Searcharxiv⌕ Search

arXiv subjects

Yucheng Wang

Publications and source records attributed to Yucheng Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

MapDream: Task-Driven Map Learning for Vision-Language Navigation

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that maps should instead be learned representations shaped directly by navigation objectives rather than exhaustive reconstructions. Based on this insight, we propose MapDream, a map-in-the-loop framework that formulates map construction as autoregressive bird's-eye-view (BEV) image synthesis. The framework jointly learns map generation and action prediction, distilling environmental context into a compact three-channel BEV map that preserves only navigation-critical affordances. Supervised pre-training bootstraps a reliable mapping-to-control interface, while the autoregressive design enables end-to-end joint optimization through reinforcement fine-tuning. Experiments on R2R-CE and RxR-CE achieve state-of-the-art monocular performance, validating task-driven generative map learning.

cs.RO↗
arXiv2026

G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition

We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Under chunk-wise decoding protocols, experiments on both oracle-segmented local evaluation and full-meeting global evaluation show strong speaker-attributed transcription performance.

eess.AS↗
arXiv2026

A Unified and Reproducible Experimentation Framework for Speech Understanding

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

eess.AS↗
arXiv2026

Audio-Mind: An Auditable Agentic Framework for Audio Understanding

Audio agents extend large audio-language models (LALMs) by decomposing audio questions into tool calls, intermediate evidence, and iterative reasoning steps. However, as LALMs become stronger, the key challenge shifts from enabling tool use to determining when agentic evidence acquisition genuinely benefits audio understanding. We propose Audio-Mind, an auditable and pluggable framework for conditional evidence acquisition in audio understanding. Audio-Mind dynamically combines a strong frontend with planner-guided tool use, preserving frontend judgment when initial evidence is sufficient while acquiring bounded external evidence for questions with unresolved evidence gaps. Experiments on MMAR and MSU-Bench show that Audio-Mind outperforms prior audio-agent baselines, reaching 80.4% accuracy on MMAR and 82.8% accuracy on MSU-Bench. A matched-backbone comparison highlights why this design matters: under strong audio frontends, agentic decomposition can become an orchestration bottleneck when the workflow does not preserve the frontend's holistic audio-grounded judgment. Beyond accuracy, Audio-Mind produces higher-quality, auditable reasoning traces that expose uncertainty, tool evidence, and answer rationales, offering a potential basis for more reliable audio-QA annotation and error analysis.

eess.AS↗
arXiv2026

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient alternative to diffusion models, but practical implementations typically rely on a single finite-capacity global vector-field estimator. In such heterogeneous temporal distributions, distinct regimes may pass through nearby flow states while requiring incompatible conditional velocities. A monolithic estimator trained with the standard $\ell_2$ velocity-matching objective may therefore learn an overly smoothed approximation of the local transport field. This estimator-level smoothing can attenuate branch-specific dynamics, leading to spectral distortion and poor mode coverage. To address this, we propose PrismFlow, a new FM method with Koopman-inspired dynamical experts. Each expert learns residual corrections in a latent space where local nonlinear temporal evolution can be approximated by linear transitions. We further propose a confidence-aware Winner-Take-All (WTA) objective that updates only the expert best aligned with each sample while masking gradients to the others, encouraging mode-specific specialization. During sampling, the selected expert adds a residual dynamical correction to the global transport field, preserving FM stability while recovering fine-grained and high-frequency temporal structures. Across various benchmarks, PrismFlow effectively mitigates the spectral contraction in standard FM and achieves state-of-the-art performance, with a 15.6% gain in Context-FID and a 38.6% improvement in Discriminative Score, while remaining robust in low-data settings and effective for forecasting and imputation.

cs.LG↗
arXiv2026

EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation

Generating high-fidelity visual effects (VFX) typically demands massive datasets and prohibitive computational power due to the intricate coupling of spatial textures and temporal dynamics. In this paper, we introduce EasyVFX, a resource-efficient framework that achieves realistic VFX synthesis under stringent constraints. Our core philosophy lies in frequency-domain decomposition: we observe that the complexity of VFX can be significantly mitigated by decoupling high-frequency components, which represent intricate spatial appearances, from low-frequency components that encapsulate global motion dynamics. This spectral disentanglement transforms a high-dimensional learning problem into manageable sub-tasks, thereby lowering the optimization barrier and reducing data dependency. Building upon this insight, we propose a two-stage training paradigm. First, we design a Frequency-aware Mixture-of-Experts (Freq-MoE) architecture. By utilizing a soft routing mechanism, our model assigns specialized experts to distinct spectral bands, enabling them to cultivate robust priors for appearance and motion dynamics. This specialization allows the model to acquire foundational VFX knowledge with fewer GPU resources. Second, we introduce a Test-Time Training strategy powered by a novel Frequency-constraint Loss. This allows the pre-trained model to swiftly adapt to specific, unseen effects through localized optimizations, requiring only about 100 steps on a single GPU. Experimental results demonstrate that EasyVFX produces structurally consistent and visually stunning effects, proving that frequency-aware learning is a key catalyst for democratizing professional-grade VFX.

cs.CV↗
arXiv2026

HoloMotion-1 Technical Report

In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1 is to scale control-policy training with a large-scale hybrid motion corpus, where video-reconstructed motions from in-the-wild videos provide the dominant source of motion diversity, while curated motion-capture and in-house motion data provide higher-fidelity supervision and deployment-oriented coverage. This data regime enables HoloMotion-1 to move beyond conventional MoCap-only training and exposes the policy to substantially broader behaviors, capture conditions, and motion styles. Learning from such heterogeneous data introduces new challenges, including reconstruction noise, source-domain mismatch, uneven motion quality, and the need for temporal modeling under large behavioral variation. To address these challenges, HoloMotion-1 integrates large-capacity temporal modeling, a sparsely activated Mixture-of-Experts Transformer with KV-cache inference for real-time control, and a sequence-level training strategy that improves learning efficiency on extended motion sequences. Extensive experiments on multiple unseen motion benchmarks show that HoloMotion-1 generalizes robustly across diverse motion types and capture conditions, significantly improves tracking accuracy over prior methods, and transfers directly to a real humanoid robot without task-specific fine-tuning.

cs.RO↗
arXiv2026

Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation

Long-form question answering (LFQA) requires open-ended long-form responses that synthesize coherent, factually grounded content from multi-source evidence. This makes reinforcement learning (RL) reward design critical. The reward must be verifiable for faithful grounding and stable optimization. However, many standard rewards assume a unique target with an exact-match notion of correctness, which fits short-form QA and math but breaks in LFQA. As a result, current RAG systems still lack verifiable reward mechanisms, yielding unstable feedback signals and suboptimal optimization outcomes. We propose RioRAG, a framework for reinforced verifiable informativeness optimization. First, it defines informativeness as a measurable and externally verifiable objective for RL. Second, RioRAG uses nugget-centric verification with cross-source checks to enable self-evolution of smaller LLMs and to provide denser, action-discriminative rewards that mitigate reward sparsity and stabilize optimization. This formulation avoids handcrafted supervision for the policy model and strong teacher-model distillation, relying instead on externally verifiable feedback. Experiments on LongFact and RAGChecker show that RioRAG achieves higher factual recall and faithfulness, establishing verifiable reward modeling as a foundation for trustworthy long-form RAG. Our codes are available at https://github.com/RUCAIBox/RioRAG.

cs.CL↗
arXiv2026

Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality

Hallucination in large language models (LLMs) during long-form generation remains difficult to address under existing reinforcement learning from human feedback (RLHF) frameworks, as their preference rewards often overlook the model's own knowledge boundaries. In this paper, we propose the $\textbf{K}$nowledge-$\textbf{L}$evel $\textbf{C}$onsistency Reinforcement Learning $\textbf{F}$ramework ($\textbf{KLCF}$), which re-examines this problem from a distribution alignment perspective. KLCF formalizes long-form factuality as a bidirectional distribution matching objective between the policy model's expressed knowledge distribution and the base model's parametric knowledge distribution: under the constraint that generation must not exceed the support set of the base knowledge, the objective maximizes coverage of high-probability facts, thereby jointly optimizing precision and recall. To achieve this, we design a Dual-Fact Alignment mechanism that approximates the recall term using a factual checklist constructed by sampling from the base model, and constrains hallucinations with a lightweight truthfulness reward model. Both components are jointly optimized and require no external retrieval throughout training. Experimental results demonstrate that KLCF consistently improves factuality metrics across multiple long-form benchmarks and model scales, effectively alleviating hallucination and over-conservatism while maintaining efficiency and scalability.

cs.CL↗
arXiv2026

Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning

Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-modal reasoning remains underexplored, with conflicting reports on whether added modalities help or harm performance. These inconsistencies stem from a lack of controlled evaluation frameworks and analysis of models' internals to isolate when and why modality interactions support or undermine reasoning. We address this gap through a logic-grounded evaluation framework that categorizes multimodal reasoning into six interaction patterns, varying how facts are distributed across modalities and logically combined. Empirically, additional modalities enhance reasoning only when they provide independent and sufficient reasoning paths, while redundant or chained entailment support often hurts performance. Moreover, reasoning degrades in three systematic ways: weaker modalities drag down overall performance, conflicts bias preference toward certain modalities, and joint signals from different modalities fail to be integrated effectively. Therefore, we identify two core failures: task-composition bottleneck, where recognition and reasoning cannot be jointly executed in one pass, and fusion bottleneck, where early integration introduces bias. For further investigation, we find that attention patterns fail to encode fact usefulness, but a simple two-step prompting (recognize then reason) restores performance, confirming the task-composition bottleneck. Moreover, modality identity remains recoverable in early layers, and softening attention in early fusion improves reasoning, highlighting biased fusion as another failure mode. Overall, our findings show that integration, not perception, is the main barrier to multimodal reasoning, suggesting composition-aware training and early fusion control as promising directions.

cs.CL↗
arXiv2026

Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation

Vision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they have advanced within a multi-step instruction. However, recent Vision-Language-Action models focus on direct action prediction and earlier progress methods predict numeric achievements; both overlook the monotonic co-progression property of the observation and instruction sequences. Building on this insight, Progress-Think introduces semantic progress reasoning, predicting instruction-style progress from visual observations to enable more accurate navigation. To achieve this without expensive annotations, we propose a three-stage framework. In the initial stage, Self-Aligned Progress Pretraining bootstraps a reasoning module via a novel differentiable alignment between visual history and instruction prefixes. Then, Progress-Guided Policy Pretraining injects learned progress states into the navigation context, guiding the policy toward consistent actions. Finally, Progress-Policy Co-Finetuning jointly optimizes both modules with tailored progress-aware reinforcement objectives. Experiments on R2R-CE and RxR-CE show state-of-the-art success and efficiency, demonstrating that semantic progress yields a more consistent representation of navigation advancement.

cs.RO↗
arXiv2026

Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection

Industrial 3D anomaly detection performance is fundamentally constrained by the scarcity and long-tailed distribution of abnormal samples. To address this challenge, we propose Synthesis4AD, an end-to-end paradigm that leverages large-scale, high-fidelity synthetic anomalies to learn more discriminative representations for 3D anomaly detection. At the core of Synthesis4AD is 3D-DefectStudio, a software platform built upon the controllable synthesis engine MPAS, which injects geometrically realistic defects guided by higher-dimensional support primitives while simultaneously generating accurate point-wise anomaly masks. Furthermore, Synthesis4AD incorporates a multimodal large language model (MLLM) to interpret product design information and automatically translate it into executable anomaly synthesis instructions, enabling scalable and knowledge-driven anomalous data generation. To improve the robustness and generalization of the downstream detector on unstructured point clouds, Synthesis4AD further introduces a training pipeline based on spatial-distribution normalization and geometry-faithful data augmentations, which alleviates the sensitivity of Point Transformer architectures to absolute coordinates and improves feature learning under realistic data variations. Extensive experiments demonstrate state-of-the-art performance on Real3D-AD, MulSen-AD, and a real-world industrial parts dataset. The proposed synthesis method MPAS and the interactive system 3D-DefectStudio will be publicly released at https://github.com/hustCYQ/Synthesis4AD.

cs.CV↗
arXiv2026

MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification

Recent advancements in machine learning-based signal analysis, coupled with open data initiatives, have fuelled efforts in automatic sleep stage classification. Despite the proliferation of classification models, few have prioritised reducing model complexity, which is a crucial factor for practical applications. In this work, we introduce Multi-Scale and Attention Convolutional Neural Network (MSA-CNN), a lightweight architecture featuring as few as ~10,000 parameters. MSA-CNN leverages a novel multi-scale module employing complementary pooling to eliminate redundant filter parameters and dense convolutions. Model complexity is further reduced by separating temporal and spatial feature extraction and using cost-effective global spatial convolutions. This separation of tasks not only reduces model complexity but also mirrors the approach used by human experts in sleep stage scoring. We evaluated both small and large configurations of MSA-CNN against nine state-of-the-art baseline models across three public datasets, treating univariate and multivariate models separately. Our evaluation, based on repeated cross-validation and re-evaluation of all baseline models, demonstrated that the large MSA-CNN outperformed all baseline models on all three datasets in terms of accuracy and Cohen's kappa, despite its significantly reduced parameter count. Lastly, we explored various model variants and conducted an in-depth analysis of the key modules and techniques, providing deeper insights into the underlying mechanisms. The code for our models, baselines, and evaluation procedures is available at https://github.com/sgoerttler/MSA-CNN.

cs.LG↗
arXiv2026

Attention Residuals

Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-state growth with depth, progressively diluting each layer's contribution. We propose Attention Residuals (AttnRes), which replaces this fixed accumulation with softmax attention over preceding layer outputs, allowing each layer to selectively aggregate earlier representations with learned, input-dependent weights. To address the memory and communication overhead of attending over all preceding layer outputs for large-scale model training, we introduce Block AttnRes, which partitions layers into blocks and attends over block-level representations, reducing the memory footprint while preserving most of the gains of full AttnRes. Combined with cache-based pipeline communication and a two-phase computation strategy, Block AttnRes becomes a practical drop-in replacement for standard residual connections with minimal overhead. Scaling law experiments confirm that the improvement is consistent across model sizes, and ablations validate the benefit of content-dependent depth-wise selection. We further integrate AttnRes into the Kimi Linear architecture (48B total / 3B activated parameters) and pre-train on 1.4T tokens, where AttnRes mitigates PreNorm dilution, yielding more uniform output magnitudes and gradient distribution across depth, and improves downstream performance across all evaluated tasks.

cs.CL↗
arXiv2026

Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation

Accurate Remaining Useful Life (RUL) prediction without labeled target domain data is a critical challenge, and domain adaptation (DA) has been widely adopted to address it by transferring knowledge from a labeled source domain to an unlabeled target domain. Despite its success, existing DA methods struggle significantly when faced with incomplete degradation trajectories in the target domain, particularly due to the absence of late degradation stages. This missing data introduces a key extrapolation challenge. When applied to such incomplete RUL prediction tasks, current DA methods encounter two primary limitations. First, most DA approaches primarily focus on global alignment, which can misaligns late degradation stage in the source domain with early degradation stage in the target domain. Second, due to varying operating conditions in RUL prediction, degradation patterns may differ even within the same degradation stage, resulting in different learned features. As a result, even if degradation stages are partially aligned, simple feature matching cannot fully align two domains. To overcome these limitations, we propose a novel evidential adaptation approach called EviAdapt, which leverages evidential learning to enhance domain adaptation. The method first segments the source and target domain data into distinct degradation stages based on degradation rate, enabling stage-wise alignment that ensures samples from corresponding stages are accurately matched. To address the second limitation, we introduce an evidential uncertainty alignment technique that estimates uncertainty using evidential learning and aligns the uncertainty across matched stages.

cs.LG↗
arXiv2026

An Extended Study of Gear-Ratio-Aware Standard Cell Layout Generation for DTCO Exploration

Advanced nodes decouple contacted poly pitch (CPP) and lower-metal pitch to improve routability. We present CPCell, an efficient standard-cell layout generation framework, to support arbitrary gear ratio (GR) and offset parameters through a fine-grained layered grid graph and constraint-programming-based placement-routing co-optimization. Layout quality is improved via Middle-of-Line routing, M0 pin enablement, pin accessibility constraints and a weighted multi-objective formulation that jointly optimizes cell layouts. To scale to netlists with up to 48 transistors, we incorporate acceleration techniques including transistor clustering, identical transistor partitioning, routing lower bound tightening and early termination strategies. Comprehensive cell-level and block-level studies are conducted to evaluate GR and offset choices, quantify the benefits of the proposed objectives and assess their impact on power, performance, area and IR-drop outcomes.

cs.AR↗
arXiv2026

Linking Perception, Confidence and Accuracy in MLLMs

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a probing experiment, we reveal a severe confidence miscalibration problem in MLLMs. To address this, we propose Confidence-Driven Reinforcement Learning (CDRL), which uses original-noise image pairs and a novel confidence-based reward to enhance perceptual sensitivity and robustly calibrate the model's confidence. Beyond training benefits, calibrated confidence enables more effective test-time scaling as a free lunch. We further propose Confidence-Aware Test-Time Scaling (CA-TTS), which dynamically coordinates Self-Consistency, Self-Reflection, and Visual Self-Check modules guided by confidence signals. An Expert Model acts in multiple roles (e.g., Planner, Critic, Voter) to schedule these modules and provide external verification. Our integrated framework establishes new state-of-the-art results with consistent 8.8% gains across four benchmarks. More ablation studies demonstrate the effectiveness of each module and scaling superiority.

cs.CV↗
arXiv2026

An Updated Assessment of Reinforcement Learning for Macro Placement

We provide an improved assessment of Google Brain's deep reinforcement learning approach to macro placement and its updated Circuit Training (CT) implementation in GitHub. A stronger simulated annealing (SA) baseline leverages the "go-with-the-winners" metaheuristic and a multi-threading implementation. We develop and release new public benchmarks in sub-10nm technology: LEF/DEF for Google's 7nm TSMC Ariane protobuf and scaled variants, as well as testcases implemented in the open-source ASAP7 7nm research enablement. We evaluate from-scratch training and fine-tuning results for the latest "AlphaChip" release of Circuit Training, alongside multiple alternative macro placers. We also study the recently-published pre-training guidance in. A commercial place-and-route tool is used to provide "true reward" post-route power, performance and area metrics. All data, evaluation flows and related scripts are publicly available in the MacroPlacement GitHub repository. Our study affords insights into reproducibility and reporting in the research literature, and points out still-missing confirmations (e.g., of CT's scalability and pre-training methodology) that remain open questions for the research community.

cs.LG↗