arXiv subjects

Mei Chen

Publications and source records attributed to Mei Chen.

At least 19 recordsLinked to original sources

arXiv2026

Parametric CAD Bench v3: Evaluating Agentic Parametric CAD Authoring from Text and Engineering Drawings

Producing an executable CAD script is not sufficient to establish that an agent has satisfied an engineering design request. Evaluation must also consider the resulting geometry, specified dimensions, and native CAD modeling history. We present Parametric CAD Bench v3, a 100-task benchmark comprising 30 text-to-CAD creation tasks, 30 text-to-CAD create-and-edit tasks, and 40 tasks that reconstruct mechanical parts from engineering drawings. Agents operate in a pinned FreeCAD environment and submit native CAD artifacts to a separate programmatic verifier. The primary metric is mean continuous task reward, combining geometry similarity and specification consistency rather than binary task success. A September 24, 2026 snapshot covers 13 model-agent systems; Claude Code with Claude Opus 5.5 achieves the highest overall point estimate, 61.03%, and an image-to-CAD mean reward of 84.66%. These measurements describe complete systems, not isolated model capabilities. We release versioned tasks, evaluation configurations, and inspectable result artifacts.

cs.AI↗

arXiv2026

UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation

Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of work address this from complementary angles: Representation Alignment (REPA) accelerates DiT training by aligning intermediate features with a pretrained external representation model (e.g., DINOv2), while Representation Auto-Encoders (RAE) replace the pixel-space VAE with a compact representation-space tokenizer learned from self-supervised features. However, these approaches are developed and applied in isolation: REPA still relies on a pixel-space VAE for latent diffusion, and RAE does not exploit the alignment signal that accelerates the diffusion backbone. We present \textbf{UniRA}, a unified framework that couples representation alignment and representation auto-encoding into a single objective. UniRA learns a representation-space tokenizer whose output serves simultaneously as the diffusion target and the alignment anchor, so the tokenizer, the diffusion backbone, and the external representation model are co-optimized. We give a theoretical result showing that this joint optimization preserves the representation quality of the external model while accelerating diffusion convergence, and we derive a principled weighting that balances the reconstruction, alignment, and generation objectives. On ImageNet class-conditional generation at 256*256 and 512*512, UniRA matches or surpasses state-of-the-art DiTs (SD3, REPA, RAE) in FID while reducing training steps by up to 5*. We further show that the unified representation space supports improved zero-shot classification and linear probing, confirming that generation and understanding benefit from a shared, aligned latent space.

cs.CV↗

arXiv2026

AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies

Vision-language-action (VLA) models have become a powerful paradigm for generalist robotic manipulation, yet they are often reactive: the policy maps the current observation directly to an action chunk without reasoning about the long-term consequences of its decisions. Prior attempts to endow policies with world models either reconstruct future frames in pixel space---expensive and dominated by task-irrelevant detail---or decouple the world model from the policy, weakening control. We present AWM-VLA, a unified framework that embeds aligned world modeling directly inside a diffusion-transformer policy. Following the Future Latent REpresentation Alignment (FLARE) principle, we add learnable future tokens whose intermediate activations are aligned with vision-language embeddings of future observations, enabling the policy to anticipate long-term consequences while generating actions. We extend this paradigm in two ways. First, we introduce an object-centric decoupled alignment objective that predicts future object-level semantics alongside the global future embedding, improving both interpretability and multi-instruction generalization. Second, we balance the global and object-centric alignment terms against the action flow-matching loss through a principled weighting, yielding a controllable accuracy--interpretability trade-off. On RoboCasa and humanoid tabletop manipulation benchmarks, AWM-VLA outperforms prior VLA and world-model baselines by up to 21% in success rate, improves generalization to novel objects and instructions, and produces object-centric rationales that are preferred by human raters in 83 of cases. Our approach adds only a few learnable tokens to the policy and is compatible with any diffusion or flow-matching policy, making aligned world modeling an inexpensive, broadly applicable component of generalist manipulation.

cs.CV↗

arXiv2026

UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling

Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods are fragmented: some predict masked parts of a single image in latent space (I-JEPA), others learn to predict global photometric transformations (Image World Models), while video-scale JEPAs predict future temporal states and are post-trained for action-conditioned planning (V-JEPA~2, DINO-World, DINO-WM). These objectives are treated as distinct recipes with separate encoders, predictors, and anti-collapse regularizers, hindering a single model from unifying image-level and video-level world modeling. We present UniJEPA, a unified JEPA that jointly learns photometric prediction (image-level transformations) and temporal prediction (video-level next-state dynamics) in one shared latent space. A single end-to-end objective, composed of a next-embedding prediction loss and a Gaussian regularizer, yields a provably anti-collapse encoder-predictor pair trainable from raw pixels without EMA, stop-gradient, or pre-trained encoders. We show that the same latent space supports controllable abstraction: photometric prediction learns invariant structure while temporal prediction learns equivariant dynamics. After action-conditioned post-training on offline trajectories, UniJEPA enables zero-shot planning by treating goal features as prediction targets. On image, video, and control benchmarks, UniJEPA matches or surpasses task-specific JEPAs while requiring a single loss hyperparameter, and plans up to tens of times faster than generative world models at comparable accuracy.

cs.CV↗

arXiv2026

DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the computation that actually produced the answer, undermining reliability in safety-critical applications. We present DiffuseAgent-MI, a self-evolving agent whose perceptual grounding is governed by a KL-minimal energy model over feature units, providing a distributional view of visual mechanistic interpretability. The agent learns an energy landscape that softly constrains generated samples to lie near the native prior conditioned on the chosen interpretable unit, closing the gap between the explanation and the internal representation. A verifier then supplies trajectory-level faithfulness rewards, and a repair branch re-conditions the energy when the verifier flags an unfaithful step. On GeoQA, SciVis, VQA-v2 and an in-house multimodal reasoning set, DiffuseAgent-MI improves accuracy by up to 5.1 points over prior self-evolving agents while more than doubling mutual-information faithfulness and human-interpretability agreement. Our analysis shows the energy term and the verifier are complementary: the former guarantees distributional faithfulness, the latter trajectory-level faithfulness, and only their combination closes both gaps.

cs.CV↗

arXiv2026

Cell as Point: One-Stage Framework for Efficient Cell Tracking

Conventional multi-stage cell tracking approaches rely heavily on detection or segmentation in each frame as a prerequisite, requiring substantial resources for high-quality segmentation masks and increasing the overall prediction time. To address these limitations, we propose CAP, a novel end-to-end one-stage framework that reimagines cell tracking by treating Cell as Point. Unlike traditional methods, CAP eliminates the need for explicit detection or segmentation, instead jointly tracking cells for sequences in one stage by leveraging the inherent correlations among their trajectories. This simplification reduces both labeling requirements and pipeline complexity. However, directly processing the entire sequence in one stage poses challenges related to data imbalance in capturing cell division events and long sequence inference. To solve these challenges, CAP introduces two key innovations: (1) adaptive event-guided (AEG) sampling, which prioritizes cell division events to mitigate the occurrence imbalance of cell events, and (2) the rolling-as-window (RAW) inference strategy, which ensures continuous and stable tracking of newly emerging cells over extended sequences. By removing the dependency on segmentation-based preprocessing while addressing the challenges of imbalanced occurrence of cell events and long-sequence tracking, CAP demonstrates promising cell tracking performance and is 8 to 32 times more efficient than existing methods. The code and model checkpoints are available at https://github.com/YXSong000/CAP.

eess.IV↗

arXiv2026

PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

Text-to-video (T2V) generation aims to synthesize videos with high visual quality and temporal consistency that are semantically aligned with input text. Reward-based post-training has emerged as a promising direction to improve the quality and semantic alignment of generated videos. However, recent methods either rely on large-scale human preference annotations or operate on misaligned embeddings from pre-trained vision-language models, leading to limited scalability or suboptimal supervision. We present $\texttt{PISCES}$, an annotation-free post-training algorithm that addresses these limitations via a novel Dual Optimal Transport (OT)-aligned Rewards module. To align reward signals with human judgment, $\texttt{PISCES}$ uses OT to bridge text and video embeddings at both distributional and discrete token levels, enabling reward supervision to fulfill two objectives: (i) a Distributional OT-aligned Quality Reward that captures overall visual quality and temporal coherence; and (ii) a Discrete Token-level OT-aligned Semantic Reward that enforces semantic, spatio-temporal correspondence between text and video tokens. To our knowledge, $\texttt{PISCES}$ is the first to improve annotation-free reward supervision in generative post-training through the lens of OT. Experiments on both short- and long-video generation show that $\texttt{PISCES}$ outperforms both annotation-based and annotation-free methods on VBench across Quality and Semantic scores, with human preference studies further validating its effectiveness. We show that the Dual OT-aligned Rewards module is compatible with multiple optimization paradigms, including direct backpropagation and reinforcement learning fine-tuning. Project page: https://roar-ai.github.io/pisces

cs.CV↗

arXiv2025

MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images

We present MatDecompSDF, a novel framework for recovering high-fidelity 3D shapes and decomposing their physically-based material properties from multi-view images. The core challenge of inverse rendering lies in the ill-posed disentanglement of geometry, materials, and illumination from 2D observations. Our method addresses this by jointly optimizing three neural components: a neural Signed Distance Function (SDF) to represent complex geometry, a spatially-varying neural field for predicting PBR material parameters (albedo, roughness, metallic), and an MLP-based model for capturing unknown environmental lighting. The key to our approach is a physically-based differentiable rendering layer that connects these 3D properties to the input images, allowing for end-to-end optimization. We introduce a set of carefully designed physical priors and geometric regularizations, including a material smoothness loss and an Eikonal loss, to effectively constrain the problem and achieve robust decomposition. Extensive experiments on both synthetic and real-world datasets (e.g., DTU) demonstrate that MatDecompSDF surpasses state-of-the-art methods in geometric accuracy, material fidelity, and novel view synthesis. Crucially, our method produces editable and relightable assets that can be seamlessly integrated into standard graphics pipelines, validating its practical utility for digital content creation.

cs.CV↗

arXiv2025

Step-GUI Technical Report

Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high-quality training data while maintaining annotation reliability? We introduce a self-evolving training pipeline powered by the Calibrated Step Reward System, which converts model-generated trajectories into reliable training signals through trajectory-level calibration, achieving >90% annotation accuracy with 10-100x lower cost. Leveraging this pipeline, we introduce Step-GUI, a family of models (4B/8B) that achieves state-of-the-art GUI performance (8B: 80.2% AndroidWorld, 48.5% OSWorld, 62.6% ScreenShot-Pro) while maintaining robust general capabilities. As GUI agent capabilities improve, practical deployment demands standardized interfaces across heterogeneous devices while protecting user privacy. To this end, we propose GUI-MCP, the first Model Context Protocol for GUI automation with hierarchical architecture that combines low-level atomic operations and high-level task delegation to local specialist models, enabling high-privacy execution where sensitive data stays on-device. Finally, to assess whether agents can handle authentic everyday usage, we introduce AndroidDaily, a benchmark grounded in real-world mobile usage patterns with 3146 static actions and 235 end-to-end tasks across high-frequency daily scenarios (8B: static 89.91%, end-to-end 52.50%). Our work advances the development of practical GUI agents and demonstrates strong potential for real-world deployment in everyday digital interactions.

cs.CV↗

arXiv2025

Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation

Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view discrepancy arises from supervision limited to pixel- or latent-space video-diffusion losses, which lack explicitly temporally aware, feature-level tracking guidance. We present \emph{Track4DGen}, a two-stage framework that couples a multi-view video diffusion model with a foundation point tracker and a hybrid 4D Gaussian Splatting (4D-GS) reconstructor. The central idea is to explicitly inject tracker-derived motion priors into intermediate feature representations for both multi-view video generation and 4D-GS. In Stage One, we enforce dense, feature-level point correspondences inside the diffusion generator, producing temporally consistent features that curb appearance drift and enhance cross-view coherence. In Stage Two, we reconstruct a dynamic 4D-GS using a hybrid motion encoding that concatenates co-located diffusion features (carrying Stage-One tracking priors) with Hex-plane features, and augment them with 4D Spherical Harmonics for higher-fidelity dynamics modeling. \emph{Track4DGen} surpasses baselines on both multi-view video generation and 4D generation benchmarks, yielding temporally stable, text-editable 4D assets. Lastly, we curate \emph{Sketchfab28}, a high-quality dataset for benchmarking object-centric 4D generation and fostering future research.

cs.CV↗

arXiv2025

Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding

Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning. However, effectively tokenizing 3D scenes into holistic scene tokens, and leveraging these tokens across diverse 3D understanding tasks, remain highly challenging. We present NDTokenizer3D, a generalist 3D VLM that performs a wide range of 3D scene understanding tasks while naturally supporting human interactions, thereby bridging language-level reasoning with 3D spatial understanding. The core of our approach is a novel three-stage scene tokenization pipeline built upon a Multi-Scale Normal Distributions Transform (NDT) representation, paired with a Multi-Scale NDT Decoder (MSDec). Specifically, NDTokenizer3D first constructs a multi-scale NDT representation from raw high-resolution point clouds, preserving both global context and fine-grained geometric details. Next, the MSDec progressively fuses cross-scale NDT features, producing holistic scene tokens consumable by LLM endpoints. Beyond tokenization, MSDec is repurposed as a general interface for human-interactive prompting (points, boxes, masks) and segmentation-mask decoding, unifying diverse 3D scene understanding tasks within a single architecture. With this compact and unified design, NDTokenizer3D offers a fine-grained, general-purpose 3D VLM, achieving remarkable improvements in 3D Referring Segmentation, 3D Visual Question Answering, and 3D Dense Captioning.

cs.CV↗

arXiv2025

Beta Distribution Learning for Reliable Roadway Crash Risk Assessment

Roadway traffic accidents represent a global health crisis, responsible for over a million deaths annually and costing many countries up to 3% of their GDP. Traditional traffic safety studies often examine risk factors in isolation, overlooking the spatial complexity and contextual interactions inherent in the built environment. Furthermore, conventional Neural Network-based risk estimators typically generate point estimates without conveying model uncertainty, limiting their utility in critical decision-making. To address these shortcomings, we introduce a novel geospatial deep learning framework that leverages satellite imagery as a comprehensive spatial input. This approach enables the model to capture the nuanced spatial patterns and embedded environmental risk factors that contribute to fatal crash risks. Rather than producing a single deterministic output, our model estimates a full Beta probability distribution over fatal crash risk, yielding accurate and uncertainty-aware predictions--a critical feature for trustworthy AI in safety-critical applications. Our model outperforms baselines by achieving a 17-23% improvement in recall, a key metric for flagging potential dangers, while delivering superior calibration. By providing reliable and interpretable risk assessments from satellite imagery alone, our method enables safer autonomous navigation and offers a highly scalable tool for urban planners and policymakers to enhance roadway safety equitably and cost-effectively.

cs.CV↗

arXiv2025

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.

cs.CV↗

arXiv2025

Improving Crash Data Quality with Large Language Models: Evidence from Secondary Crash Narratives in Kentucky

This study evaluates advanced natural language processing (NLP) techniques to enhance crash data quality by mining crash narratives, using secondary crash identification in Kentucky as a case study. Drawing from 16,656 manually reviewed narratives from 2015-2022, with 3,803 confirmed secondary crashes, we compare three model classes: zero-shot open-source large language models (LLMs) (LLaMA3:70B, DeepSeek-R1:70B, Qwen3:32B, Gemma3:27B); fine-tuned transformers (BERT, DistilBERT, RoBERTa, XLNet, Longformer); and traditional logistic regression as baseline. Models were calibrated on 2015-2021 data and tested on 1,771 narratives from 2022. Fine-tuned transformers achieved superior performance, with RoBERTa yielding the highest F1-score (0.90) and accuracy (95%). Zero-shot LLaMA3:70B reached a comparable F1 of 0.86 but required 139 minutes of inference; the logistic baseline lagged well behind (F1:0.66). LLMs excelled in recall for some variants (e.g., GEMMA3:27B at 0.94) but incurred high computational costs (up to 723 minutes for DeepSeek-R1:70B), while fine-tuned models processed the test set in seconds after brief training. Further analysis indicated that mid-sized LLMs (e.g., DeepSeek-R1:32B) can rival larger counterparts in performance while reducing runtime, suggesting opportunities for optimized deployments. Results highlight trade-offs between accuracy, efficiency, and data requirements, with fine-tuned transformer models balancing precision and recall effectively on Kentucky data. Practical deployment considerations emphasize privacy-preserving local deployment, ensemble approaches for improved accuracy, and incremental processing for scalability, providing a replicable scheme for enhancing crash-data quality with advanced NLP.

cs.CL↗

arXiv2025

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.

cs.LG↗

arXiv2025

Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce $\textbf{Hummingbird}$, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the reference image while ensuring high fidelity by accurately preserving scene attributes, such as object interactions and spatial relationships from the text guidance. Hummingbird employs a novel Multimodal Context Evaluator that simultaneously optimizes our formulated Global Semantic and Fine-grained Consistency Rewards to ensure generated images preserve the scene attributes of reference images in relation to the text guidance while maintaining diversity. As the first model to address the task of maintaining both diversity and fidelity given a multimodal context, we introduce a new benchmark formulation incorporating MME Perception and Bongard HOI datasets. Benchmark experiments show Hummingbird outperforms all existing methods by achieving superior fidelity while maintaining diversity, validating Hummingbird's potential as a robust multimodal context-aligned image generator in complex visual tasks. Project page: https://roar-ai.github.io/hummingbird

cs.CV↗

arXiv2025

DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos

Long Video Temporal Grounding (LVTG) aims at identifying specific moments within lengthy videos based on user-provided text queries for effective content retrieval. The approach taken by existing methods of dividing video into clips and processing each clip via a full-scale expert encoder is challenging to scale due to prohibitive computational costs of processing a large number of clips in long videos. To address this issue, we introduce DeCafNet, an approach employing ``delegate-and-conquer'' strategy to achieve computation efficiency without sacrificing grounding performance. DeCafNet introduces a sidekick encoder that performs dense feature extraction over all video clips in a resource-efficient manner, while generating a saliency map to identify the most relevant clips for full processing by the expert encoder. To effectively leverage features from sidekick and expert encoders that exist at different temporal resolutions, we introduce DeCaf-Grounder, which unifies and refines them via query-aware temporal aggregation and multi-scale temporal refinement for accurate grounding. Experiments on two LTVG benchmark datasets demonstrate that DeCafNet reduces computation by up to 47\% while still outperforming existing methods, establishing a new state-of-the-art for LTVG in terms of both efficiency and performance. Our code is available at https://github.com/ZijiaLewisLu/CVPR2025-DeCafNet.

cs.CV↗

arXiv2025

Defense against Prompt Injection Attacks via Mixture of Encodings

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt injection attacks, where external content embeds malicious instructions that manipulate the LLM's output. Recently, the Base64 defense has been recognized as one of the most effective methods for reducing success rate of prompt injection attacks. Despite its efficacy, this method can degrade LLM performance on certain NLP tasks. To address this challenge, we propose a novel defense mechanism: mixture of encodings, which utilizes multiple character encodings, including Base64. Extensive experimental results show that our method achieves one of the lowest attack success rates under prompt injection attacks, while maintaining high performance across all NLP tasks, outperforming existing character encoding-based defense methods. This underscores the effectiveness of our mixture of encodings strategy for both safety and task performance metrics.

cs.CL↗