with RL-guided expert adaptation, yielding DUET+. With the Wan2.1-T2V-1.3B backbone, DUET lifts the two-step quality of sCM close to the level of DMD while retaining nearly all of its structural diversity---about twice that of DMD---and DUET+ further improves overall quality while preserving this diversity advantage. Together, these results establish noise-level expert specialization as a simple, effective paradigm for reconciling diversity and quality in two-step video generation.

cs.CV↗

arXiv2026

Hidden-Domain Routing for All-Type Audio Deepfake Detection

All-type audio deepfake detection requires authenticity decisions across speech, environmental sound, singing voice, and music, while the audio type is unavailable at inference time. In AT-ADD Track2, this setting creates a hidden audio-domain condition: the binary real/fake label is shared across domains, but representation structure and detector-score behavior vary with audio type. We present a closed-condition routed system that first recovers the hidden audio domain and then interprets detector scores within the selected branch. The AudioType-BEATs-6s Router estimates audio type from a 6-second window; speech inputs are handled by the Speech-XLSR Expert, while sound, singing, and music rely on EAT-based general-audio experts with branch-local score interpretation. Development-set representation analysis, router-family comparisons, and component results show audio-domain separation and complementary detector strengths across audio types. On the official AT-ADD Track2 final evaluation, the system achieves 96.10% Track2 Macro-F1 and ranks first on the final leaderboard, with type-wise Macro-F1 scores of 88.07%, 98.18%, 99.07%, and 99.08% for speech, sound, singing, and music, respectively. These results support recovering the hidden audio domain before interpreting detector scores in all-type audio deepfake detection.

cs.SD↗

arXiv2026

Organizing Principles for Moiré Quantum Matter

Moiré flat bands in van der Waals bilayers are usually discussed through a small set of mechanisms associated with the $Γ$ and $K$ valleys of hexagonal crystals, and more recently with $M$-valleys systems. Here we show that this view is incomplete. The momentum-space location and effective local orbital character of the monolayer's band edge, in conjunction with the moiré symmetry and the symmetry representations of the resulting bands, provide a general set of organizing variables for the emergent low-energy moiré Hamiltonian. Applying fully relaxed first-principles calculations, band unfolding and symmetry-representation analysis to more than 600 commensurate twisted bilayers spanning all 2D lattice classes, we identify several routes to moiré quantum matter beyond the conventional single-orbital paradigm. The resulting flat bands realize trigonal, honeycomb, square, checkerboard and kagome-like Hubbard models with single-orbital, multi-orbital and multi-site Hilbert spaces; spin-orbit-coupled multi-orbital flat bands exhibit symmetry-indicated topology beyond the conventional $K$-valley setting; and nonsymmorphic moiré symmetries enforce semimetallic flat-band connectivity. Analogous quasi-one-dimensional flat-band structures are found in $M$-valley hexagonal systems and $X$-valley square or rectangular systems resulting from emergent momentum-space nonsymmorphic symmetries. Separately, coupled multi-valley manifolds with kagome-like connectivity are identified in several systems whose parent band edges lie at non-high-symmetry points. These results establish a valley-orbital-symmetry framework for connecting parent-material electronic structure to emergent moiré Hamiltonians relevant to correlated, topological and symmetry-enforced moiré phases.

cond-mat.mtrl-sci↗

arXiv2026

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when. In practice, prompt pools are often static or only weakly coupled to policy progress, so uniform sampling fails to track the moving capability frontier and wastes rollouts on regions that are already solved or still unreachable. Prior methods improve efficiency via filtering, curricula, adaptive rollout allocation, or teacher guidance, but they often assume a fixed pool, which does not support stable on-policy pool growth, or they introduce additional teacher cost and latency. In this work, we propose HeaPA (Heap Sampling and On-Policy Query Augmentation), which maintains a bounded, evolving pool, tracks the frontier with heap-based boundary sampling, grows the pool via on-policy augmentation under lightweight asynchronous validation, and stabilizes correlated queries via topology-aware pool statistics re-estimation and controlled reinsertion. Across two training corpora, two training recipes, and seven benchmarks, HeaPA consistently improves accuracy and reaches target performance with fewer computations at comparable wall-clock time. Analyses attribute the gains to frontier-focused sampling and on-policy pool growth, with more pronounced improvements at mid-to-large model scales. Our training code is publicly available at https://github.com/horizon-llm/HeaPA.

cs.LG↗

arXiv2026

Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants

Conversational shopping assistants now serve hundreds of millions of customers, yet no existing benchmark jointly evaluates the open-ended multi-turn reasoning, domain expertise, and criterion-level quality that real shopping conversations demand. Shopping reasoning is unique among language model applications. Unlike factual question answering or verifiable code generation, it requires balancing subjective preferences, budget constraints, and cross-product trade-offs across multi-turn dialogue, capabilities absent from previous e-commerce and general-purpose benchmarks. We introduce the Shopping Reasoning Bench, an expert-authored benchmark of 525 missions (232 single-turn, 293 multi-turn) with 10863 importance-weighted binary rubrics authored by retail domain experts. These criteria are organized under a taxonomy of five reasoning categories and fifteen subcategories covering diverse demands such as preference refinement, trade-off analysis, and compatibility assessment. An evaluation of nine models across three families (GPT, Claude, Gemini) shows that pass rates reach only 57--77% overall. On multi-turn missions, all models score 13--29 points lower on optional above-and-beyond criteria than on required ones, and performance degrades 4--18 points as conversations progress. These gaps show that current models handle basic shopping assistance but fall short of expert-level advice, making Shopping Reasoning Bench a challenging testbed for future shopping assistant development.

cs.CL↗

arXiv2026

LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data

Type 2 Diabetes (T2D) poses an increasing global health threat, demanding effective glycemic assessment to support personalized and improved diabetes care. Wearable sensors such as continuous glucose monitors (CGM) and fitness trackers offer many valuable insights for glycemic assessment. However, effectively analyzing these data requires integration with essential individual-level context. Existing methods are often based on traditional machine learning (ML) and rely primarily on historical blood glucose measurements and overlook personalized information, which limits their performance across diverse diabetes populations. Recent advances in large language models (LLMs) have demonstrated their ability to integrate diverse data modalities while modeling sequential dependencies, motivating the exploration of their potential for personalized glycemic assessment. In this paper, we propose GlyLLM, an LLM-powered framework for modeling CGM-based glycemic dynamics through the integration of wearable sensor data and structured metadata. GlyLLM can leverage the extensive prior knowledge of pre-trained LLMs and achieve sensor-text semantic abstraction at decision time. Experiments on two related tasks on the AI-READI dataset demonstrate that our model outperforms traditional ML methods by an average of 13.66\% in Root Mean Squared Error (RMSE) for glucose forecasting and 13.08\% in Area Under the Receiver Operating Characteristic (AUROC) for diabetes categorization. Additionally, our ablation study shows that diabetes surveys and biometric tests are more critical than other health information for glycemic assessment. Our work presents a promising step toward harnessing the power of LLMs to advance personalized glycemic assessment in T2D care.

cs.LG↗

arXiv2026

AtlasGS: Brain MRI Spatial Resolution Harmonization With Shared Gaussian Geometry

Splatting (GS)-based shared geometry framework adopts a two-stage training strategy, in which an explicit, subject-specific Gaussian scaffold encoding anatomical geometry is first learned from the isotropic structural scan and then reused to fit appearance for target modalities acquired with sparse slices. Experiments on the UK Biobank, GBM, and ABCD datasets for through-plane super-resolution across multiple modalities (T2-weighted, FLAIR, DWI, ASL), degradation factors ($\times 3$, $\times 5$, $\times 7$), and pathological abnormalities (glioblastoma) demonstrate state-of-the-art reconstruction fidelity. The shared Gaussian geometry enables arbitrary-view generation for target modalities with strong structural consistency and further shows potential for self-supervised in-plane super-resolution. This work establishes explicit geometry-guided representations as a novel, flexible, and interpretable pathway toward retrospective multi-contrast MRI harmonization and reliable clinical reference construction. Source code is available at: https://github.com/yfgao76/AtlasGS

eess.IV↗

arXiv2026

Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges

We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools, prompt engineering, multimodal learning, and ethical considerations. We integrate findings from interdisciplinary studies utilizing diverse data sources such as social media posts, electronic medical records, and multimodal inputs to enable early detection of depression, suicide risk assessment, personalized therapy support, and psychoeducational content generation. Our review highlights advancements in LLM models and annotation strategies that enhance interpretability and clinical relevance, while we also emphasize the critical role of prompt engineering for domain adaptation. We also discuss emerging multimodal fusion techniques integrating text, speech, and sensor data for improved mental health diagnosis and monitoring. Finally, we address ongoing ethical, sociotechnical, and regulatory challenges, and advocate frameworks to ensure safe, equitable, and accountable deployment of LLMs in real-world mental health care.

cs.AI↗

arXiv2026

Odd spin symmetry and anisotropy switching in p-wave magnet CeNiAsO

Odd-parity magnets, complementary to altermagnets, exhibit unique properties such as high efficiency in charge-spin conversion and compatibility with conventional superconductivity, of critical importance in the pursuit of energy-efficient spintronics and topological superconductors for quantum computation. For even-parity d-wave and g-wave altermagnets, the magnetic structure, spin-split band structure and physical properties are currently under intensive study. On the contrary, while hundreds of odd-parity magnets and the promising properties have been predicted in theory, experimental studies are scarce. Specifically, the magnetic structure and transport properties of candidates NiI2 and Ga3Ru4Al12 have been reported, yet the characteristic band structure and particularly the odd-parity spin symmetry remain elusive. Here we demonstrate experimentally the deterministic p-wave spin symmetry and resistance anisotropy switching for the prototype odd-parity magnet, CeNiAsO. Angle-resolved photoemission spectroscopy (ARPES) reveals two cleaved terminations with distinct surface band structure. By compensating the polar surface, we achieve intrinsic bulk band structure, for which the spin splitting can be well described by the p-wave magnetic structure through first-principles calculation. The bulk spin polarization measured by spin-resolved ARPES exhibits symmetry with only one degenerate plane, fingerprint of p-wave magnetism. We further demonstrate giant resistance anisotropy and switching between high-resistance and low-resistance states through modest field-induced domain selection, highlighting its potential for antiferromagnetic spin memory devices. The structural similarity between CeNiAsO and 1111-type Fe-based superconductors stimulates further exploration on the interplay between p-wave magnetism, superconductivity and band topology.

cond-mat.str-el↗

arXiv2026

Percolation of discrete GFF in dimension two II. Connectivity properties of two-sided level sets

We study percolation of two-sided level sets for the discrete Gaussian free field (DGFF) in 2D. For a DGFF $φ$ defined in a box $B_N$ with side length $N$, for $C$ large enough, there exist low crossings in the set of vertices $z$ where $|φ(z)|\le C \sqrt{\log \log N}$, with probability tending to $1$ as $N \to \infty$, while the average and the maximum of $φ$ are of order $\sqrt{\log N}$ and $\log N$, respectively. As a consequence, we also obtain connectivity properties of the set of thick points of a random walk. We rely on an isomorphism between the DGFF and the random walk loop soup (RWLS) with critical intensity $α=1/2$, and further extend our study to the occupation field of the RWLS for all subcritical intensities $α\in(0,1/2)$. For the RWLS in $B_N$, we show that for $λ$ large enough, there exist low crossings of $B_N$, remaining below $λ$, even though the average occupation time is of order $\log N$. Our results thus uncover a non-trivial phase-transition for this highly-dependent percolation model. For both the DGFF and the occupation field of the RWLS, we further show that such low crossings can be found in the "carpet" of the RWLS - the set of vertices which are not in the interior of any cluster of loops. This work is the second part of a series of two papers. It relies heavily on tools and techniques developed for the RWLS in the first part, especially surgery arguments on loops, which were made possible by a separation result in the RWLS. This allowed us, in that companion paper, to derive several useful properties such as quasi-multiplicativity, and obtain a precise upper bound for the probability that two large connected components of loops "almost touch", which is instrumental here.

math.PR↗

arXiv2026

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents

Large Language Model (LLM) empowered agents have recently emerged as advanced paradigms that exhibit impressive capabilities in a wide range of domains and tasks. Despite their potential, current LLM agents often adopt a one-size-fits-all approach, lacking the flexibility to respond to users' varying needs and preferences. This limitation motivates us to develop PersonaAgent, the first personalized LLM agent framework designed to address versatile personalization tasks. Specifically, PersonaAgent integrates two complementary components - a personalized memory module that includes episodic and semantic memory mechanisms; a personalized action module that enables the agent to perform tool actions tailored to the user. At the core, the persona (defined as unique system prompt for each user) functions as an intermediary: it leverages insights from personalized memory to control agent actions, while the outcomes of these actions in turn refine the memory. Based on the framework, we propose a test-time user-preference alignment strategy that simulate the latest n interactions to optimize the persona prompt, ensuring real-time user preference alignment through textual loss feedback between simulated and ground-truth responses. Experimental evaluations demonstrate that PersonaAgent significantly outperforms other baseline methods by not only personalizing the action space effectively but also scaling during test-time real-world applications. These results underscore the feasibility and potential of our approach in delivering tailored, dynamic user experiences.

cs.AI↗

arXiv2026

BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery

Many recent medical VLM and agent studies are benchmarked on 2D images or comparatively short tool-calling exchanges, whereas real MRI analysis typically demands long, interdependent pipelines that operate on 3D/4D volumetric data. Under these conditions, reactive tool-calling agents are prone to cascading breakdowns triggered by faulty intermediate references, mismatched tool arguments, and limited control over cross-step dependencies. To address this, we introduce BCER (Brain-Cerebellum-Extremity-Reflector), a controller architecture aimed at dependable long-horizon MRI workflow execution. BCER decouples high-level planning from execution and provides bounded local recovery. We assess BCER on a multi-organ MRI benchmark covering brain, prostate, and cardiac tasks with both short- and long-chain workflows, using matched task contracts across controller variants and several backbone models. Relative to reactive baselines, BCER yields consistent improvements in end-to-end execution, with the most pronounced gains observed on long-chain workflows. BCER additionally enables auditability by maintaining explicit links between final outputs and intermediate artifacts and measurements. Code and benchmark are released at https://github.com/Albertlongzi/BCER.

eess.IV↗

arXiv2026

END: Early Noise Dropping for Efficient and Effective Context Denoising

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, they are often distracted by irrelevant or noisy context in input sequences that degrades output quality. This problem affects both long- and short-context scenarios, such as retrieval-augmented generation, table question-answering, and in-context learning. We reveal that LLMs can implicitly identify whether input sequences contain useful information at early layers, prior to token generation. Leveraging this insight, we introduce Early Noise Dropping (\textsc{END}), a novel approach to mitigate this issue without requiring fine-tuning the LLMs. \textsc{END} segments input sequences into chunks and employs a linear prober on the early layers of LLMs to differentiate between informative and noisy chunks. By discarding noisy chunks early in the process, \textsc{END} preserves critical information, reduces distraction, and lowers computational overhead. Extensive experiments demonstrate that \textsc{END} significantly improves both performance and efficiency across different LLMs on multiple evaluation datasets. Furthermore, by investigating LLMs' implicit understanding to the input with the prober, this work also deepens understanding of how LLMs do reasoning with contexts internally.

cs.CL↗

arXiv2026

Generalized intersection exponents and local cut points for three-dimensional Brownian loop soup

We study generalized non-intersection probabilities for the three-dimensional Brownian loop soup at subcritical intensities. We establish the existence of generalized intersection exponents (GIE) and prove an up-to-constants estimate for these probabilities by means of a separation lemma tailored to this setting. We also relate the Hausdorff dimension of the set of local cut points of the three-dimensional Brownian loop soup to the GIE, and show that the GIE is continuous at intensity zero, where it reduces to the classical Brownian intersection exponent. In particular, this implies that, for sufficiently small intensity parameters, the set of local cut points has Hausdorff dimension strictly larger than $1$.

math.PR↗

arXiv2026

DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible optimization signals in shared modules, resulting in gradient conflicts and negative transfer during training. To address this challenge, we first introduce gradient-based diagnostics to quantify module-level cross-category contention. Building on results of diagnostics, we propose DecomPose, a difficulty-aware decomposition framework that mitigates optimization contention via: (1) difficulty-aware gradient decoupling, which groups categories using a data-driven difficulty proxy and routes each instance to a group-specific correspondence branch to isolate incompatible updates; and (2) stability-driven asymmetric branching, which assigns higher-capacity branches to structurally simple categories as stable optimization anchors while constraining complex categories with lightweight branches to suppress noisy updates and alleviate negative transfer. Extensive experiments on REAL275, CAMERA25, and HouseCat6D demonstrate that DecomPose effectively reduces cross-category optimization contention and delivers superior pose estimation performance across multiple benchmarks.

cs.CV↗