arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera Odometry

Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving efficient use of rig geometry a challenge. We present StreamRig, a freeze-and-stream framework that builds causal streaming odometry for calibrated rigs on a frozen multi-view 3D foundation model. The frozen front-end jointly perceives the synchronized views using rig calibration. A Rig-Resampler compresses their features, a CausalBridge applies causal attention with a key-value cache, and a lightweight head regresses rig poses. A periodic re-anchoring protocol supports stable pose estimation over long sequences. Only these modules are trained, 74.6M parameters in total, with relative poses as the sole supervision. Our two-stage training strategy combines group relocalization pretraining with causal rig training to transfer the geometric priors of the frozen front-end and the alignment ability of the pretrained modules to streaming odometry. We evaluate on NCLT, TartanGround, KITTI-360, and our self-collected humanoid-robot dataset ZJH, where training uses only simulation and real-world evaluation is zero-shot. Across all four datasets, StreamRig achieves lower translation and rotation drift than the evaluated non-oracle monocular streaming and rig-aware offline models, while maintaining low inference cost. Ablations and controlled camera-count experiments identify the sources of these gains. We further examine how longer training windows affect inference over longer horizons. Code has been released at https://github.com/WeiYuFei0217/StreamRig.

cs.CV↗

arXiv2026

Robust Nash Alignment under Preference Uncertainty

Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are uncertain: noisy, heterogeneous, or shift after deployment. To address these issues, we propose Robust Nash Alignment, a game-theoretic framework for alignment to uncertain pairwise preferences. Our formulation has a major learner seeking a policy with a large worst-case win rate against both an adversarial competitor and any preference kernel lying in an ambiguity set around a nominal preference. When the ambiguity set captures the uncertainty in preferences, the resulting robust objective of the game directly yields a certified lower bound on worst-case performance. However, we note this problem is computationally challenging to optimize, and to address this, we introduce a four-player primal-dual proxy game involving the leader policy, follower policy, adversarial kernel, and dual variable, and develop a single-loop optimistic mirror descent-ascent algorithm for it. We show that the proxy always lower-bounds the truncated hard-constrained objective, quantify the proxy-to-hard gap, and characterize an exactness condition under which the proxy recovers the robust objective. We then prove an $\mathcal{O}(1/\sqrt{T})$ average-iteration convergence for the proxy-game duality gap, which implies a near-optimal robust policy for the original robust objective. Experiments on controlled tabular games and LLM alignment with uncertain preference further validate the convergence theory and show improved performance over nominal baselines.

cs.AI↗

arXiv2026

EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis

Novel view synthesis (NVS) of static and dynamic urban scenes is essential for autonomous driving simulation, yet existing methods often struggle to balance reconstruction time with quality. While state-of-the-art neural radiance fields and 3D Gaussian Splatting approaches achieve photorealism, they often rely on time-consuming per-scene optimization. Conversely, emerging feed-forward methods frequently adopt per-pixel Gaussian representations, which lead to 3D inconsistencies when aggregating multi-view predictions in complex, dynamic environments. We propose EvolSplat4D, a feed-forward framework that moves beyond existing per-pixel paradigms by unifying volume-based and pixel-based Gaussian prediction across three specialized branches. For close-range static regions, we predict consistent geometry of 3D Gaussians over multiple frames directly from a 3D feature volume, complemented by a semantically-enhanced image-based rendering module for predicting their appearance. For dynamic actors, we utilize object-centric canonical spaces and a motion-adjusted rendering module to aggregate temporal features, ensuring stable 4D reconstruction despite noisy motion priors. Far-Field scenery is handled by an efficient per-pixel Gaussian branch to ensure full-scene coverage. Experimental results on the KITTI-360, KITTI, Waymo, and PandaSet datasets show that EvolSplat4D reconstructs both static and dynamic environments with superior accuracy and consistency, outperforming both per-scene optimization and state-of-the-art feed-forward baselines.

cs.CV↗

arXiv2026

Distilled Reinforcement Learning for LLM Post-training

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.

cs.LG↗

arXiv2026

Collision-Aware and Observation-Aligned Object-Centric Scene Reconstruction from Point Cloud

Object-centric scene reconstruction requires completing partial object observations while preserving metric alignment and avoiding collisions with the surrounding. Existing generation-based methods are often image-conditioned and suffer from scale ambiguity and insufficient geometric constraints. We propose COOL, a framework for COllision-aware and Observation-aLigned reconstruction. Based on an object generation model, COOL conditions the generation on instance and background point clouds. Instance geometry anchors generation in scene coordinates, while background geometry provides local context for scene-consistent completion. We further introduce an explicit collision loss and use joint optimization and resampling to reduce collisions during inference. Experiments on 3D-Front and Scan2CAD demonstrate strong scene-level fidelity, observation alignment, and collision reduction. Moreover, additional studies validate its robustness to mask errors and its applicability to real-world scene replicas.

cs.CV↗

arXiv2026

PhysWAM: Physically Consistent World Action Model for Autonomous Driving

World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constraint on these predictions. We present PhysWAM, a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer. To ground world and action generation in measured scene geometry, we introduce Coupled Point Projection (CPP) that unprojects the generated depth into 3D points, transforms them using the generated $\mathrm{SE}(3)$ ego motion, and minimizes their distance to LiDAR points transformed using the recorded ego motion. This geometric constraint promotes physical consistency with the measured scene by jointly supervising generated depth and motion alongside their standard flow-matching objectives. At inference, trajectory selection relies only on a simple label-free consensus rule, with no learned scorer or simulator feedback. We evaluate PhysWAM across NAVSIM v1 and v2 planning, zero-shot closed-loop transfer, and future video and metric-depth prediction. Despite PhysWAM's simple selection procedure, it achieves strong planning performance and transfers zero-shot to unseen driving environments. It also generates accurate metric depth and temporally coherent video, with CPP improving both planning and depth prediction. Together, these results demonstrate that the geometric relationship between scene depth and ego motion provides a direct way to couple world and action generation within a simple unified model.

cs.RO↗

arXiv2026

BIND: Binding 3D Robot Actions to 2D Image Features

We introduce BIND, a new action representation for visuomotor robot policies that binds 3D robot actions to their corresponding 2D image features, yielding strong data efficiency gains and robustness to out-of-distribution object positions and camera viewpoints. The action heads of current robot policies are typically formulated as an MLP regression from a single global feature vector produced by a pre-trained vision encoder. This global formulation requires the policy network to discover, from demonstrations alone, the relationship between target robot actions and the image features they project onto. The consequence is that although modern image features are semantically descriptive, spatially robust, and even multiview-consistent, the policies built on them are brittle to subtle changes in camera viewpoint and object placement--and surprisingly data-inefficient. BIND closes this gap by supplying the action-feature relationship through camera geometry rather than learning: it discretizes a volume of candidate end effector positions, attaches each candidate to the pre-trained features at its projection in each camera view, and selects actions by scoring each candidate's position and image-bound feature combination. On a real robot, we study data efficiency and out-of-distribution robustness to unseen object positions and camera viewpoints, as well as general long-horizon task execution and dexterity. We find BIND to be highly data-efficient and robust: it achieves near-perfect success on tasks with as few as 5 demonstrations, and degrades gracefully under steep camera-viewpoint shifts and held-out object positions where coordinate-regression baselines completely fail.

cs.RO↗

arXiv2026

BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots

Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the scale drift problem of monocular visual odometry (MVO) by providing a metric-scaled planar workspace, enabling the simplification of 6-DoF ego-motion to a more robust 3-DoF model. However, existing BEV-based methods suffer from two key limitations: sparse supervision signals from pose-only training, and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework in the BEV-ODOM line that addresses both limitations without supervision modalities beyond the pose ground truth. Our approach introduces (1) pose-derived dense rigid BEV flow supervision, which reparameterizes the 3-DoF pose ground truth into a pixel-level training signal, and (2) Perspective View (PV)-BEV fusion, which computes correlation volumes before projection to retain additional motion cues and help alleviate projection ambiguity. An enhanced rotation sampling strategy further balances diverse motion patterns during training. We evaluate on four datasets with varied spatial scales: KITTI, Oxford, NCLT, and our newly collected ZJH-VO benchmark. BEV-ODOM2 reduces the RTE of BEV-ODOM by 39% on average across the four datasets. It further enables closed-loop navigation on a physical robot with centimeter-level cross-track error. Real-time inference on an NVIDIA Jetson AGX Orin confirms edge deployment feasibility. The code and the ZJH-VO dataset are publicly released to facilitate future research.

cs.RO↗

arXiv2026

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation. However, RAEs still need to decide which encoder layers form the shared latent space for the generator and pixel decoder. This choice involves a trade-off: shallower layers tend to preserve fine pixel details better, while deeper layers tend to yield better generation metrics. A fixed heuristic layer fusion therefore couples two stages that benefit from different information. We introduce FuseReg, which replaces heuristic feature selection with training over random subsets of encoder layers. We theoretically analyze the underlying mechanism: subset sampling preserves the full-layer latent mean in expectation while explicitly penalizing sensitivity to cross-layer disagreement. On ImageNet-256 with DINOv3-L, a single FuseReg decoder reconstructs from full, sparse, and single-layer fusions without retraining, achieving higher PSNR than decoders specialized to fixed fusions. This flexibility also benefits generation: decoder replacement alone reduces unguided gFID by 27% with an unchanged RAEv2 DiT-XL generator. Applying FuseReg to both stages also reduces unguided gFID by 29% on DiT-Base. The reconstruction and generation benefits also extend to other encoder families. FuseReg narrows the reconstruction-generation gap without additional training cost or architectural changes.

cs.CV↗

arXiv2026

PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems

AutoResearch improves systems through iterative experimentation: agents propose candidate modifications, evaluate them, and use the results to guide subsequent exploration. Applying this paradigm to industrial search presents two challenges. (1) Common AutoResearch approaches follow a keep-if-better rule, retaining the highest-scoring candidate for subsequent experiments. Under non-stationary traffic, transient gains may be mistaken for persistent improvements, impairing reliable accumulation of search knowledge. (2) Candidate modifications can be evaluated at multiple fidelity levels, from low-cost proxies to online validation, differing in cost, objective alignment, and statistical reliability. Existing methods rely on individual signals or task-specific procedures, lacking a unified basis for using evidence across levels to guide search. We introduce Progressive Evidence-Based AutoResearch (PEAR) with two complementary components. Evidence-driven AutoResearch maintains an independent, hypothesis-guided research state for each strategy task within a predefined objective and intervention scope. Each state evolves through a Plan-Execute-Evaluate-Update transition that links experimentation to context-aware evidence interpretation and hypothesis revision. Confidence-Gated Verifier Ladder organizes evaluation into four levels of increasing fidelity: Offline Replay, Shadow-Traffic Evaluation, Rapid Online Evaluation, and Decision-Grade Online Evaluation. A unified confidence-based gate promotes candidates only when evidence supports a statistically significant positive effect, enabling broad low-cost exploration while reserving costly online experiments for promoted candidates. In a real-world industrial search system, strategies optimized with PEAR significantly increased Main Order/DAU by 2.7336% and 3.2957% relative to their respective baselines in two A/B experiments.

cs.IR↗

arXiv2026

AwarenessBench: Assessing Cognitive Capabilities of Language Models

As language models (LMs) exhibit increasingly consciousness-like behaviors, evaluating their cognitive abilities becomes essential. We introduce AwarenessBench, the first comprehensive benchmark for assessing the cognitive abilities of LMs in four dimensions: metacognition, self-awareness, social awareness, and situational awareness, covering 15 cognitive functions and 14,381 samples. Evaluating 18 state-of-the-art LMs, we find that all consistently surpass random baselines, with more advanced models performing better. We further compare LMs with human performance across three demographic groups, where the best-performing model surpasses human averages overall, but most still fall markedly short in metacognition and self-awareness. Finally, we show that awareness is a distinct capability: progress in language modeling or reasoning does not necessarily translate into improved cognition.

cs.CL↗

arXiv2026

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implicit. We introduce YuE2, which unifies symbolic and audio music generation at frontier quality through symbolic planning. A single AR-NAR Mixture-of-Transformers (MoT) first writes a readable score specifying melody and harmony, expands it into semantic music tokens, and realizes it as full-song audio. In comparisons using the same checkpoint, experts prefer symbolic planning for overall quality and musicality, with 49.3% of overall preferences versus 34.6% without planning. Experts also favor the unified model over a separate language model and diffusion Transformer. On WildSongBench, YuE2 scores 6.73 on SongBench Global Avg, exceeding all evaluated public baselines. Selecting from eight candidates (best-of-8), YuE2 reaches 6.96, the highest observed mean among all evaluated systems. Expert listening further establishes its competitiveness with proprietary song generators, favoring best-of-8 over Suno v4.5 and yielding nearly balanced preferences against Suno v5. To learn this generation process from recordings without aligned scores, we introduce MERT2 and SheetSage2 to supply semantic and symbolic supervision. MERT2 sets a new state of the art in music representation learning, surpassing previous best results on 14 of 15 MARBLE metrics; SheetSage2 leads 12 of 15 benchmark-metric pairs in our lead-sheet transcription comparison. The same checkpoint follows score edits while largely preserving unedited musical content and generates zero-shot covers without cover-specific training. Its readable score also enables agentic music editing, with external language models translating user feedback into revisions of the composition.

eess.AS↗

arXiv2026

COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning

Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated speech typically relies on clear user-specified instructions. In natural conversations, speaking style should be naturally inferred from the preceding conversational context. Therefore, we propose COT-TTS, a context-aware, reasoning-based text-to-speech task. Given historical conversation audio, target text, and a reference speech, the system should comprehend the conversational context, infer an explicit intermediate reasoning, and finally synthesize the target speech with the specified timbre. To support this task, we constructed a large-scale bilingual conversational speech dataset comprising 9 million training samples, including a high-quality subset of 1 million samples. We further constructed a source-disjoint benchmark with 800 human-verified samples and established strong task-specific baselines. Additionally, we developed end-to-end autoregressive models with parameter sizes of 0.6B and 1.7B, generating emotion-labeled transcripts, editable speech style inferences, and speech tokens. Experimental results show that the proposed model achieves performance comparable to large-scale baseline systems with significantly fewer parameters. At the same time, the model performs well in terms of duration consistency and emotional consistency, and can generate appropriate emotional, stress, and rhythmic variations based on the conversational context. To facilitate future research, we will publicly release the data construction pipeline, dataset, trained models, and related resources. The demo page and additional resources are available at https://luckybian.github.io/COT-TTS

cs.CL↗

arXiv2026

From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks

Mobile GUI agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.

cs.AI↗

arXiv2026

Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation

Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic interactions among agents. Distributionally robust Markov games (DRMGs) provide a principled framework for addressing such uncertainty, yet existing methods often rely on restrictive assumptions or scale poorly to large state and joint action spaces. We study online learning in general-sum DRMGs with general function approximation and $ϕ$-divergence uncertainty sets. We propose RoMEX-$ϕ$, a model-free framework that integrates equilibrium-based exploration with dual fitted learning. Through a functional dual representation of the robust multi-agent Bellman operator, RoMEX-$ϕ$ enables tractable worst-case value estimation from nominal interaction data using a centered empirical robust discrepancy. We introduce the robust Multi-Agent Decoupling Coefficient (robust MADC) to characterize the intrinsic exploration complexity arising from strategic interactions and adversarial transition uncertainty. We establish sublinear robust regret guarantees governed by the robust MADC rather than explicitly by the state and joint action space sizes, replacing tabular dependence with intrinsic function-class complexity. Numerical experiments on a scalable general-sum DRMG under total variation uncertainty show that RoMEX-$ϕ$ is substantially more resilient to transition shifts than its non-robust counterpart while remaining competitive with an exact tabular robust baseline. Our results provide a scalable framework for distributionally robust multi-agent reinforcement learning with general function approximation.

cs.LG↗

arXiv2026

Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes

Robust average-reward Markov decision processes provide a fundamental framework for long-term performance optimization under uncertainty, and can have optimal long-run rewards that depend on the initial state. This state dependence requires a vector Bellman theory that accounts for both recurrent-class rewards and transition uncertainty. We develop such a theory for finite models with compact, post-action $(s,a)$-rectangular ambiguity. A gain-first, bias-second optimization principle yields a coupled vector gain-bias system, and every finite solution identifies the optimal robust gain and supplies stationary saddle strategies against history-dependent opponents, simultaneously from all initial states. We further characterize solvability through stationary gain conditions and a uniform bound on canonical transient corrections, and give sufficient conditions that permit distinct recurrent-class gains. The certificates also yield asymptotically affine trajectories of the robust Bellman operator, based on which we design a robust approximately shifted Halpern planning algorithm. Under finite Bellman solvability, the gain estimates and Bellman displacements converge to the optimal gain vector, and every extracted greedy controller is average-optimal after a finite, instance-dependent budget. These results thus connect finite Bellman certificates to undiscounted planning for state-dependent robust average rewards, providing theoretical understandings.

cs.LG↗

arXiv2026

Duet: Dual-Robot Understanding via Efficient Teaching

Dual-robot collaboration enables tasks that exceed the reach and payload of a single robot, such as collaboratively transporting objects across environments and executing coordinated handovers. Data acquisition is the primary bottleneck for training these systems. To this end, we introduce DUET, a dual-robot learning framework for mobile manipulation. For efficient data collection, we create a unified dual-embodiment synchronized VR-based teleoperation system for in-domain heterogeneous robot data collection. We further develop a complementary tracking pipeline that records human-human coordination and collaborative mobile manipulation priors. To allow efficient learning, we introduce an Action Chunking Transformer based architecture that first pretrains collaborative policies on efficient human-human demonstrations, before finetuning them on a minimal set of real-robot teleoperation trajectories. We develop a benchmark of four collaborative tasks to evaluate our framework using a Unitree G1 humanoid and a Dexmate Vega1 mobile manipulator. The results demonstrate that harnessing human priors not only yields superior task performance compared to baselines trained only on robot data, but also reduces the total human effort required for data collection. Our human data collection pipeline achieves 5.4 times acceleration on average from teleoperation, but we perform better than robot-only data trained policies across all tasks. Our project page is available at https://zhaoy37.github.io/Duet/.

cs.RO↗

arXiv2026

On Property (H) of c_0 and Lipschitz Problems of Gromov and Johnson

Let $X$ be a normed space and $S_X$ be the unit sphere of $X$. We say that $X$ has Property (H) if there exist two increasing sequences $V_j\subset X$ and $H_j\subset \ell_2$, $j=1,2,\ldots$, of finite dimensional subspaces such that $V=\bigcup_j V_j$ is dense in $X$, and there is a uniformly continuous mapping $ψ:S_V\to S_{\ell_2}$ such that the restrictions $ψ|_{S_{V_j}}$, $j=1,2,\ldots$, are isomorphisms from $S_{V_j}$ onto $S_{H_j}$. The Kasparov-Yu problem asks whether the Banach space $c_0$ of all null sequences admits Property (H), or rational Property (H). In this paper, we prove that $c_0$ admits neither Property (H) nor rational Property (H). We also obtain the following results. (1) The infimum $μ_n$ of the Lipschitz constants of all nonzero-degree maps from $S_{\ell_\infty^n}$ to $S_{\ell_2^n}$ satisfies $\lim_{n\to\infty} μ_n/\log n=1/2$. (2) Let $λ_n$ and $C_n$ denote the infima of the Lipschitz constants of homeomorphisms from $S_{\ell_\infty^n}$ onto $S_{\ell_2^n}$ and from $B_{\ell_\infty^n}$ onto $B_{\ell_2^n}$, respectively. Then $\lim_{n\to\infty} λ_n/\log n=\lim_{n\to\infty} C_n/\log n=1/2$. The first result solves a problem of Gromov on nonzero-degree maps between finite-dimensional spheres, while the second settles Johnson's problem on the Lipschitz distortion of finite-dimensional unit balls.

math.FA↗