arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 109 records · Page 6Linked to original sources

arXiv2026

What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution

Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Synthetic data offers a cost-effective and perfectly labeled alternative. However, its performance often lags behind, revealing a significant domain gap between real and current synthetic data. In this work, we systematically analyze mainstream rendering-based synthetic datasets and identify their key limitations: insufficient diversity in corpus, font, and layout, which restricts their realism in complex scenarios. To address these issues, we introduce UnionST, a strong data engine synthesizes text covering a union of challenging samples and better aligns with the complexity observed in the wild. We then construct UnionST-S, a large-scale synthetic dataset with improved simulations in challenging scenarios. Furthermore, we develop a self-evolution learning (SEL) framework for effective real data annotation. Experiments show that models trained on UnionST-S achieve significant improvements over existing synthetic datasets. They even surpass real-data performance in certain scenarios. Moreover, when using SEL, the trained models achieve competitive performance by only seeing 9% of real data labels. Code is available at https://github.com/YesianRohn/UnionST.

cs.CV↗

arXiv2026

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).

cs.CV↗

arXiv2026

Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model ($\text{R}^2$VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train $\text{R}^2$VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that $\text{R}^2$VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at \href{https://huggingface.co/collections/zhangyuelin/r2vlm}{huggingface}.

cs.CV↗

arXiv2026

CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis

Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to capture the coherent tissue architecture beyond isolated patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that automatically partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the most representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.

cs.CV↗

arXiv2026

Partially Recentralization Softmax Loss for Vision-Language Models Robustness

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input. While several defense techniques have been proposed both in computer vision and NLP models, the multimodal robustness of models have not been fully explored. In this paper, we study the adversarial robustness provided by modifying loss function of pre-trained multimodal models, by restricting top K softmax outputs. Based on the evaluation and scoring, our experiments show that after a fine-tuning, adversarial robustness of pre-trained models can be significantly improved, against popular attacks. Further research should be studying, such as output diversity, generalization and the robustness-performance trade-off of this kind of loss functions. Our code will be available after this paper is accepted

cs.CL↗

arXiv2026

GazeMoE: Perception of Gaze Target with Mixture-of-Experts

Estimating human gaze target from visible images is a critical task for robots to understand human attention, yet the development of generalizable neural architectures and training paradigms remains challenging. While recent advances in pre-trained vision foundation models offer promising avenues for locating gaze targets, the integration of multi-modal cues -- including eyes, head poses, gestures, and contextual features -- demands adaptive and efficient decoding mechanisms. Inspired by Mixture-of-Experts (MoE) for adaptive domain expertise in large vision-language models, we propose GazeMoE, a novel end-to-end framework that selectively leverages gaze-target-related cues from a frozen foundation model through MoE modules. To address class imbalance in gaze target classification (in-frame vs. out-of-frame) and enhance robustness, GazeMoE incorporates a class-balancing auxiliary loss alongside strategic data augmentations, including region-specific cropping and photometric transformations. Extensive experiments on benchmark datasets demonstrate that our GazeMoE achieves state-of-the-art performance, outperforming existing methods on challenging gaze estimation tasks. The code and pre-trained models are released at https://huggingface.co/zdai257/GazeMoE

cs.CV↗

arXiv2026

NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing

Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly challenging and constitutes a critical bottleneck, especially for local video editing data. Existing workarounds transfer image editing to video through global motion control for pair-free video editing, but such designs struggle with background and temporal consistency. In this paper, we propose NOVA: Sparse Control \& Dense Synthesis, a new framework for unpaired video editing. Specifically, the sparse branch provides semantic guidance through user-edited keyframes distributed across the video, and the dense branch continuously incorporates motion and texture information from the original video to maintain high fidelity and coherence. Moreover, we introduce a degradation-simulation training strategy that enables the model to learn motion reconstruction and temporal consistency by training on artificially degraded videos, thus eliminating the need for paired data. Our extensive experiments demonstrate that NOVA outperforms existing approaches in edit fidelity, motion preservation, and temporal coherence.

cs.CV↗

arXiv2026

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

cs.LG↗

arXiv2026

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction

Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction fidelity. To fill this gap, we introduce a powerful and concise WeTok tokenizer, which surpasses the previous leading tokenizers via two core innovations. (1) Group-wise lookup-free Quantization (GQ). We partition the latent features into groups, and perform lookup-free quantization for each group. As a result, GQ can efficiently overcome memory and computation limitations of prior tokenizers, while achieving a reconstruction breakthrough with more scalable codebooks. (2) Generative Decoder (GD). Different from prior tokenizers, we introduce a generative decoder with a prior of extra noise variable. In this case, GD can probabilistically model the distribution of visual data conditioned on discrete tokens, allowing WeTok to reconstruct visual details, especially at high compression ratio. On the ImageNet 50k validation set, at a high-fidelity setting, WeTok achieves a record-low zero-shot rFID of 0.12, outperforming leading continuous tokenizers like FLUX-VAE (0.18) and SD-VAE 3.5 (0.19) with 400% compression ratio. Furthermore, in a high-compression regime, WeTok achieves a zero-shot rFID of 3.49 at a 768$\times$ compression ratio, substantially surpassing Cosmos, which scores 4.57 at only 50% our compression ratio. Code and models are available: https://github.com/zhuangshaobin/WeTok.

cs.CV↗

arXiv2026

STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision

Vision-language models (VLMs) have made significant strides in reasoning, yet they often struggle with complex multimodal tasks and tend to generate overly verbose outputs. A key limitation is their reliance on chain-of-thought (CoT) reasoning, despite many tasks benefiting from alternative topologies like trees or graphs. To address this, we introduce STELAR-Vision, a training framework for topology-aware reasoning. At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures. Using supervised fine-tuning and reinforcement learning, we post-train Qwen2VL models with both accuracy and efficiency in mind. Additionally, we propose Frugal Learning, which reduces output length with minimal accuracy loss. On MATH-V and VLM-S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%. On five out-of-distribution benchmarks, it outperforms Phi-4-Multimodal-Instruct by up to 28.4% and LLaMA-3.2-11B-Vision-Instruct by up to 13.2%, demonstrating strong generalization. Compared to Chain-Only training, our approach achieves 4.3% higher overall accuracy on in-distribution datasets and consistently outperforms across all OOD benchmarks.

cs.AI↗

arXiv2026

Improving Reconstruction of Representation Autoencoder

Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are easy to learn. However, such semantic features often lack low-level information (\eg, color and texture), leading to degraded reconstruction fidelity, which has emerged as a primary bottleneck in further scaling LDMs. To address this limitation, we propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information, enabling high-fidelity reconstruction while remaining highly aligned with the semantic distribution. We further observe that the resulting high-dimensional, information-rich latent make decoders sensitive to latent perturbations, causing severe artifacts when decoding generated latent and consequently degrading generation quality. Our analysis suggests that this sensitivity primarily stems from excessive decoder responses along directions off the data manifold. Building on these insights, we propose fine-tuning the decoder to increase its robustness and smoothing the generated latent via controlled noise injection, thereby enhancing generation quality. Experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction and achieving strong generative quality. Our code is available at https://github.com/modyu-liu/LVRAE.

cs.CV↗

arXiv2026

R2LED: Equipping Retrieval and Refinement in Lifelong User Modeling with Semantic IDs for CTR Prediction

Lifelong user modeling, which leverages users' long-term behavior sequences for CTR prediction, has been widely applied in personalized services. Existing methods generally adopted a two-stage "retrieval-refinement" strategy to balance effectiveness and efficiency. However, they still suffer from (i) noisy retrieval due to skewed data distribution and (ii) lack of semantic understanding in refinement. While semantic enhancement, e.g., LLMs modeling or semantic embeddings, offers potential solutions to these two challenges, these approaches face impractical inference costs or insufficient representation granularity. Obsorbing multi-granularity and lightness merits of semantic identity (SID), we propose a novel paradigm that equips retrieval and refinement in Lifelong User Modeling with SEmantic IDs (R2LED) to address these issues. First, we introduce a Multi-route Mixed Retrieval for the retrieval stage. On the one hand, it captures users' interests from various granularities by several parallel recall routes. On the other hand, a mixed retrieval mechanism is proposed to efficiently retrieve candidates from both collaborative and semantic views, reducing noise. Then, for refinement, we design a Bi-level Fusion Refinement, including a target-aware cross-attention for route-level fusion and a gate mechanism for SID-level fusion. It can bridge the gap between semantic and collaborative spaces, exerting the merits of SID. The comprehensive experimental results on two public datasets demonstrate the superiority of our method in both performance and efficiency. To facilitate the reproduction, we have released the code online https://github.com/abananbao/R2LED.

cs.IR↗

arXiv2026

Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search

Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, current approaches remain predominantly stateless, discarding successful reasoning patterns after each problem instance and failing to mimic the empirical accumulation of wisdom characteristic of human problem-solving. To bridge this gap, we introduce Empirical-MCTS, a dual-loop framework that transforms stateless search into a continuous, non-parametric learning process. The framework unifies local exploration with global memory optimization through two novel mechanisms: Pairwise-Experience-Evolutionary Meta-Prompting (PE-EMP) and a Memory Optimization Agent. PE-EMP functions as a reflexive optimizer within the local search, utilizing pairwise feedback to dynamically synthesize adaptive criteria and evolve meta-prompts (system prompts) in real-time. Simultaneously, the Memory Optimization Agent manages a global repository as a dynamic policy prior, employing atomic operations to distill high-quality insights across problems. Extensive evaluations on complex reasoning benchmarks, including AIME25, ARC-AGI-2, and MathArena Apex, demonstrate that Empirical-MCTS significantly outperforms both stateless MCTS strategies and standalone experience-driven agents. These results underscore the critical necessity of coupling structured search with empirical accumulation for mastering complex, open-ended reasoning tasks.

cs.AI↗

arXiv2026

TaskAudit: Detecting Functiona11ity Errors in Mobile Apps via Agentic Task Execution

Accessibility checkers are tools in support of accessible app development, and their use is encouraged by accessibility best practices. However, most current checkers evaluate static or mechanically-generated contexts, failing to capture common accessibility errors impacting mobile app functionality. In this work, we define functiona11ity errors as accessibility barriers that only manifest through interaction (i.e., named according to a blend of "functionality" and "accessibility"). We introduce TaskAudit, which comprises three components: a Task Generator that constructs interactive tasks from app screens, a Task Executor that uses agents with a screen reader proxy to perform these tasks, and an Accessibility Analyzer that detects and reports accessibility errors by examining interaction traces. Our evaluation on real-world apps shows that TaskAudit detects 48 functiona11ity errors from 54 app screens, compared to between 4 and 20 with existing checkers. Our analysis demonstrates common error patterns that TaskAudit can detect in addition to those from prior work, including label-functionality mismatch, cluttered navigation, and inappropriate feedback.

cs.HC↗

arXiv2026

FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering

Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical applications. Existing detection methods mainly fall into two categories: external verification approaches relying on auxiliary models or knowledge bases, and uncertainty-driven approaches using repeated sampling or uncertainty estimates. The former suffer from high computational overhead and are limited by external resource quality, while the latter capture only limited facets of model uncertainty and fail to sufficiently explore the rich internal signals associated with the diverse failure modes. Both paradigms thus have inherent limitations in efficiency, robustness, and detection performance. To address these challenges, we propose FaithSCAN: a lightweight network that detects hallucinations by exploiting rich internal signals of VLMs, including token-level decoding uncertainty, intermediate visual representations, and cross-modal alignment features. These signals are fused via branch-wise evidence encoding and uncertainty-aware attention. We also extend the LLM-as-a-Judge paradigm to VQA hallucination and propose a low-cost strategy to automatically generate model-dependent supervision signals, enabling supervised training without costly human labels while maintaining high detection accuracy. Experiments on multiple VQA benchmarks show that FaithSCAN significantly outperforms existing methods in both effectiveness and efficiency. In-depth analysis shows hallucinations arise from systematic internal state variations in visual perception, cross-modal reasoning, and language decoding. Different internal signals provide complementary diagnostic cues, and hallucination patterns vary across VLM architectures, offering new insights into the underlying causes of multimodal hallucinations.

cs.CV↗

arXiv2026

Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA

Decentralized federated learning (DFL), a serverless variant of federated learning, poses unique challenges for parameter-efficient fine-tuning due to the factorized structure of low-rank adaptation (LoRA). Unlike linear parameters, decentralized aggregation of LoRA updates introduces topology-dependent cross terms that can destabilize training under dynamic communication graphs. We propose \texttt{TAD-LoRA}, a Topology-Aware Decentralized Low-Rank Adaptation framework that coordinates the updates and mixing of LoRA factors to control inter-client misalignment. We theoretically prove the convergence of \texttt{TAD-LoRA} under non-convex objectives, explicitly characterizing the trade-off between topology-induced cross-term error and block-coordinate representation bias governed by the switching interval of alternative training. Experiments under various communication conditions validate our analysis, showing that \texttt{TAD-LoRA} achieves robust performance across different communication scenarios, remaining competitive in strongly connected topologies and delivering clear gains under moderately and weakly connected topologies, with particularly strong results on the MNLI dataset.

cs.LG↗

arXiv2026

MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption

Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA, a unified, backbone-agnostic post-training framework for efficient and scalable alignment. MetaVLA introduces Context-Aware Meta Co-Training, which consolidates diverse target tasks into a single fine-tuning stage while leveraging structurally diverse auxiliary tasks to improve in-domain generalization. Unlike naive multi-task SFT, MetaVLA integrates a lightweight meta-learning mechanism-derived from Attentive Neural Processes-to enable rapid adaptation from diverse contexts with minimal architectural change or inference overhead. On the LIBERO benchmark, MetaVLA with six auxiliary tasks outperforms OpenVLA by up to 8.0% on long-horizon tasks, reduces training steps from 240K to 75K, and cuts GPU time by ~76%. These results show that scalable, low-resource post-training is achievable-paving the way toward general-purpose embodied agents. Code will be available.

cs.AI↗

arXiv2026

HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection

Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global slide contexts - drive expert diagnostic reasoning. While Vision-Language (V-L) models promise data efficiency by leveraging semantic priors, adapting them faces a critical Granularity Mismatch, where generic representations fail to resolve such subtle defects. Current adaptation methods often treat modalities as independent streams, failing to ground semantic prompts in ROI-specific visual contexts. To bridge this gap, we propose the Hierarchical Adaptation and Alignment Framework (HAAF). At its core is a novel Cross-Level Scaled Alignment (CLSA) mechanism that enforces a sequential calibration order: visual features first inject context into text prompts to generate content-adaptive descriptors, which then spatially guide the visual encoder to spotlight anomalies. Additionally, a dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings. Experiments on four benchmarks show HAAF significantly outperforms state-of-the-art methods and effectively scales with domain-specific backbones (e.g., CONCH) in low-resource scenarios.

cs.CV↗