Searcharxiv⌕ Search

arXiv subjects

Yu-Xiong Wang

Publications and source records attributed to Yu-Xiong Wang.

At least 19 recordsLinked to original sources
arXiv2026

ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation

Achieving autonomous and versatile whole-body loco-manipulation remains a central barrier to making humanoids practically useful. Yet existing approaches are fundamentally constrained: retargeted data are often scarce or low-quality; methods struggle to scale to large skill repertoires; and, most importantly, they rely on tracking predefined motion references rather than generating behavior from perception and high-level task specifications. To address these limitations, we propose ULTRA, a unified framework with two key components. First, we introduce a physics-driven neural retargeting algorithm that translates large-scale motion capture to humanoid embodiments while preserving physical plausibility for contact-rich interactions. Second, we learn a unified multimodal controller that supports both dense references and sparse task specifications, under sensing ranging from accurate motion-capture state to noisy egocentric visual inputs. We distill a universal tracking policy into this controller, compress motor skills into a compact latent space, and apply reinforcement learning finetuning to expand coverage and improve robustness under out-of-distribution scenarios. This enables coordinated whole-body behavior from sparse intent without test-time reference motions. We evaluate ULTRA in simulation and on a real Unitree G1 humanoid. Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception, consistently outperforming tracking-only baselines with limited skills.

cs.RO↗
arXiv2026

One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models

Self-evolving harnesses are closed-loop systems in which an agent inspects its own rollouts and edits its prompts, tools, and memory. They reliably improve coding agents in evaluations, but prior work reports aggregate gains rather than analyzing what the evolved artifacts encode. It therefore remains unclear whether they encode benchmark-specific adaptations, language-specific engineering knowledge, or compensation for limitations of the underlying model. We disentangle these factors by holding an evolution recipe fixed across a grid of eight programming languages (Multi-SWE-Bench) and three base models, and analyzing the resulting harnesses. The recipe routes every edit through a typed failure signal and records it as a falsifiable contract, making each modification attributable after evolution. Four findings emerge. (1)The loop improves held-out solve rates over both a minimal seed and the manually designed mini-SWE-agent scaffold in most cells, but with two null regions. (2)Gains compensate recoverable execution defects, where defect mass is near zero, and gain is near zero; which defect dominates is cell-specific. A harness closes the gap between what a policy can do and what it does. (3)Evolved harnesses share an abstract playbook across languages but instantiate it with almost disjoint language ecosystem machinery. (4)The shared core transfers and can be distilled into one universal harness, while an ecosystem margin resists both and requires native re-evolution. Together, these results recast the evolved harness as a legible compensation layer, shaped jointly by the language's engineering demands and the model's behavioral gaps, rather than an opaque benchmark-tuned scaffold.

cs.SE↗
arXiv2026

CoCo-IR: Contextual Composed Image Retrieval

Current instruction-based image retrieval systems are powerful but limited to single-turn interactions, failing to capture the iterative nature of complex, real-world visual searches. To overcome this limitation, we introduce Contextual Composed Image Retrieval (CoCo-IR), a novel task that enables users to progressively refine search results through interactions. We address this new task by proposing a new model based on a Large Multimodal Model (LMM) that functions as a context-aware reasoner for CoCo-IR. Our model interprets the entire interaction history to generate Transformable Image Embeddings (TIE) that evolve across turns. To fuel the model training without expensive human annotations, we develop a fully autonomous, scalable data engine that leverages LMMs to generate high-quality contextual retrieval data, and uses model-guided verification to mine challenging hard negatives. Extensive experiments demonstrate that our approach establishes new state-of-the-art performance: We achieve 39.4 mAP@5 on the challenging single-turn benchmark CIRCO; furthermore, on our new CoCo-IR benchmark, our model maintains robust performance with 44.1 R@1 on 4-turn dialogues, dramatically outperforming existing methods (28.2 4-turn R@1) that fail to handle multi-turn context. Project page: https://CoCo-IR.github.io.

cs.CV↗
arXiv2026

D$_4$CNN$\times$AnaCal: Physics-Informed Machine Learning for Accurate and Precise Weak Lensing Shear Estimation

Traditional weak gravitational lensing shear estimators are carefully calibrated but struggle to fully capture realistic galaxy morphologies, point-spread-function (PSF) effects, blending, and noise in deep surveys, while blindly trained machine learning (ML) models can introduce significant calibration biases. Here we construct a fully D$_4$-equivariant deep neural network for galaxy shape measurement whose architecture enforces symmetry under 90$^{\circ}$ rotations and mirror transformations, and adopt the Analytical Calibration framework (AnaCal) to calibrate the model using its backpropagated gradients. For isolated galaxies in LSST-like single-band simulations, we demonstrate that our approach achieves $\sim$10% lower shape noise than the traditional moment-based Fourier Power Function Shapelets estimator in the high-noise regime, equivalent to a $\sim$20% gain in effective galaxy number density, while simultaneously achieving multiplicative biases consistent with zero across a wide range of noise levels, PSF sizes and ellipticities, and magnitude selection cuts, with all measurements satisfying $|m| {<} 2 \times 10^{-3}$ (i.e., within the 0.2% LSST requirement) and most at the ${\sim}10^{-4}$ level. We demonstrate this framework on isolated single-band galaxy images with Gaussian noise and known PSF, establishing a rigorous, physics-informed foundation for future extensions of ML-based shear estimation to blended sources and multi-band observations in Stage-IV surveys. All codes and data products will be made publicly available upon acceptance.

astro-ph.IM↗
arXiv2026

Walk through Paintings: Egocentric World Models from Internet Priors

What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pre-trained video diffusion model into an action-conditioned world model, enabling precisely controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models by injecting appropriately compressed motor commands through lightweight conditioning layers. This allows our model to follow actions faithfully while preserving generalization and realism. Our approach scales naturally across embodiments and action spaces -- from 3-DoF mobile robots to 25-DoF humanoids, where predicting egocentric joint-angle-driven dynamics is substantially more challenging. The model produces coherent rollouts for both navigation and manipulation, requiring only modest fine-tuning. To evaluate physical correctness independent of appearance, we introduce the Structural Consistency Score (SCS), which measures whether stable scene elements evolve consistently with the provided actions. Our method improves SCS by up to 65\% over the prior state of the art, Navigation World Models; applies seamlessly to three different video diffusion model architectures; and effectively utilizes Internet priors to generalize to unseen environments, including navigation and manipulation inside paintings. Finally, we demonstrate the applicability of EgoWM to robotic planning.

cs.CV↗
arXiv2026

UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling

Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface. While diffusion-based systems dominate UVG due to strong quality and controllability, their iterative sampling incurs substantial inference latency, limiting practical deployment. To address these limitations, we propose UniGen-AR, a framework that pairs a general-purpose multi-modal language model (MLLM) with an efficient next-scale visual auto-regressive (VAR) decoder. This design retains the flexibility of MLLM-based conditioning while leveraging the sampling efficiency and latent unification properties of VAR models. In our framework, the MLLM encodes free-form instructions and control signals into a unified sequence, which guides the VAR decoder to generate image-valued outputs for over 15 tasks spanning four families. Empirically, UniGen-AR achieves up to $19 \times$ lower inference latency than diffusion-based baselines while maintaining or improving output quality. Our ablations further reveal that VQ-VAE tokenizer design, particularly codebook size and hierarchy, is a critical factor for VAR scalability in UVG. These results establish visual auto-regressive modeling as a compelling and efficient backbone for unified visual generation. Our project page is at https://zpbao.github.io/projects/unigenar.

cs.CV↗
arXiv2026

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval

Keyframe selection is a direct way to provide verifiable visual evidence for long-video question answering (QA). Queries differ in what they require, and finding the right frames depends on knowing what to look for. Existing keyframe selectors either score every frame against a single query, or decompose the query into a fixed schema evaluated by a single visual tool. We propose ToolMerge, a keyframe retrieval method based on decomposition and merging: an Large Language Model (LLM) based planner decomposes the query into tool calls and specifies how their per-tool rankings are merged using boolean operators. To evaluate retrieval directly, we construct Molmo-2 Moments (M2M), a benchmark in which every question is anchored to a specific time interval by construction. Across QA, question retrieval, and caption retrieval, ToolMerge is competitive with prior keyframe selectors, most notably on caption retrieval, outperforming other methods by 5%. Code and data can be found at https://github.com/michalsr/ToolMerge .

cs.CV↗
arXiv2026

PPTArena: A Benchmark for PowerPoint Editing

We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions. Unlike benchmarks that rely on image-PDF renderings or text-to-slide generation, PPTArena features 100 decks with over 1,300 human-curated edits across 2,125 slides, spanning text, charts, animations, and professional master styles. Each edit pairs a ground-truth deck with a target rubric and is scored by two Vision-Language Model (VLM) judges: one rates instruction following from structural diffs, the other visual quality from slide images. On top of this benchmark, we present PPTPilot, a structure-aware agent that plans semantic edit sequences, routes between programmatic tools and deterministic XML operations, and verifies each result in an iterative plan-edit-check loop. PPTPilot outperforms strong VLM-based agents by more than 10 percentage points on compound, layout-sensitive, and cross-slide edits, with large gains in visual fidelity and deck-wide consistency. Despite this, all agents still struggle on long-horizon, document-scale tasks, underscoring how hard reliable PowerPoint editing remains. We publicly release our code at https://github.com/michaelofengend/PPTArena .

cs.CV↗
arXiv2026

Think in Latent, Explain in Language: Self-Explainable Latent Reasoning

Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current methods present a stark trade-off: they either function as unexplainable ''black boxes'' (e.g., Coconut), where the latent reasoning is not human-readable, or rely on separate post-hoc decoders for explainability (e.g., Heima), introducing architectural overhead and decoupling the explanation from the actual reasoning process. In this work, we present a unified framework for Self-Explainable Latent Reasoning (SELR) that trains a single model to perform efficient and inherently explainable latent reasoning. Our core contribution is a novel multi-task training objective that optimizes for two goals simultaneously: (1) an Answer Loss that optimizes the latent reasoning trajectory to produce accurate final answers, and (2) a CoT Loss that explicitly trains the same model to decode its own latent representations back into human-understandable reasoning steps. This design ensures that generated latent representations are both task-effective and semantically interpretable, eliminating the need for external decoders. We validate the effectiveness of SELR on both Large Language Models (LLMs) and Vision-Language Models (VLMs), demonstrating that SELR achieves superior token efficiency and accuracy compared to baselines, while uniquely providing self-contained explainability without auxiliary models. Project page is available at https://jasondayuan.github.io/SELR/.

cs.CL↗
arXiv2026

Vesta: A Generalist Embodied Reasoning Model

Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at individual tasks, deploying a multi-model stack is computationally expensive and prone to cascading errors. We present Vesta, a unified embodied generalist that consolidates these capabilities into a single foundation model. Our approach combines a diverse and massive curated corpus designed to induce spatial grounding and a simple multimodal memory harness that enables reasoning over extended time horizons. Across diverse benchmarks, Vesta on average beats individual SOTA baselines by >$20\%$ and beats an ensemble of per-category-best baselines by $>10\%$ -- thus demonstrating that a generalist model can match or exceed specialists. On real-world robotic tasks requiring memory and reasoning, Vesta improves task success by >35\%. Our work thus demonstrates that a single generalist is a feasible, scalable, and arguably preferable alternative to combining specialists.

cs.RO↗
arXiv2026

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved great success in developing Large Language Models (LLMs) with chain-of-thought rollouts for many tasks such as math and coding. Nevertheless, RLVR struggles with sample efficiency on difficult problems where correct rollouts are hard to generate. Prior works propose to address this issue via demonstration-guided RLVR, i.e., to conduct Supervised FineTuning (SFT) when RL fails; however, SFT often requires a lot of data, which can be expensive to acquire. In this paper, we propose FEST, a FEw-ShoT demonstration-guided RLVR algorithm. It attains compelling results with only 128 demonstrations randomly selected from an SFT dataset. We find that three components are vital for the success: supervised signal, on-policy signal, and decaying weights on the few-shot SFT dataset to prevent overfitting from multiple-epoch training. On several benchmarks, FEST outperforms baselines with magnitudes less SFT data, even matching their performance with full dataset.

cs.LG↗
arXiv2026

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames sparsely and lose temporal information. To address this, we explore extreme video token compression towards one token per frame at the final LLM layer. Our key insight is that heuristic-based compression, widely adopted by previous methods, is prone to information loss, and this necessitates supervising LLM layers into learnable and progressive modules for token-level compression (LP-Comp). Such compression enables our VLM to digest 2x-4x more frames with improved performance. To further increase the token efficiency, we investigate frame-level compression, which selects the frames most relevant to the queries via the internal attention scores of the LLM layers, named question-conditioned compression (QC-Comp). As a notable distinction from previous studies, we mitigate the position bias of LLM attention in long contexts, i.e., the over-concentration on the beginning and end of a sequence, by splitting long videos into short segments and employing local attention. Collectively, our combined token-level and frame-level leads to an extreme compression model for long video understanding, named XComp, achieving a significantly larger compression ratio and enabling denser frame sampling. Our XComp is finetuned from VideoChat-Flash with a data-efficient supervised compression tuning stage that only requires 2.5% of the supervised fine-tuning data, yet boosts the accuracy from 42.9% to 46.2% on LVBench and enhances multiple other long video benchmarks.

cs.CV↗
arXiv2026

HandX: Scaling Bimanual Motion and Interaction Generation

Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled strategy that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.

cs.CV↗
arXiv2026

Unleashing Guidance Without Classifiers for Human-Object Interaction Animation

Generating realistic human-object interaction (HOI) animations remains challenging because it requires jointly modeling dynamic human actions and diverse object geometries. Prior diffusion-based approaches often rely on hand-crafted contact priors or human-imposed kinematic constraints to improve contact quality. We propose LIGHT, a data-driven alternative in which guidance emerges from the denoising pace itself, reducing dependence on manually designed priors. Building on diffusion forcing, we factor the representation into modality-specific components and assign individualized noise levels with asynchronous denoising schedules. In this paradigm, cleaner components guide noisier ones through cross-attention, yielding guidance without auxiliary classifiers. We find that this data-driven guidance is inherently contact-aware, and can be enhanced when training is augmented with a broad spectrum of synthetic object geometries, encouraging invariance of contact semantics to geometric diversity. Extensive experiments show that pace-induced guidance more effectively mirrors the benefits of contact priors than conventional classifier-free guidance, while achieving higher contact fidelity, more realistic HOI generation, and stronger generalization to unseen objects and tasks.

cs.CV↗
arXiv2026

Latent Wasserstein Adversarial Imitation Learning

Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations, both of which are often unavailable. To reduce this need, we propose Latent Wasserstein Adversarial Imitation Learning (LWAIL), a novel adversarial imitation learning framework that focuses on state-only distribution matching. It benefits from the Wasserstein distance computed in a dynamics-aware latent space. This dynamics-aware latent space differs from prior work and is obtained via a pre-training stage, where we train the Intention Conditioned Value Function (ICVF) to capture a dynamics-aware structure of the state space using a small set of randomly generated state-only data. We show that this enhances the policy's understanding of state transitions, enabling the learning process to use only one or a few state-only expert episodes to achieve expert-level performance. Through experiments on multiple MuJoCo environments, we demonstrate that our method outperforms prior Wasserstein-based IL methods and prior adversarial IL methods, achieving better results across various tasks.

cs.LG↗
arXiv2026

LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight

To act in the world, a model must name what it sees and know where it is in 3D. Today's vision-language models (VLMs) excel at open-ended 2D description and grounding, yet multi-object 3D detection remains largely missing from the VLM toolbox. We present LocateAnything3D, a VLM-native recipe that casts 3D detection as a next-token prediction problem. The key is a short, explicit Chain-of-Sight (CoS) sequence that mirrors how human reason from images: find an object in 2D, then infer its distance, size, and pose. The decoder first emits 2D detections as a visual chain-of-thought, then predicts 3D boxes under an easy-to-hard curriculum: across objects, a near-to-far order reduces early ambiguity and matches ego-centric utility; within each object, a center-from-camera, dimensions, and rotation factorization ranks information by stability and learnability. This VLM-native interface preserves open-vocabulary and visual-prompting capability without specialized heads. On the challenging Omni3D benchmark, our model achieves state-of-the-art results, with 38.90 AP_3D, surpassing the previous best by +13.98 absolute improvement even when the baseline is given ground-truth 2D boxes. It also generalizes zero-shot to held-out categories with strong robustness. By turning 3D detection into a disciplined next-token problem, LocateAnything3D offers a practical foundation for models to perceive in 3D.

cs.CV↗
arXiv2026

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack surface: visual backdoor attacks, where the agent behaves normally until a visual trigger appears in the scene, then persistently executes an attacker-specified multi-step policy. We introduce BEAT, the first framework to inject such visual backdoors into VLM-based embodied agents using objects in the environments as triggers. Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably. BEAT addresses this challenge by (1) constructing a training set that spans diverse scenes, tasks, and trigger placements to expose agents to trigger variability, and (2) introducing a two-stage training scheme that first applies supervised fine-tuning (SFT) and then our novel Contrastive Trigger Learning (CTL). CTL formulates trigger discrimination as preference learning between trigger-present and trigger-free inputs, explicitly sharpening the decision boundaries to ensure precise backdoor activation. Across various embodied agent benchmarks and VLMs, BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance, and generalizes reliably to out-of-distribution trigger placements. Notably, compared to naive SFT, CTL boosts backdoor activation accuracy up to 39% under limited backdoor data. These findings expose a critical yet unexplored security risk in VLM-based embodied agents, underscoring the need for robust defenses before real-world deployment.

cs.AI↗
arXiv2026

InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions

Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements. High-level intentions, such as affordance, define the goal, while coordinated balance, contact, and manipulation can emerge naturally from underlying physical and motor priors. Scaling such priors is key to enabling humanoids to compose and generalize loco-manipulation skills across diverse contexts while maintaining physically coherent whole-body coordination. To this end, we introduce InterPrior, a scalable framework that learns a unified generative controller through large-scale imitation pretraining and post-training by reinforcement learning. InterPrior first distills a full-reference imitation expert into a versatile, goal-conditioned variational policy that reconstructs motion from multimodal observations and high-level intent. While the distilled policy reconstructs training behaviors, it does not generalize reliably due to the vast configuration space of large-scale human-object interactions. To address this, we apply data augmentation with physical perturbations, and then perform reinforcement learning finetuning to improve competence on unseen goals and initializations. Together, these steps consolidate the reconstructed latent skills into a valid manifold, yielding a motion prior that generalizes beyond the training data, e.g., it can incorporate new behaviors such as interactions with unseen objects. We further demonstrate its effectiveness for user-interactive control and its potential for real robot deployment.

cs.CV↗