arXiv subjects

Baochang Zhang

Publications and source records attributed to Baochang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but incurs substantial costs from rollouts and policy updates. Online prompt selection improves efficiency by using per-prompt Bayesian posteriors to predict difficulty and prioritize informative prompts. However, existing methods overlook how reliably learning signals are extracted from sampled responses. In GRPO, a response's advantage depends on both its own outcome and the randomly sampled outcomes of its peers through group normalization. Our theoretical and experimental analyses show that uncertainty in group composition introduces composition noise, a non-vanishing variance component that imposes an irreducible lower bound on gradient estimation error and impairs downstream prompt selection. We propose MaPP (Marginalized Posterior-Predictive), a unified framework for data-efficient RLVR that denoises response-level advantage estimation and improves prompt selection using a shared Beta posterior. For each response, MaPP replaces the standard group-relative advantage with a composition-invariant intrinsic advantage through closed-form Beta-Binomial marginalization. The resulting posterior-predictive estimator has an error that provably diminishes as the posterior concentrates. Using the same posterior, MaPP derives an uncertainty-aware prompt selection score to improve data efficiency without additional rollout cost. Experiments on mathematics, planning, and visual geometry across five model backbones show that MaPP consistently outperforms GRPO and strong selection baselines, achieving up to +2.45 average accuracy improvement over the strongest baseline under the same rollout budget and setting a new state of the art.

cs.LG↗

arXiv2026

Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning

Group-based reinforcement learning such as GRPO trains LLM agents by comparing rollouts sampled for each task, without a learned critic. In long-horizon settings, these rollouts revisit shared anchor states, offering cross-rollout evidence for step-level credit. Ideally, step-level credit should incorporate evidence beyond the realized suffixes observed at an anchor while aggregating alternative continuations according to their empirical frequencies. Visit-local averaging pools realized suffix returns at shared anchors and respects observed frequencies, but does not recursively propagate evidence across rollouts, whereas shortest-path estimators have global reach but allow a rarely observed route to dominate an anchor's value. We introduce Cross-Rollout Bellman Closure (CRBC), which merges each rollout group into a finite empirical process with absorbing success and failure boundaries and evaluates its behavior-policy Bellman fixed point with one linear solve. This fixed point uses the same empirical action and transition frequencies to propagate evidence through shared anchors and aggregate alternative continuations. Backing up the resulting state values through observed transitions yields action values, whose gain over the corresponding state value provides step-level credit. A corresponding finite-depth family recovers visit-local return averaging at zero depth and converges to the exact closure as depth increases. The normalized closure credit is combined with the trajectory-level group advantage for policy optimization, without additional environment rollouts. Across ALFWorld, WebShop, and Sokoban benchmarks with multiple model scales, CRBC consistently improves final performance and learning efficiency. For example, CRBC outperforms the strongest evaluated baseline by 5.59 percentage points on ALFWorld with Qwen2.5-1.5B-Instruct.

cs.LG↗

arXiv2026

GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents

Group-based reinforcement learning (RL) has advanced large language models (LLMs) and is increasingly extending to agentic tasks, where sparse terminal rewards make step-level credit assignment essential. Existing methods assign credit from what follows an action in sampled rollouts, but do not explicitly capture its retrospective relation to the realized outcome. Hindsight credit assignment (HCA) instead attributes credit through the ratio of hindsight to behavior-policy probabilities, but estimating the hindsight distribution requires an auxiliary model or an extra pass. To address this estimation bottleneck, we propose GraphHCA, a model-free realization of HCA that eliminates explicit hindsight-distribution estimation. For terminal-goal tasks with deterministic transitions, Bayes' rule reduces the hindsight ratio to a ratio of behavior-policy success probabilities at consecutive states. Taking logs yields a state-wise success potential, whose increment across a transition provides step-level credit. GraphHCA estimates this potential from pooled rollouts through a discounted recursion on the induced transition graph, which admits a unique fixed point on any directed graph. The resulting step-level signal is combined with the trajectory-level advantage, requiring neither a learned hindsight model nor an extra forward pass and recovering GRPO when the step-level weight is zero. Among all compared baselines, GraphHCA achieves state-of-the-art results on ALFWorld and WebShop at both LLM scales, and on Sokoban with a vision-language agent. For example, on ALFWorld it improves overall success rate by up to 24.6 points over GRPO and by up to 4.7 points over the strongest step-level baseline.

cs.LG↗

arXiv2026

MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery

Monocular 3D hand and body mesh recovery often suffers from severe occlusion and ambiguity. Traditional deterministic methods typically regress a single optimal solution, leading to overconfident predictions. In this paper, we introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection. Specifically, during exploration, based on our probabilistic formulation and entropy maximization, we propose a novel multi-hypothesis method referred to as MHE-Former. It is a Transformer-based multi-hypothesis framework, ensuring high training efficiency and label friendliness while generating plausible and diverse hypotheses. During exploitation, we propose Hypothesis Selection, a context-aware process for multiple predictions. Especially leveraging VLM's powerful visual understanding and reasoning capabilities, it allows users to choose the most plausible and desired estimate with additional evidence and natural language intent. Extensive experiments demonstrate that our framework achieves state-of-the-art performance in accuracy and diversity across multiple datasets. The user preference study further shows the practicality of our hypothesis selection process.

cs.CV↗

arXiv2026

Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and accelerate inference, but extreme compression (i.e., mean bit-width <= 2) often leads to severe performance degradation. To address this, we propose Squeeze10-LLM, effectively "squeezing" 16-bit LLMs' weights by 10 times. Specifically, Squeeze10-LLM is a staged mixed-precision post-training quantization (PTQ) framework and achieves an average of 1.6 bits per weight by quantizing 80% of the weights to 1 bit and 20% to 4 bits. We introduce Squeeze10LLM with two key innovations: Post-Binarization Activation Robustness (PBAR) and Full Information Activation Supervision (FIAS). PBAR is a refined weight significance metric that accounts for the impact of quantization on activations, improving accuracy in low-bit settings. FIAS is a strategy that preserves full activation information during quantization to mitigate cumulative error propagation across layers. Experiments on LLaMA and LLaMA2 show that Squeeze10-LLM achieves state-of-the-art performance for sub-2bit weight-only quantization, improving average accuracy from 43% to 56% on six zero-shot classification tasks--a significant boost over existing PTQ methods.

cs.LG↗

arXiv2026

AcoustiTrace: When Plausible Sound Violates Physics

Recent audio-video generators can produce semantically plausible and apparently synchronized sound, yet may still violate the acoustic processes implied by visible events and environments. Existing benchmarks provide limited support for attributing such violations to particular acoustic processes and quantifying their severity. We introduce AcoustiTrace, a diagnostic benchmark that formalizes acoustic physical realism in audio-video generation. AcoustiTrace organizes text-to-audio-video (T2AV) and image-to-audio-video (I2AV) evaluation around the acoustic process, covering sound generation, propagation environment, and acoustic reception through eight dimensions grounded in measurable acoustic quantities. Based on these evaluation dimensions, we construct a large-scale dataset organized around acoustic mechanisms, comprising real-world audio-video recordings and acoustically annotated RGB-D observations, and use it to develop targeted prompt suites and validated evaluators. Experiments reveal that even leading generators still struggle with fundamental acoustic processes despite producing plausible sound events. Finally, we show that the diagnostics AcoustiTrace provides for specific acoustic relations can guide model refinement toward more physically faithful audio and open new directions for incorporating acoustic principles into training objectives, reward modeling, and candidate selection.

cs.MM↗

arXiv2026

Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing

Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural consistency of the original motion. Existing diffusion-based approaches struggle to balance text-responsive "change" and inertial "invariance". They often rely on coarse spatial constraints and rigid uniform time assumptions, leading to spatial motion distortions and the destruction of intrinsic physical rhythms during variable-length editing. To handle these challenges, we propose Change and Invariance Motion Editing (CIME), a unified framework that comprehensively decouples change and invariance into spatial pose and temporal rhythm dimensions. For spatial poses, our method integrates an omni-supervised positive-negative learning mechanism comprising hierarchical retrospective feature supervision, subtle motion preservation, and triplet-based semantic alignment. For temporal rhythms, we introduce the Riemannian Non-uniform Integral Manifold Mapping (RNIMM) module, which achieves high-fidelity reproduction of physical beats in the edited text via kinematics-aware non-uniform timestamps. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that CIME achieves state-of-the-art performance in editing alignment and structural fidelity, validating the effectiveness of our unified architecture. Our source codes and models have been released at: github.com/ZhenwuShi/CIME.git

cs.CV↗

arXiv2026

RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification

Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approaches typically predict scene-level accidents, infer risk objects indirectly from ego behavior, or apply geometric checks after trajectory forecasting, without directly using predicted ego--object relations for risk-source localization. We propose RiskWorld, an object-centric latent world model that identifies risk from the imagined evolution of each candidate relative to the ego vehicle. RiskWorld combines pretrained predictive video representations with structured ego--object histories, contextualizes observed interactions, and rolls relation-aware object states into the future using RSSM-style latent dynamics. It decodes the rollout into object-level risk scores, supported by auxiliary future-relation and temporal-risk predictions. Inference uses only observations up to the current time, while logged futures provide training supervision. On RiskBench, RiskWorld achieves the best overall F1 of 63.0\% and the lowest false-alarm rate of 2.1\%. Further analyses show that the learned rollout captures the evolution of object-level risk before critical events, while RiskWorld's selections preserve planning-critical information under filtered observation.

cs.RO↗

arXiv2026

Contextual Information Policy Optimization for Search Agents

Search agents extend large language models beyond static parametric memory by enabling them to acquire and use external evidence during multi-step reasoning. For knowledge-intensive tasks involving complex or evolving information, their reliability depends not only on retrieving relevant evidence but also on using it to guide subsequent reasoning. However, existing methods primarily reward final-answer correctness or intermediate progress, without directly assessing whether post-retrieval actions are grounded in the retrieved evidence. This misalignment encourages prior-driven reasoning: agents form conclusions based on internal knowledge and use retrieval mainly to confirm them, resulting in confirmation bias and inefficient evidence use. To address this issue, we propose Contextual Information Policy Optimization (CIPO), an evidence-oriented reinforcement learning framework that explicitly aligns policy optimization with external evidence use. CIPO assigns dense, turn-level credit to reasoning actions influenced by retrieved information, while combining this evidence-use signal with a global outcome reward to preserve answer correctness. With this manner, CIPO discourages evidence-detached guesses and promotes reasoning trajectories in which retrieved facts can guide or revise subsequent reasoning. Importantly, CIPO requires neither human process annotations nor an additional reward model. Extensive experiments on seven in-domain and out-of-domain benchmarks show that CIPO reduces the prevalence of prior-driven reasoning and achieves excellent performance on most tasks.

cs.AI↗

arXiv2026

CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM

Simultaneous localization and mapping (SLAM) based on Neural Radiance Fields (NeRF) enables dense, continuous scene reconstruction. However, existing systems operating with limited online resources struggle to simultaneously construct two types of constraints, namely, compact yet discriminative spatial constraints derived from scene representations and persistent temporal constraints derived from historical observations. To address this challenge, we propose CHOW-SLAM, a dense RGB-D SLAM framework that explicitly constructs these complementary spatial and temporal constraints. Spatially, we propose a compact parametric-hash (P-H) hybrid representation that organizes components based on planes and grids across scales in P and H branches. A unified multi-output decoder further aligns the ray termination distributions induced by TSDF and density, preserving geometry and appearance under a compact parameter budget. Temporally, we propose a complementary overlap-window strategy to prevent optimization from being dominated by short-term overlap or weakly related historical observations. Within a fixed budget, the strategy retains recent frames, selects high-overlap local frames, and introduces temporally distributed historical keyframes. Loss-aware keyframe insertion and bundle adjustment scheduling further adapt optimization to tracking quality. In addition, ORB-based tracking and geometric pose estimation are used for pose initialization, followed by neural rendering optimization to improve tracking stability. Extensive evaluations on multiple datasets demonstrate that CHOW-SLAM outperforms state-of-the-art methods in both scene reconstruction quality and camera tracking accuracy. The source code is available at https://github.com/jinjidexiaohuoban/CHOW-SLAM.

cs.CV↗

arXiv2026

PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion

Existing autoregressive (AR) methods for generating artist-designed meshes struggle to balance global structural consistency with high-fidelity local details, and are susceptible to error accumulation. To address this, we propose PartDiffuser, a novel semi-autoregressive diffusion framework for point-cloud-to-mesh generation. The method first performs semantic segmentation on the mesh and then operates in a "part-wise" manner: it employs autoregression between parts to ensure global topology, while utilizing a parallel discrete diffusion process within each semantic part to precisely reconstruct high-frequency geometric features. PartDiffuser is based on the DiT architecture and introduces a part-aware cross-attention mechanism, using point clouds as hierarchical geometric conditioning to dynamically control the generation process, thereby effectively decoupling the global and local generation tasks. Experiments demonstrate that this method significantly outperforms state-of-the-art (SOTA) models in generating 3D meshes with rich detail, exhibiting exceptional detail representation suitable for real-world applications.

cs.CV↗

arXiv2026

Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning

Reinforcement learning (RL) finetuning significantly enhances the reasoning capabilities of large language models (LLMs), yet its effectiveness critically depends on selecting prompts of appropriate difficulty for the current policy. This is challenging because prompt difficulty evolves throughout training. Existing online methods therefore face a trade-off: evaluation-based approaches are accurate but expensive, while prediction-based approaches are efficient but typically assume stationary difficulty, making them ill-suited to RL's non-stationary training dynamics. To address these issues, we propose a Kalman-Guided Prompt Selection method (KGPS), which reformulates prompt selection as a dynamic state estimation problem rather than static difficulty prediction. KGPS models each prompt's latent success rate in logit space using a linear-Gaussian state-space model, with process noise coupled to the magnitude of policy updates so that uncertainty increases when the policy changes more substantially. A Kalman filter then maintains a calibrated Gaussian posterior over prompt difficulty, and prompts are selected by maximizing a posterior-expected training utility that favors intermediate-difficulty prompts while naturally revisiting uncertain ones. The resulting procedure is adaptive to policy drift and requires no additional rollouts beyond standard policy training. Extensive experiments across mathematics, planning, and geometry reasoning benchmarks, as well as multiple RL algorithms, show that KGPS consistently improves both final accuracy and rollout efficiency over strong baselines, establishing state-of-the-art performance among online prompt selection methods. For example, on DeepSeek-R1-Distill-7B, KGPS uses 83% fewer rollouts than DS while even improving the average performance by 0.12 point across six math reasoning benchmarks.

cs.LG↗

arXiv2026

End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation

Generating closed-loop traffic scenarios that are both realistic and controllable is crucial for evaluating autonomous driving systems, especially under rare safety-critical interactions. Existing learning-based methods often struggle to balance controllability and realism, offering either limited fine-grained control over traffic behavior or controllable scenarios at the expense of behavioral plausibility. This paper presents E2E-CDiff, an end-to-end conditional diffusion framework for controllable and realistic scenario generation. Conditioned on front-view visual observations, E2E-CDiff jointly denoises future motion states and executable low-level controls for route-interacting background vehicles. This unified state-action generation mitigates the planning-control mismatch in conventional two-stage trajectory-then-controller pipelines. Differentiable guidance further regulates speed, enforces drivable-area compliance, and supports collision-avoidance or collision-seeking behaviors, enabling both naturalistic and safety-critical scenario generation. Experiments on Bench2Drive show that E2E-CDiff achieves a favorable controllability-realism trade-off compared with representative reinforcement- and imitation-learning baselines, while its collision-guided variant induces challenging interactions across multiple autonomous driving systems. E2E-CDiff also performs competitively as a learning-based ego planner, demonstrating the generality of end-to-end state-action diffusion.

cs.RO↗

arXiv2026

FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written. We reveal that Post-Training Quantization (PTQ) error easily flips these borderline decisions at the write frontier, which are then permanently locked in and amplified. To address this, we propose Frontier-Aware Instability-Reweighted Calibration (FAIR-Calib), a two-stage PTQ framework for dLLMs. Stage I probes a full-precision teacher to estimate a position prior that combines frontier hits and masked-stage reliability. Stage II performs off-policy, layer-wise calibration by minimizing a reweighted hidden-state MSE, effectively prioritizing the protection of fragile frontier states without requiring expensive end-to-end diffusion rollouts. We further theoretically justify our weighted objective as a surrogate for output KL divergence. Empirically, FAIR-Calib consistently outperforms state-of-the-art baselines on LLaDA and Dream (W4A4), significantly reducing frontier decision flips and suppressing post-commit mismatches across diverse benchmarks.

cs.LG↗

arXiv2026

LDFE: Laplacian Decoupled Feature Enhancement Block for Dual-Stream CNN-based RGB-IR Object Detection

The complementary information between RGB and IR images can significantly enhance object detection performance under extreme conditions. Existing methods prefer dual-stream CNN backbones built upon YOLO for feature extraction and focus on the design of feature fusion. In this paper, we introduce the Laplacian Decoupled Feature Enhancement block (LDFE) to fuse features from different stages of the dual-stream CNN backbone. By design, LDFE simultaneously considers the characteristics of modalities and structures for feature fusion by employing global-local decomposition, denoising, fusion, and reconstruction, sequentially. The LDFE first separates features into global and local components based on Laplacian Pyramid, and then performs denoising and fusion based on Global State Space Enhancement module (GS2E) and Local Convolutional Correlation Enhancement module (LC2E) separately. Specifically, the GS2E conducts a two-branch architecture for the main and auxiliary modalities. It dynamically suppresses noise in the main modality through cross-modal attention derived from the auxiliary modality, while employing a State Space Model to capture long-range dependencies within the global feature representations of the main modality. To obtain bidirectional interaction, the two modalities systematically alternate their main/auxiliary roles. Moreover, the LC2E suppresses noise in local features and leverages spatial and channel dimension along with triple convolution to extract fine-grained details for fusion. These innovative designs achieve a significant performance improvement, with mAP surpassing the SOTA methods 6.2%, 3.7%, 4.7%, 2.3%, 4.1% and 2.0% on M3FD, DroneVehicle, LLVIP, FLIR-Aligned, KAIST and VEDAI datasets,respectively.

cs.CV↗

arXiv2026

MAC-XA: Multi-view Anatomy-Correspondence Fusion for Coronary Stenosis Reporting from X-ray Angiography

Multi-view reasoning in coronary X-ray angiography is inherently a cross-projection geometric problem, yet automated report generation in this setting remains largely unexplored. The 3D vascular topology leads to projection-dependent branch overlap and foreshortening, rendering single-view modeling fundamentally incomplete and unstable for lesion localization and stenosis grading. Although multi-view fusion appears promising, learning anatomically consistent fusion from real angiograms is impeded by a critical limitation: cross-view alignment is unobservable and cannot be explicitly supervised. Consequently, conventional fusion relies on implicit correlations rather than verified anatomical correspondence. We address this by reformulating multi-view stenosis reporting as an alignment-constrained aggregation problem. A controllable synthetic angiography generation strategy is introduced to expose geometry-derived patch-level correspondence supervision unavailable in real data. An anatomy-correspondence module learns cross-view correspondence matrices that explicitly align auxiliary features within the main-view coordinate space prior to fusion, thereby constraining evidence aggregation to anatomically consistent regions. Experiments on synthetic data and zero-shot transfer to real angiograms show that this alignment-constrained design improves correspondence consistency and structured stenosis reporting compared to single-view modeling and conventional multi-view fusion methods. The code will be publicly available upon publication.

cs.CV↗

arXiv2026

InfraNet: Quality-Aware RGB Guidance for Efficient Infrared Object Detection

Robust object detection under adverse visual conditions remains a long-standing challenge for multi-modal perception systems. Existing fusion-based methods typically require both RGB and infrared (IR) inputs, and treat them equally during both training and inference, which compromises their robustness when the RGB modality becomes unreliable or unavailable. In this case, we propose \textbf{InfraNet}, an IR-centric quality-aware framework that regulates RGB guidance during training and supports flexible RGB--IR or IR-only deployment. InfraNet employs an asymmetric architecture where the primary IR pathway extracts multi-scale infrared features for predictions, while the auxiliary RGB pathway provides reliability-controlled supervisory signals. The core of InfraNet is \textbf{QualGate}, a quality-aware fusion module that learns a task-oriented control signal to suppress unreliable RGB guidance and compensate IR features during cross-modal training. Built upon InfraNet, we design two architectural variants: a lightweight IR-only architecture InfraNet-IR and an RGB--IR architecture InfraNet-RGB-IR. Our method is evaluated through extensive experiments on four benchmark datasets (LLVIP, FLIR-Aligned, M$^3$FD, and DroneVehicle), showing strong or competitive accuracy in challenging low-light and adverse weather conditions. Notably, InfraNet maintains high efficiency in IR-only inference, making it both accurate and computationally efficient.

cs.CV↗

arXiv2026

Teaching Vision-Language-Action Models What to See and Where to Look

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects driving-specific perceptual priors into the vision encoder, while 2D Trajectory-Guided Prompts (2D-TGP) provide spatial conditioning aligned with feasible driving trajectories. Together, they form a vision-guided learning pipeline: what to see (DVD pretraining) - where to look (TGP-guided SFT) - how to act (TGP-guided GRPO). DriveTeach-VLA achieves the state-of-the-art performance on NAVSIM and nuScenes. Our code is available at: https://github.com/ShivaTeam/DriveTeach-VLA.

cs.CV↗