Searcharxiv⌕ Search

arXiv subjects

Yufei Wang

Publications and source records attributed to Yufei Wang.

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

World Engine: Towards the Era of Post-Training for Autonomous Driving

Autonomous vehicles must operate safely in the real world, where errors can have severe consequences. Although modern end-to-end driving policies excel in routine scenarios, their reliability is limited by the scarcity of safety-critical ``long-tail'' events in real driving datasets. These rare interactions define the practical safety boundary of the learned policy, yet they are difficult to collect at scale in the real world. Here we show that this fundamental limitation can be addressed by post-training pre-trained driving models on synthesized high-stakes interactions. We introduce World Engine, a generative framework that reconstructs high-fidelity interactive environments from real-world logs and systematically extrapolates them into realistic safety-critical variations. This paradigm enables reinforcement-based post-training to align policies with safety constraints, circumventing the physical risks inherent in real-world exploration. On a public benchmark built on nuPlan, World Engine substantially reduces failures in rare safety-critical scenarios and yields significantly larger gains than scaling pre-training data alone. Furthermore, when deployed on a production-scale autonomous driving system, the resulting policy reduces simulated collisions and demonstrates measurable improvements in on-road testing, showing that post-training on synthesized, safety-critical interactions offers a scalable and effective pathway to safer autonomous driving. The full codebase suite, including training, is released to the public.

cs.RO↗
arXiv2026

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling

Large language models (LLMs) have opened new paradigms in optimization modeling by enabling the generation of executable solver code from natural language descriptions. Despite this promise, existing approaches typically remain solver-driven: they rely on single-pass forward generation and apply limited post-hoc fixes based on solver error messages, leaving undetected semantic errors that silently produce syntactically correct but logically flawed models. To address this challenge, we propose SAC-Opt, a backward-guided correction framework that grounds optimization modeling in problem semantics rather than solver feedback. At each step, SAC-Opt aligns the original semantic anchors with those reconstructed from the generated code and selectively corrects only the mismatched components, driving convergence toward a semantically faithful model. This anchor-driven correction enables fine-grained refinement of constraint and objective logic, enhancing both fidelity and robustness without requiring additional training or supervision. Empirical results on seven public datasets demonstrate that SAC-Opt improves average modeling accuracy by 7.7%, with gains of up to 21.9% on the ComplexLP dataset. These findings highlight the importance of semantic-anchored correction in LLM-based optimization workflows to ensure faithful translation from problem intent to solver-executable code.

cs.AI↗
arXiv2026

NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results

This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset~\cite{jin2024raindrop}. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task.

cs.CV↗
arXiv2026

Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution

Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substantial content information. Such redundancy leads to increased computational overhead and learning burden, as the model performs superfluous operations and must learn to filter out irrelevant information. To address this problem, we propose OASIS, an efficient $\textbf{o}$ne-step diffusion model with $\textbf{a}$ttention $\textbf{s}$pecialization for real-world v$\textbf{i}$deo $\textbf{s}$uper-resolution. OASIS incorporates an attention specialization routing that assigns attention heads to different patterns according to their intrinsic behaviors. This routing mitigates redundancy while effectively preserving pretrained knowledge, allowing diffusion models to better adapt to VSR and achieve stronger performance. Moreover, we propose a simple yet effective progressive training strategy, which starts with temporally consistent degradations and then shifts to inconsistent settings. This strategy facilitates learning under complex degradations. Extensive experiments demonstrate that OASIS achieves state-of-the-art performance on both synthetic and real-world datasets. OASIS also provides superior inference speed, offering a $\textbf{6.2$\times$}$ speedup over one-step diffusion baselines such as SeedVR2. The code will be available at \href{https://github.com/jp-guo/OASIS}{https://github.com/jp-guo/OASIS}.

cs.CV↗
arXiv2026

Scouting By Reward: VLM-TO-IRL-Driven Player Selection For Esports

Traditional esports scouting workflows rely heavily on manual video review and aggregate performance metrics, which often fail to capture the nuanced decision-making patterns necessary to determine if a prospect fits a specific tactical archetype. To address this, we reframe style-based player evaluation in esports as an Inverse Reinforcement Learning (IRL) problem. In this paper, we introduce a novel player selection framework that learns professional-specific reward functions from logged gameplay demonstrations, allowing organizations to rank candidates by their stylistic alignment with a target star player. Our proposed architecture utilizes a multimodal, two-branch intake: one branch encodes structured state-action trajectories derived from high-resolution in-game telemetry, while the second encodes temporally aligned tactical pseudo-commentary generated by Vision-Language Models (VLMs) from broadcast footage. These representations are fused and evaluated via a Generative Adversarial Imitation Learning (GAIL) objective, where a discriminator learns to capture the unique mechanical and tactical signatures of elite professionals. By transitioning from generic skill estimation to scouting "by reward," this framework provides a scalable, workflow-aware digital twin system that enables data-driven roster construction and targeted talent discovery across massive candidate pools.

cs.LG↗
arXiv2026

CCA Reimagined: An Exploratory Study of Large Language Models for Congestion Control

In this paper, we conduct an emulation-guided study to systematically investigate the feasibility of Large language model (LLM)-driven congestion control. The exploration is structured into two phases. The first phase derisks the whole capability where we isolate the role of LLM on a single yet crucial congestion avoidance phase so that we can safely examine when to invoke the LLM, what information to provide, and how to formulate LLM instructions. Based on the gained insights, we extend LLM's role to multiple congestion control phase and propose a more generic LLM-based congestion control policy. Our evaluation on both static and dynamic network traces demonstrates that the LLM-based solution can reduce latency by up to 50\% with only marginal throughput sacrifice (e.g., less than 0.3\%) compared to traditional CCAs. Overall, our exploration study confirms the potential of LLMs for adaptive and general congestion control, demonstrating that when granted appropriate control freedom and paired with an effective triggering mechanism, LLM-based policies achieve significant performance gains, particularly under highly dynamic network conditions.

cs.NI↗
arXiv2026

Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models

Diffusion models have become the dominant paradigm in text-to-image generation, and test-time scaling (TTS) improves sample quality by allocating additional computation at inference. Existing TTS methods, however, resample the entire image, while generation quality is often spatially heterogeneous. This leads to unnecessary computation on regions that are already correct, and localized defects remain insufficiently corrected. In this paper, we explore a new direction - Localized TTS - that adaptively resamples defective regions while preserving high-quality regions, thereby substantially reducing the search space. This raises two challenges: accurately localizing defects and maintaining global consistency. We propose LoTTS, the first fully training-free framework for localized TTS. For defect localization, LoTTS contrasts cross- and self-attention signals under quality-aware prompts (e.g., high-quality vs. low-quality) to identify defective regions, and then refines them into coherent masks. For consistency, LoTTS perturbs only defective regions and denoises them locally, ensuring that corrections remain confined while the rest of the image remains undisturbed. Extensive experiments on SD2.1, SDXL, and FLUX demonstrate that LoTTS achieves state-of-the-art performance: it consistently improves both local quality and global fidelity, while reducing GPU cost by 2-4x compared to Best-of-N sampling. These findings establish localized TTS as a promising new direction for scaling diffusion models at inference time.

cs.CV↗
arXiv2026

DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild

Blind image quality assessment (IQA) in the wild, which assesses the quality of images with complex authentic distortions and no reference images, presents significant challenges. Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem. Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA (DP-IQA), to utilize the T2I model's prior for improved performance and generalization ability. Specifically, we utilize pre-trained Stable Diffusion as the backbone, extracting multi-level features from the denoising U-Net guided by prompt embeddings through a tunable text adapter. Simultaneously, an image adapter compensates for information loss introduced by the lossy pre-trained encoder. Unlike T2I models that require full image distribution modeling, our approach targets image quality assessment, which inherently requires fewer parameters. To improve applicability, we distill the knowledge into a lightweight CNN-based student model, significantly reducing parameters while maintaining or even enhancing generalization performance. Experimental results demonstrate that DP-IQA achieves state-of-the-art performance on various in-the-wild datasets, highlighting the superior generalization capability of T2I priors in blind IQA tasks. To our knowledge, DP-IQA is the first method to apply pre-trained diffusion priors in blind IQA. Codes and checkpoints are available at https://github.com/RomGai/DP-IQA.

cs.CV↗
arXiv2026

RubricBench: Aligning Model-Generated Rubrics with Human Standards

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing benchmarks lack both the discriminative complexity and the ground-truth rubric annotations required for rigorous analysis. To bridge this gap, we introduce RubricBench, a curated benchmark with 1,147 pairwise comparisons specifically designed to assess the reliability of rubric-based evaluation. Our construction employs a multi-dimensional filtration pipeline to target hard samples featuring nuanced input complexity and misleading surface bias, augmenting each with expert-annotated, atomic rubrics derived strictly from instructions. Comprehensive experiments reveal a substantial capability gap between human-annotated and model-generated rubrics, indicating that even state-of-the-art models struggle to autonomously specify valid evaluation criteria, lagging considerably behind human-guided performance.

cs.AI↗
arXiv2026

AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations. In this work, we present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision to efficiently tackle complex mathematical problems. Our approach introduces three key innovations: (1) An automated method that converts natural language chain-of-thought into structured tool-augmented trajectories, generating high-quality supervised fine-tuning (SFT) data to alleviate data scarcity; (2) A novel agentic reinforcement learning (RL) paradigm that dynamically interleaves natural language generation with real-time code execution. This enables models to autonomously learn optimal tool-use strategies through multi-round interactive feedback, while fostering emergent capabilities in code refinement and error correction; (3) An efficient training system incorporating innovative techniques, including request-level asynchronous rollout scheduling, agentic partial rollout, and prefix-aware weighted load balancing, achieving 4-5x speedup and making efficient RL training feasible on ultra-long sequences with scenarios with massive tool invocation. The evaluations show that AgentMath achieves state-of-the-art performance on challenging mathematical competition benchmarks including AIME24, AIME25, and HMMT25. Specifically, AgentMath-30B-A3B attains 90.6%, 86.4%, and 73.8% accuracy respectively, surpassing OpenAI-o3-mini and Claude-Opus-4.0-Thinking while remaining competitive with OpenAI-o3, Gemini-2.5-Pro, and DeepSeek-R1-671B-0528.These results validate the effectiveness of our approach and pave the way for building scalable mathematical reasoning agents.

cs.AI↗
arXiv2026

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evaluation. However, current works predominantly rely on unstructured length scaling, ignoring the divergent efficacy of different reasoning mechanisms: Breadth-CoT (B-CoT, i.e., multi-dimensional principle coverage) and Depth-CoT (D-CoT, i.e., substantive judgment soundness). To address this, we introduce Mix-GRM, a framework that reconfigures raw rationales into structured B-CoT and D-CoT through a modular synthesis pipeline, subsequently employing Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR) to internalize and optimize these mechanisms. Comprehensive experiments demonstrate that Mix-GRM establishes a new state-of-the-art across five benchmarks, surpassing leading open-source RMs by an average of 8.2\%. Our results reveal a clear divergence in reasoning: B-CoT benefits subjective preference tasks, whereas D-CoT excels in objective correctness tasks. Consequently, misaligning the reasoning mechanism with the task directly degrades performance. Furthermore, we demonstrate that RLVR acts as a switching amplifier, inducing an emergent polarization where the model spontaneously allocates its reasoning style to match task demands. The synthesized data and models are released at \href{https://huggingface.co/collections/DonJoey/mix-grm}{Hugging Face}, and the code is released at \href{https://github.com/Don-Joey/Mix-GRM}{Github}.

cs.AI↗
arXiv2026

Controlling Your Image via Simplified Vector Graphics

Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled at the element level, enabling intuitive modifications such as adjusting shapes, altering colors, or adding and removing objects? In this work, we address this challenge by introducing layer-wise controllable generation through simplified vector graphics (VGs). Our approach first efficiently parses images into hierarchical VG representations that are semantic-aligned and structurally coherent. Building on this representation, we design a novel image synthesis framework guided by VGs, allowing users to freely modify elements and seamlessly translate these edits into photorealistic outputs. By leveraging the structural and semantic features of VGs in conjunction with noise prediction, our method provides precise control over geometry, color, and object semantics. Extensive experiments demonstrate the effectiveness of our approach in diverse applications, including image editing, object-level manipulation, and fine-grained content creation, establishing a new paradigm for controllable image generation. Project page: https://guolanqing.github.io/Vec2Pix/

cs.CV↗
arXiv2026

Optical transport of cold atoms to quantum degeneracy

Efficient transport of cold atoms is essential for continuous operation, enabling applications ranging from atomic lasers to continuously operated qubits. However, deep potentials required to overcome vibrations, axial trap nonuniformity and insufficient cooling have limited transport of cold atoms near quantum degeneracy. Here we demonstrate rapid optical transport of cold atoms to Bose-Einstein condensation using a moving optical lattice formed by two Bessel beams. A gas of $3 \times 10^5$ ytterbium atoms at a temperature of $340\,$nK is transported over $34\,$cm in $350\,$ms with efficiency over $60\%$. Furthermore, a degenerate gas of $1 \times 10^5$ atoms with a $40\%$ condensate fraction emerges from the phase synchronization process driven by atomic interactions. This demonstration enables the fast preparation of ultracold atomic beams and large-scale atom arrays for quantum sensing, simulation and computing.

cond-mat.quant-gas↗
arXiv2026

Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving

Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these methods, they primarily rely on post-selection or predefined strategies, leaving an open question: whether LLMs can autonomously adapt their reasoning strategy based on their inherent capabilities. In this work, we propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously, aligning it with their intrinsic aptitude. TATA incorporates base-LLM-aware data selection during supervised fine-tuning (SFT) to tailor training data to the model's unique abilities. This approach equips LLMs to autonomously determine and apply the appropriate reasoning strategy at test time. We evaluate TATA through extensive experiments on six mathematical reasoning benchmarks, using both general-purpose and math-specialized LLMs. Empirical results demonstrate that TATA effectively combines the complementary strengths of CoT and TIR, achieving superior or comparable performance with improved inference efficiency compared to TIR alone. Further analysis underscores the critical role of aptitude-aware data selection in enabling LLMs to make effective and adaptive reasoning decisions and align reasoning strategies with model capabilities.

cs.CL↗
arXiv2026

Tighnari v2: Mitigating Label Noise and Distribution Shift in Multimodal Plant Distribution Prediction via Mixture of Experts and Weakly Supervised Learning

Large-scale, cross-species plant distribution prediction plays a crucial role in biodiversity conservation, yet modeling efforts in this area still face significant challenges due to the sparsity and bias of observational data. Presence-Absence (PA) data provide accurate and noise-free labels, but are costly to obtain and limited in quantity; Presence-Only (PO) data, by contrast, offer broad spatial coverage and rich spatiotemporal distribution, but suffer from severe label noise in negative samples. To address these real-world constraints, this paper proposes a multimodal fusion framework that fully leverages the strengths of both PA and PO data. We introduce an innovative pseudo-label aggregation strategy for PO data based on the geographic coverage of satellite imagery, enabling geographic alignment between the label space and remote sensing feature space. In terms of model architecture, we adopt Swin Transformer Base as the backbone for satellite imagery, utilize the TabM network for tabular feature extraction, retain the Temporal Swin Transformer for time-series modeling, and employ a stackable serial tri-modal cross-attention mechanism to optimize the fusion of heterogeneous modalities. Furthermore, empirical analysis reveals significant geographic distribution shifts between PA training and test samples, and models trained by directly mixing PO and PA data tend to experience performance degradation due to label noise in PO data. To address this, we draw on the mixture-of-experts paradigm: test samples are partitioned according to their spatial proximity to PA samples, and different models trained on distinct datasets are used for inference and post-processing within each partition. Experiments on the GeoLifeCLEF 2025 dataset demonstrate that our approach achieves superior predictive performance in scenarios with limited PA coverage and pronounced distribution shifts.

cs.CV↗
arXiv2026

Weak to Strong: VLM-Based Pseudo-Labeling as a Weakly Supervised Training Strategy in Multimodal Video-based Hidden Emotion Understanding Tasks

To tackle the automatic recognition of "concealed emotions" in videos, this paper proposes a multimodal weak-supervision framework and achieves state-of-the-art results on the iMiGUE tennis-interview dataset. First, YOLO 11x detects and crops human portraits frame-by-frame, and DINOv2-Base extracts visual features from the cropped regions. Next, by integrating Chain-of-Thought and Reflection prompting (CoT + Reflection), Gemini 2.5 Pro automatically generates pseudo-labels and reasoning texts that serve as weak supervision for downstream models. Subsequently, OpenPose produces 137-dimensional key-point sequences, augmented with inter-frame offset features; the usual graph neural network backbone is simplified to an MLP to efficiently model the spatiotemporal relationships of the three key-point streams. An ultra-long-sequence Transformer independently encodes both the image and key-point sequences, and their representations are concatenated with BERT-encoded interview transcripts. Each modality is first pre-trained in isolation, then fine-tuned jointly, with pseudo-labeled samples merged into the training set for further gains. Experiments demonstrate that, despite severe class imbalance, the proposed approach lifts accuracy from under 0.6 in prior work to over 0.69, establishing a new public benchmark. The study also validates that an "MLP-ified" key-point backbone can match - or even surpass - GCN-based counterparts in this task.

cs.CV↗
arXiv2026

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is challenging because there is no unambiguous ground truth. Relying on single-dot supervision often leads to inefficiency and reward hacking. To address these issues, we propose reinforcement learning with verifiable reference-based rewards (RLVRR). Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e, reward chain). Specifically, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts (e.g., keywords), and style, which evaluates adherence to stylistic properties through LLM-based verification. In this way, RLVRR combines the exploratory strength of RL with the efficiency and reliability of supervised fine-tuning (SFT). Extensive experiments on more than 10 benchmarks with Qwen and Llama models confirm the advantages of our approach. RLVRR (1) substantially outperforms SFT trained with ten times more data and advanced reward models, (2) unifies the training of structured reasoning and open-ended generation, and (3) generalizes more effectively while preserving output diversity. These results establish RLVRR as a principled and efficient path toward verifiable reinforcement learning for general-purpose LLM alignment. We release our code and data at https://github.com/YJiangcm/RLVRR.

cs.CL↗
arXiv2025

Symbol-Level Precoding for Integrated Sensing and Covert Communication

Integrated sensing and communication (ISAC) systems have emerged as a promising solution to improve spectrum efficiency and enable functional convergence. However, ensuring secure information transmission while maintaining high-quality sensing performance remains a significant challenge. In this paper, we investigate an integrated sensing and covert communication (ISCC) system, in which a base station (BS) simultaneously serves multiple downlink users and senses malicious targets that may act as both potential eavesdroppers (Eves) and wardens. We propose a novel symbol-level precoding (SLP)-based waveform design for ISCC that achieves covert communication intrinsically, without requiring additional transmission resources such as artificial noise. The proposed design integrates symbol shaping to enhance reliability for legitimate users and noise shaping to obscure transmission activities from the targets. For imperfect channel state information (CSI), the framework incorporates bounded uncertainty models for user channels and target angles, yielding a more robust design. The resulting ISCC waveform optimization problem is non-convex; to address this, we develop a low-complexity proximal distance algorithm (PDA) with closed-form updates under both PSK and QAM modulations. Simulation results demonstrate that the proposed method achieves superior covertness and sensing-communication performance with negligible degradation compared to traditional beamforming and conventional SLP approaches without noise-shaping mechanisms.

eess.SP↗