arXiv subjects

En Yu

Publications and source records attributed to En Yu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction

Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superior understanding of environmental dynamics via authentic feedback, current approaches often impose a rigid reasoning process, which constrains the model's active learning, ultimately hindering efficient world model reasoning. To address these issues, we explore world-model internalization through efficient interaction and active reasoning (WMAct), which liberates the model from structured reasoning, allowing the model to shape thinking directly through its doing, and achieves effective and efficient world model reasoning with two key mechanisms: (1) a reward rescaling mechanism adjusting outcome reward based on action efficacy to incentivize redundancy reduction and purposeful interaction; (2) an interaction frequency annealing strategy to progressively reduce the maximum allowed interaction turns, which compels the model to condense its learning and internalize environmental dynamics rather than over-relying on environmental cues. Our experiments on Sokoban, Maze, and Taxi show that WMAct yields effective world model reasoning capable of resolving tasks in a single turn that previously required multiple interactions and fosters strong transferability to complex environments, improving performance on a suite of reasoning benchmarks.

cs.AI↗

arXiv2025

Autonomous Concept Drift Threshold Determination

Existing drift detection methods focus on designing sensitive test statistics. They treat the detection threshold as a fixed hyperparameter, set once to balance false alarms and late detections, and applied uniformly across all datasets and over time. However, maintaining model performance is the key objective from the perspective of machine learning, and we observe that model performance is highly sensitive to this threshold. This observation inspires us to investigate whether a dynamic threshold could be provably better. In this paper, we prove that a threshold that adapts over time can outperform any single fixed threshold. The main idea of the proof is that a dynamic strategy, constructed by combining the best threshold from each individual data segment, is guaranteed to outperform any single threshold that apply to all segments. Based on the theorem, we propose a Dynamic Threshold Determination algorithm. It enhances existing drift detection frameworks with a novel comparison phase to inform how the threshold should be adjusted. Extensive experiments on a wide range of synthetic and real-world datasets, including both image and tabular data, validate that our approach substantially enhances the performance of state-of-the-art drift detectors.

cs.LG↗

arXiv2025

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments

This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory. We propose Autonomous Preference Optimization (APO), a novel framework that treats inter-model divergences not as noise, but as dynamic negative constraints. APO operates via a two-stage protocol: first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative Plackett-Luce objective. Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark comprising 170,982 reasoning trajectories from seven large-scale MLLMs to facilitate research on reasoning alignment under drift. Code and data are available at: https://github.com/XiaoyuYoung/APO.

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

Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learning

Learning from multiple data streams in real-world scenarios is fundamentally challenging due to intrinsic heterogeneity and unpredictable concept drifts. Existing methods typically assume homogeneous streams and employ static architectures with indiscriminate knowledge fusion, limiting generalizability in complex dynamic environments. To tackle this gap, we propose CAMEL, a dynamic \textbf{C}ollaborative \textbf{A}ssistance \textbf{M}ixture of \textbf{E}xperts \textbf{L}earning framework. It addresses heterogeneity by assigning each stream an independent system with a dedicated feature extractor and task-specific head. Meanwhile, a dynamic pool of specialized private experts captures stream-specific idiosyncratic patterns. Crucially, collaboration across these heterogeneous streams is enabled by a dedicated assistance expert. This expert employs a multi-head attention mechanism to distill and integrate relevant context autonomously from all other concurrent streams. It facilitates targeted knowledge transfer while inherently mitigating negative transfer from irrelevant sources. Furthermore, we propose an Autonomous Expert Tuner (AET) strategy, which dynamically manages expert lifecycles in response to drift. It instantiates new experts for emerging concepts (freezing prior ones to prevent catastrophic forgetting) and prunes obsolete ones. This expert-level plasticity provides a robust and efficient mechanism for online model capacity adaptation. Extensive experiments demonstrate CAMEL's superior generalizability across diverse multistreams and exceptional resilience against complex concept drifts.

cs.LG↗

arXiv2025

Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion

3D Semantic Scene Completion (SSC) has gained increasing attention due to its pivotal role in 3D perception. Recent advancements have primarily focused on refining voxel-level features to construct 3D scenes. However, treating voxels as the basic interaction units inherently limits the utilization of class-level information, which is proven critical for enhancing the granularity of completion results. To address this, we propose \textbf{D}isentangling Instance and Scene Contexts (DISC), a novel dual-stream paradigm that enhances learning for both instance and scene categories through separated optimization. Specifically, we replace voxel queries with discriminative class queries, which incorporate class-specific geometric and semantic priors. Additionally, we exploit the intrinsic properties of classes to design specialized decoding modules, facilitating targeted interactions and efficient class-level information flow. Experimental results demonstrate that DISC achieves state-of-the-art (SOTA) performance on both SemanticKITTI and SSCBench-KITTI-360 benchmarks, with mIoU scores of 17.35 and 20.55, respectively. Remarkably, DISC even outperforms multi-frame SOTA methods using only single-frame input and significantly improves instance category performance, surpassing both single-frame and multi-frame SOTA instance mIoU by 17.9\% and 11.9\%, respectively, on the SemanticKITTI hidden test. The code is available at https://github.com/Enyu-Liu/DISC.

cs.CV↗

arXiv2025

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2.5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1,000 steps, surpassing all previous open-source efforts in scale. This pioneering work reveals three fundamental insights: 1) Behavior transfer emerges surprisingly early in cold start due to linguistic mental imagery. 2) Cold start broadly memorizes visual behaviors, while RL critically discerns and scales up effective patterns. 3) Transfer strategically favors high-utility behaviors such as visual reflection. Our resulting model, Open-Vision-Reasoner (OVR), achieves state-of-the-art performance on a suite of reasoning benchmarks, including 95.3% on MATH500, 51.8% on MathVision and 54.6% on MathVerse. We release our model, data, and training dynamics to catalyze the development of more capable, behavior-aligned multimodal reasoners.

cs.CV↗

arXiv2025

Generalized Incremental Learning under Concept Drift across Evolving Data Streams

Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods address isolated distribution shifts, they overlook the critical co-evolution of label spaces and distributions under limited supervision and persistent uncertainty. To address this, we formalize Generalized Incremental Learning under Concept Drift (GILCD), characterizing the joint evolution of distributions and label spaces in open-environment streaming contexts, and propose a novel framework called Calibrated Source-Free Adaptation (CSFA). First, CSFA introduces a training-free prototype calibration mechanism that dynamically fuses emerging prototypes with base representations, enabling stable new-class identification without optimization overhead. Second, we design a novel source-free adaptation algorithm, i.e., Reliable Surrogate Gap Sharpness-aware (RSGS) minimization. It integrates sharpness-aware perturbation loss optimization with surrogate gap minimization, while employing entropy-based uncertainty filtering to discard unreliable samples. This mechanism ensures robust distribution alignment and mitigates generalization degradation caused by uncertainties. Thus, CSFA establishes a unified framework for stable adaptation to evolving semantics and distributions in open-world streaming scenarios. Extensive experiments validate the superior performance and effectiveness of CSFA compared to SOTA approaches.

cs.LG↗

arXiv2025

ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object Tracking

Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on explicit visual-textual matching and consequently fail to generalize to complex instructions that require logical reasoning. To overcome this, we propose Reasoning-based Multi-Object Tracking (ReaMOT), a novel task that elevates tracking to a cognitive level, requiring models to infer and track specific targets satisfying implicit constraints via logical reasoning. To advance this field, we construct the ReaMOT Challenge, a comprehensive benchmark featuring a tailored metric suite and a large scale dataset. This dataset comprises 1,156 language instructions, 423,359 image language pairs, and 869 distinct video sequences systematically categorized into six distinct evaluation scenarios, with over 75\% of the instructions dedicated to High Level Reasoning. Furthermore, recognizing that traditional trackers lack cognitive capacity while direct application of Large Vision-Language Model (LVLM) yields severe temporal inconsistencies, we propose ReaTrack. Driven by the insight to decouple high-level cognitive localization from low-level physical motion continuity, this training-free framework dynamically aligns the semantic detections of a Thinking-variant LVLM with the robust motion priors of SAM2. Extensive experiments on the ReaMOT Challenge benchmark demonstrate that ReaTrack establishes a new leading performance standard. Notably, it achieves a more than threefold improvement in RHOTA on the High Level Reasoning subset. Our dataset and code will be available at https://github.com/chen-si-jia/ReaMOT.

cs.CV↗

arXiv2025

Learning Robust Spectral Dynamics for Temporal Domain Generalization

Modern machine learning models struggle to maintain performance in dynamic environments where temporal distribution shifts, \emph{i.e., concept drift}, are prevalent. Temporal Domain Generalization (TDG) seeks to enable model generalization across evolving domains, yet existing approaches typically assume smooth incremental changes, struggling with complex real-world drifts involving long-term structure (incremental evolution/periodicity) and local uncertainties. To overcome these limitations, we introduce FreKoo, which tackles these challenges via a novel frequency-domain analysis of parameter trajectories. It leverages the Fourier transform to disentangle parameter evolution into distinct spectral bands. Specifically, low-frequency component with dominant dynamics are learned and extrapolated using the Koopman operator, robustly capturing diverse drift patterns including both incremental and periodicity. Simultaneously, potentially disruptive high-frequency variations are smoothed via targeted temporal regularization, preventing overfitting to transient noise and domain uncertainties. In addition, this dual spectral strategy is rigorously grounded through theoretical analysis, providing stability guarantees for the Koopman prediction, a principled Bayesian justification for the high-frequency regularization, and culminating in a multiscale generalization bound connecting spectral dynamics to improved generalization. Extensive experiments demonstrate FreKoo's significant superiority over SOTA TDG approaches, particularly excelling in real-world streaming scenarios with complex drifts and uncertainties.

cs.LG↗

arXiv2025

Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning

This paper uncovers a critical yet overlooked phenomenon in multi-modal large language models (MLLMs): detrimental concept drift within chain-of-thought (CoT) reasoning during non-stationary reinforcement fine-tuning (RFT), where reasoning token distributions evolve unpredictably, thereby introducing significant biases in final predictions. To address this, we are pioneers in establishing the theoretical bridge between concept drift theory and RFT processes by formalizing CoT's autoregressive token streams as non-stationary distributions undergoing arbitrary temporal shifts. Leveraging this framework, we propose a novel counterfact-aware RFT that systematically decouples beneficial distribution adaptation from harmful concept drift through concept graph-empowered LLM experts generating counterfactual reasoning trajectories. Our solution, Counterfactual Preference Optimization (CPO), enables stable RFT in non-stationary environments, particularly within the medical domain, through custom-tuning of counterfactual-aware preference alignment. Extensive experiments demonstrate our superior performance of robustness, generalization and coordination within RFT. Besides, we also contributed a large-scale dataset CXR-CounterFact (CCF), comprising 320,416 meticulously curated counterfactual reasoning trajectories derived from MIMIC-CXR. Our code and data are public.

cs.LG↗

arXiv2025

Perception-R1: Pioneering Perception Policy with Reinforcement Learning

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking process through RL does not consistently lead to performance gains across all visual perception tasks. This leads us to delve into the essential role of RL in the context of visual perception. In this work, we return to the fundamentals and explore the effects of RL on different perception tasks. We observe that the perceptual complexity is a major factor in determining the effectiveness of RL. We also observe that reward design plays a crucial role in further approching the upper limit of model perception. To leverage these findings, we propose Perception-R1, a scalable RL framework using GRPO during MLLM post-training. With a standard Qwen2.5-VL-3B-Instruct, Perception-R1 achieves +4.2% on RefCOCO+, +17.9% on PixMo-Count, +4.2% on PageOCR, and notably, 31.9% AP on COCO2017 val for the first time, establishing a strong baseline for perception policy learning.

cs.CV↗

arXiv2025

Perception in Reflection

We present a perception in reflection paradigm designed to transcend the limitations of current large vision-language models (LVLMs), which are expected yet often fail to achieve perfect perception initially. Specifically, we propose Reflective Perception (RePer), a dual-model reflection mechanism that systematically alternates between policy and critic models, enables iterative refinement of visual perception. This framework is powered by Reflective Perceptual Learning (RPL), which reinforces intrinsic reflective capabilities through a methodically constructed visual reflection dataset and reflective unlikelihood training. Comprehensive experimental evaluation demonstrates RePer's quantifiable improvements in image understanding, captioning precision, and hallucination reduction. Notably, RePer achieves strong alignment between model attention patterns and human visual focus, while RPL optimizes fine-grained and free-form preference alignment. These advancements establish perception in reflection as a robust paradigm for future multimodal agents, particularly in tasks requiring complex reasoning and multi-step manipulation.

cs.CV↗

arXiv2025

OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracker is constrained by its framework structure, isolated frame-level perception, and insufficient modal interactions, which hinder its performance in open-vocabulary classification and tracking. In this paper, we propose OVTR (End-to-End Open-Vocabulary Multiple Object Tracking with TRansformer), the first end-to-end open-vocabulary tracker that models motion, appearance, and category simultaneously. To achieve stable classification and continuous tracking, we design the CIP (Category Information Propagation) strategy, which establishes multiple high-level category information priors for subsequent frames. Additionally, we introduce a dual-branch structure for generalization capability and deep multimodal interaction, and incorporate protective strategies in the decoder to enhance performance. Experimental results show that our method surpasses previous trackers on the open-vocabulary MOT benchmark while also achieving faster inference speeds and significantly reducing preprocessing requirements. Moreover, the experiment transferring the model to another dataset demonstrates its strong adaptability. Models and code are released at https://github.com/jinyanglii/OVTR.

cs.CV↗

arXiv2025

InstaFace: Identity-Preserving Facial Editing with Single Image Inference

Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, preserving identity with generative models is challenging, especially in scenarios with limited data availability. Traditional methods often require multiple images and still struggle with unnatural face shifts, inconsistent hair alignment, or excessive smoothing effects. To overcome these challenges, we introduce a novel diffusion-based framework, InstaFace, to generate realistic images while preserving identity using only a single image. Central to InstaFace, we introduce an efficient guidance network that harnesses 3D perspectives by integrating multiple 3DMM-based conditionals without introducing additional trainable parameters. Moreover, to ensure maximum identity retention as well as preservation of background, hair, and other contextual features like accessories, we introduce a novel module that utilizes feature embeddings from a facial recognition model and a pre-trained vision-language model. Quantitative evaluations demonstrate that our method outperforms several state-of-the-art approaches in terms of identity preservation, photorealism, and effective control of pose, expression, and lighting.

cs.CV↗

arXiv2025

Unhackable Temporal Rewarding for Scalable Video MLLMs

In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the "anti-scaling law", where more data and larger models lead to worse performance. This study unmasks the culprit: "temporal hacking", a phenomenon where models shortcut by fixating on select frames, missing the full video narrative. In this work, we systematically establish a comprehensive theory of temporal hacking, defining it from a reinforcement learning perspective, introducing the Temporal Perplexity (TPL) score to assess this misalignment, and proposing the Unhackable Temporal Rewarding (UTR) framework to mitigate the temporal hacking. Both theoretically and empirically, TPL proves to be a reliable indicator of temporal modeling quality, correlating strongly with frame activation patterns. Extensive experiments reveal that UTR not only counters temporal hacking but significantly elevates video comprehension capabilities. This work not only advances video-AI systems but also illuminates the critical importance of aligning proxy rewards with true objectives in MLLM development.

cs.CV↗

arXiv2025

Resilient Contrastive Pre-training under Non-Stationary Drift

The remarkable success of large-scale contrastive pre-training has been largely driven by by vast yet static datasets. However, as the scaling paradigm evolves, this paradigm encounters a fundamental challenge when applied to dynamic data streams characterized by concept drift - unpredictable changes in the underlying data distribution. This paper aims to advance robust pre-training under such non-stationary environments. We begin by revealing that conventional contrastive pre-training methods are highly susceptible to concept drift, resulting in significant substantial bias and instability within the learned feature representations. To systematically analyze these effects, we develop a structural causal model that elucidates how drift acts as a confounder, distorting the learned representations. Based on these causal insights, we propose Resilient Contrastive Pre-training (RCP), a novel method that incorporates causal intervention. RCP formulates a causally-informed objective to mitigate drift-induced biases through targeted interventions. The method is designed for simple and scalable implementation and exhibits notable adaptability, promoting robust and autonomous pre-training on non-stationary data. Comprehensive experiments across various downstream tasks consistently demonstrate that RCP effectively alleviates the detrimental impact of concept drift, yielding more resilient and generalizable representations.

cs.LG↗

arXiv2025

PerPO: Perceptual Preference Optimization via Discriminative Rewarding

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with human visual perception process, PerPO employs discriminative rewarding to gather diverse negative samples, followed by listwise preference optimization to rank them.By utilizing the reward as a quantitative margin for ranking, our method effectively bridges generative preference optimization and discriminative empirical risk minimization. PerPO significantly enhances MLLMs' visual discrimination capabilities while maintaining their generative strengths, mitigates image-unconditional reward hacking, and ensures consistent performance across visual tasks. This work marks a crucial step towards more perceptually aligned and versatile MLLMs. We also hope that PerPO will encourage the community to rethink MLLM alignment strategies.

cs.AI↗