Searcharxiv⌕ Search

arXiv subjects

Jianhua Han

Publications and source records attributed to Jianhua Han.

At least 19 recordsLinked to original sources
arXiv2026

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from open-source generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality.

cs.CV↗
arXiv2026

4D-WAM: 4D Consistent World Modeling for Autonomous Driving

Emerging World-Action Models (WAMs) have demonstrated promising performance in autonomous driving by jointly modeling future driving scene evolution and trajectory planning. However, existing WAMs are typically trained with video data, which is only 2D projections of the underlying 4D driving scene. Consequently, WAMs fail to understand and capture the structure of 4D scenes and thus generate visually plausible yet 4D inconsistent future predictions that mislead downstream planning. To alleviate this issue, we present 4D-WAM, a model that leverages geometric foundation models for training-time supervision to enable 4D consistent world modeling. Specifically, we feed WAM-predicted future frames into a geometric foundation model, and use 4D-aware responses to define a 4D consistency loss. This loss encourages the model to understand, represent, and predict physically consistent 4D scenes during training, without additional inference cost. Moreover, we identify an early-decision phenomenon in WAMs and propose a decision-oriented timestep sampling strategy that emphasizes supervision at early, high-noise stages, where driving decisions are primarily formed. By propagating 4D supervision to this critical decision-formation phase, the proposed strategy further improves trajectory planning. Extensive experiments demonstrate that 4D-WAM effectively models 4D consistent scene evolution and achieves state-of-the-art performance on challenging NAVSIM-v1 and NAVSIM-v2 benchmarks.

cs.CV↗
arXiv2026

SUV: Future Scene Understanding as Video Generation for End-to-End Driving

End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output formats, with limited scalability. Can video generation instead provide a shared predictor? We introduce SUV, a unified end-to-end driving framework that casts future Scene Understanding as Video generation using a pretrained video foundation model. SUV models future appearance, semantics, relative depth, and instance-level dynamics as video streams with a shared video expert, without stream-specific visual prediction heads. Through joint video-action attention, the action expert attends to the latent representations of all future streams and generates the ego trajectory. Experiments show that SUV directly predicts all four future streams, while controlled ablations show that structured future supervision and direct future-stream access yield higher trajectory planning scores. With only a single front camera and no candidate-trajectory selection, SUV outperforms a broad set of recent state-of-the-art methods on both NAVSIM-v2 splits, achieving 91.0 EPDMS on navtest and 36.9 on navhard. On the long-tail WOD-E2E benchmark, SUV achieves a competitive RFS of 7.94.

cs.CV↗
arXiv2026

WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA

Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding. Conversely, while specialized diffusion policies enable low-latency, parallel execution, training them from scratch typically yields narrow, single-task architectures that lack holistic visual-linguistic reasoning. Successfully transforming pre-trained autoregressive generalists into parallel diffusion models could combine multi-task cognitive intelligence with execution efficiency, yet this transition presents a formidable architectural challenge due to mismatched attention patterns (causal versus bidirectional) and divergent optimization objectives. To bridge this divide, we introduce WAM-Diff2, a multi-task discrete diffusion VLA framework powered by a three-stage hierarchical distillation strategy. By structuring the architectural shift through progressive block-wise adaptation, block-wise distillation, and model-wise cross-scale distillation, WAM-Diff2 preserves the underlying semantic foundations of the base model while accelerating inference. Extensive evaluations across driving understanding, perception, and planning benchmarks demonstrate that WAM-Diff2 effectively mitigates exposure bias and achieves performance parity with autoregressive baselines. Crucially, the autoregressive-to-diffusion transition yields a 2.8x decoding speedup, which scales to an ultimate 15.1x acceleration when combined with system-level optimizations including FlashInfer and CUDA Graphs.

cs.RO↗
arXiv2026

Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools

Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency.

cs.CV↗
arXiv2026

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities, which are both costly and challenging to scale. Although recent self-improving models that iteratively refine themselves offer a feasible solution, they still suffer from two core challenges: (i) most existing methods augment visual or textual data separately, resulting in discrepancies in data complexity (e.g., over-simplified diagrams paired with redundant textual descriptions); and (ii) the evolution of data and models is also separated, leading to scenarios where models are exposed to tasks with mismatched difficulty levels. To address these issues, we propose C2-Evo, an automatic, closed-loop self-improving framework that jointly evolves both training data and model capabilities. Specifically, given a base dataset and a base model, C2-Evo enhances them by a cross-modal data evolution loop and a data-model evolution loop. The former loop expands the base dataset by generating complex multimodal problems that combine structured textual sub-problems with iteratively specified geometric diagrams, while the latter loop adaptively selects the generated problems based on the performance of the base model, to conduct supervised fine-tuning and reinforcement learning alternately. Consequently, our method continuously refines its model and training data, and consistently obtains considerable performance gains across multiple mathematical reasoning benchmarks. Our code, models, and datasets will be released.

cs.CV↗
arXiv2026

Latent Visual States for Efficient Multimodal Reasoning

The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete outputs (etc., code or box coordinates) to invoke external tools, a process that introduces rigid dependencies and substantial latency. To overcome these limitations, we propose {EVA} (LatEnt Visual StAtes), a novel framework that natively generates continuous latent visual representations. These internal representations manifest as an adaptive sequence of Latent\_slot tokens, serving as intermediate visual thoughts during the reasoning process. These Latent\_slot tokens are then trained end-to-end with the discrete text tokens. This co-optimization, notably, causes extreme policy deviation in the 'transition window' following the Latent\_slot tokens. We develop D-GSPO (Decouple-GSPO) to target this root cause by decoupling the optimization of latent and discrete components. To support SFT, we construct EVA-230K, a high-quality text-image interleaved CoT dataset encompassing a diverse range of real-world scenes, documents, charts and OCR tasks. Extensive experiments across multiple benchmarks confirm that EVA achieves significant performance gains while enhancing inference efficiency.

cs.CV↗
arXiv2026

Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving

Recent Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving by incorporating reasoning for better interpretability and planning quality. However, most existing approaches directly generate the final trajectory without explicitly examining its future consequences, which limits their reliability in complex and dynamic environments. To address this limitation, we propose IRR-Drive (Intend, Reflect, Refine), an adaptive multimodal reflection framework for autonomous driving. Specifically, to tightly couple high-level reasoning with physical constraints, IRR-Drive first generates a preliminary textual intention and anticipates potential interactions by predicting future semantic bird's-eye view (BEV) representations. This dual-modality (Text + BEV) reflection space explicitly models anticipated scene evolution, enabling the model to rigorously self-correct and refine its initial intent before generating the final trajectory. Furthermore, to balance planning performance and computational efficiency, we construct reflection-oriented training data and design an adaptive reflection reward, enabling the model to adaptively select its reasoning mode according to scene complexity. Instead of using reasoning primarily as an auxiliary interpretation, IRR-Drive directly integrates an adaptive reflection mechanism into the planning framework, enabling grounded, decision-aware trajectory correction that is driven by scene complexity. Our method achieves state-of-the-art performance on the NAVSIM benchmark in both PDMS and EPDMS. Extensive experiments demonstrate the effectiveness of our multimodal reflection framework and validate the efficacy of the proposed adaptive reflection strategy.

cs.CV↗
arXiv2026

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence. Code can be found at https://github.com/Li-Hao-yuan/GeoThinker.

cs.CV↗
arXiv2026

Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI

The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a unified bridging framework. This work provides a comprehensive overview of physical AI, establishing clear distinctions between theoretical physics reasoning and applied physical understanding while systematically examining how physics-grounded methods enhance AI's real-world comprehension across structured symbolic reasoning, embodied systems, and generative models. Through rigorous analysis of recent advances, we advocate for intelligent systems that ground learning in both physical principles and embodied reasoning processes, transcending pattern recognition toward genuine understanding of physical laws. Our synthesis envisions next-generation world models capable of explaining physical phenomena and predicting future states, advancing safe, generalizable, and interpretable AI systems. We maintain a continuously updated resource at https://github.com/AI4Phys/Awesome-AI-for-Physics.

cs.AI↗
arXiv2026

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation

Open-world semantic segmentation presently relies significantly on extensive image-text pair datasets, which often suffer from a lack of fine-grained pixel annotations on sufficient categories. The acquisition of such data is rendered economically prohibitive due to the substantial investments of both human labor and time. In light of the formidable image generation capabilities of diffusion models, we introduce a novel diffusion model-driven pipeline for automatically generating datasets tailored to the needs of open-world semantic segmentation, named "MagicSeg". Our MagicSeg initiates from class labels and proceeds to generate high-fidelity textual descriptions, which in turn serve as guidance for the diffusion model to generate images. Rather than only generating positive samples for each label, our process encompasses the simultaneous generation of corresponding negative images, designed to serve as paired counterfactual samples for contrastive training. Then, to provide a self-supervised signal for open-world segmentation pretraining, our MagicSeg integrates an open-vocabulary detection model and an interactive segmentation model to extract object masks as precise segmentation labels from images based on the provided category labels. By applying our dataset to the contrastive language-image pretraining model with the pseudo mask supervision and the auxiliary counterfactual contrastive training, the downstream model obtains strong performance on open-world semantic segmentation. We evaluate our model on PASCAL VOC, PASCAL Context, and COCO, achieving SOTA with performance of 62.9%, 26.7%, and 40.2%, respectively, demonstrating our dataset's effectiveness in enhancing open-world semantic segmentation capabilities. Project website: https://github.com/ckxhp/magicseg.

cs.CV↗
arXiv2026

Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization

Unified vision-language models have made significant progress in multimodal understanding and generation, yet they largely fall short in producing multimodal interleaved outputs, which is a crucial capability for tasks like visual storytelling and step-by-step visual reasoning. In this work, we propose a reinforcement learning-based post-training strategy to unlock this capability in existing unified models, without relying on large-scale multimodal interleaved datasets. We begin with a warm-up stage using a hybrid dataset comprising curated interleaved sequences and limited data for multimodal understanding and text-to-image generation, which exposes the model to interleaved generation patterns while preserving its pretrained capabilities. To further refine interleaved generation, we propose a unified policy optimization framework that extends Group Relative Policy Optimization (GRPO) to the multimodal setting. Our approach jointly models text and image generation within a single decoding trajectory and optimizes it with our novel hybrid rewards covering textual relevance, visual-text alignment, and structural fidelity. Additionally, we incorporate process-level rewards to provide step-wise guidance, enhancing training efficiency in complex multimodal tasks. Experiments on MMIE and InterleavedBench demonstrate that our approach significantly enhances the quality and coherence of multimodal interleaved generation.

cs.CV↗
arXiv2026

AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots

Recent advances in Visual-Language-Action (VLA) models have shown promising potential for robotic manipulation tasks. However, real-world robotic tasks often involve long-horizon, multi-step problem-solving and require generalization for continual skill acquisition, extending beyond single actions or skills. These challenges present significant barriers for existing VLA models, which use monolithic action decoders trained on aggregated data, resulting in poor scalability. To address these challenges, we propose AtomicVLA, a unified planning-and-execution framework that jointly generates task-level plans, atomic skill abstractions, and fine-grained actions. AtomicVLA constructs a scalable atomic skill library through a Skill-Guided Mixture-of-Experts (SG-MoE), where each expert specializes in mastering generic yet precise atomic skills. Furthermore, we introduce a flexible routing encoder that automatically assigns dedicated atomic experts to new skills, enabling continual learning. We validate our approach through extensive experiments. In simulation, AtomicVLA outperforms $\pi_{0}$ by 2.4\% on LIBERO, 10\% on LIBERO-LONG, and outperforms $\pi_{0}$ and $\pi_{0.5}$ by 0.22 and 0.25 in average task length on CALVIN. Additionally, our AtomicVLA consistently surpasses baselines by 18.3\% and 21\% in real-world long-horizon tasks and continual learning. These results highlight the effectiveness of atomic skill abstraction and dynamic expert composition for long-horizon and lifelong robotic tasks. The project page is \href{https://zhanglk9.github.io/atomicvla-web/}{here}.

cs.RO↗
arXiv2026

CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning

Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the frequent updates of GUI applications, adapting to new tasks without forgetting old tasks in GUI continual learning remains an open problem. In this work, we reveal that while Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting, whereas Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure. Based on this insight, we propose a \textbf{C}ontinual \textbf{G}UI \textbf{L}earning (CGL) framework that dynamically balances adaptation efficiency and skill retention by enhancing the synergy between SFT and RL. Specifically, we introduce an SFT proportion adjustment mechanism guided by policy entropy to dynamically control the weight allocation between the SFT and RL training phases. To resolve explicit gradient interference, we further develop a specialized gradient surgery strategy. By projecting exploratory SFT gradients onto GRPO-based anchor gradients, our method explicitly clips the components of SFT gradients that conflict with GRPO. On top of that, we establish an AndroidControl-CL benchmark, which divides GUI applications into distinct task groups to effectively simulate and evaluate the performance of continual GUI learning. Experimental results demonstrate the effectiveness of our proposed CGL framework across continual learning scenarios. The benchmark, code, and model will be made publicly available.

cs.LG↗
arXiv2026

SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation

In this paper, we introduce SemHiTok, a unified image Tokenizer via Semantic-Guided Hierarchical codebook that provides consistent discrete representations for multimodal understanding and generation. Recently, unified image tokenizers have sparked exploration within the research community, which is designed to capture high-level semantic features for understanding and retaining low-level pixel features for generation. Previous works attempt to train a unified image tokenizer by combining loss for semantic distillation and pixel reconstruction. However, due to the differing levels of features prioritized by multimodal understanding and generation, joint training methods face significant challenges in achieving a good trade-off. SemHiTok addresses this challenge through a novel semantic-guided hierarchical codebook, which builds pixel sub-codebooks on a pretrained semantic codebook. This design decouples the semantic and pixel in terms of structure and training strategy, enabling the tokenizer to capture pixel features while retaining its ability to comprehend high-level semantic information. Our experiments demonstrate that SemHiTok achieves leading performance in image reconstruction and multimodal understanding under the LLaVA-v1.5 setting. Further, we develop a unified MLLM with SemHiTok, which exhibits superior performance across multimodal understanding and generation tasks. Extensive experiments confirm our analysis, showing that our unified image tokenizer architecture achieves a better trade-off.

cs.CV↗
arXiv2026

RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training

Pre-trained Multi-modal Large Language Models (MLLMs) provide a knowledge-rich foundation for post-training by leveraging their inherent perception and reasoning capabilities to solve complex tasks. However, the lack of an efficient evaluation framework impedes the diagnosis of their performance bottlenecks. Current evaluation primarily relies on testing after supervised fine-tuning, which introduces laborious additional training and autoregressive decoding costs. Meanwhile, common pre-training metrics cannot quantify a model's perception and reasoning abilities in a disentangled manner. Furthermore, existing evaluation benchmarks are typically limited in scale or misaligned with pre-training objectives. Thus, we propose RADAR, an efficient ability-centric evaluation framework for Revealing Asymmetric Development of Abilities in MLLM pRe-training. RADAR involves two key components: (1) Soft Discrimination Score, a novel metric for robustly tracking ability development without fine-tuning, based on quantifying nuanced gradations of the model preference for the correct answer over distractors; and (2) Multi-Modal Mixture Benchmark, a new 15K+ sample benchmark for comprehensively evaluating pre-trained MLLMs' perception and reasoning abilities in a 0-shot manner, where we unify authoritative benchmark datasets and carefully collect new datasets, extending the evaluation scope and addressing the critical gaps in current benchmarks. With RADAR, we comprehensively reveal the asymmetric development of perceptual and reasoning capabilities in pretrained MLLMs across diverse factors, including data volume, model size, and pretraining strategy. Our RADAR underscores the need for a decomposed perspective on pre-training ability bottlenecks, informing targeted interventions to advance MLLMs efficiently. Our code is publicly available at https://github.com/Nieysh/RADAR.

cs.CV↗
arXiv2026

SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to simultaneously retain high-quality frame-level semantic information (i.e., a sufficient number of tokens per frame) and comprehensive video-level temporal information (i.e., an adequate number of sampled frames per video). This limitation hinders the advancement of Vid-LLMs towards fine-grained video understanding. To address this issue, we introduce the SlowFocus mechanism, which significantly enhances the equivalent sampling frequency without compromising the quality of frame-level visual tokens. SlowFocus begins by identifying the query-related temporal segment based on the posed question, then performs dense sampling on this segment to extract local high-frequency features. A multi-frequency mixing attention module is further leveraged to aggregate these local high-frequency details with global low-frequency contexts for enhanced temporal comprehension. Additionally, to tailor Vid-LLMs to this innovative mechanism, we introduce a set of training strategies aimed at bolstering both temporal grounding and detailed temporal reasoning capabilities. Furthermore, we establish FineAction-CGR, a benchmark specifically devised to assess the ability of Vid-LLMs to process fine-grained temporal understanding tasks. Comprehensive experiments demonstrate the superiority of our mechanism across both existing public video understanding benchmarks and our proposed FineAction-CGR.

cs.CV↗
arXiv2026

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising direction is to use sliding windows to slice the input into uniform patches, each matching the input size of the well-trained vision encoder. Although efficient, this slicing strategy leads to the fragmentation of original input, i.e., the continuity of contextual information and spatial geometry is lost across patches, adversely affecting performance in cross-patch context perception and position-specific tasks. To overcome these shortcomings, we introduce HiRes-LLaVA, a novel framework designed to efficiently process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compresses the vision tokens based on themselves, preserving the original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related and position-related tasks. Our comprehensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and on EntityGrid-QA, particularly on document-oriented tasks, establishing new standards for handling high-resolution inputs.

cs.CV↗