arXiv subjects

Zhihao Zhang

Publications and source records attributed to Zhihao Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Learning High-Quality Initial Noise for Single-View Synthesis with Diffusion Models

Single-view novel view synthesis (NVS) models based on diffusion models have recently attracted increasing attention, as they can generate a series of novel view images from a single image prompt and camera pose information as conditions. It has been observed that in diffusion models, certain high-quality initial noise patterns lead to better generation results than others. However, there remains a lack of dedicated learning frameworks that enable NVS models to learn such high-quality noise. To obtain high-quality initial noise from random Gaussian noise, we make the following contributions. First, we design a discretized Euler inversion method to inject image semantic information into random noise, thereby constructing paired datasets of random and high-quality noise. Second, we propose a learning framework based on an encoder-decoder network (EDN) that directly transforms random noise into high-quality noise. Experiments demonstrate that the proposed EDN can be seamlessly plugged into various NVS models, such as SV3D and MV-Adapter, achieving significant performance improvements across multiple datasets. Code is available at: https://github.com/zhihao0512/EDN.

cs.CV↗

arXiv2025

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance performance. However, these breakthroughs are predominantly observed for the mathematically strong Qwen2.5 series on benchmarks such as MATH-500, AMC, and AIME, and seldom transfer to models like Llama, which warrants a more in-depth investigation. In this work, our empirical analysis reveals that pre-training on massive web-scale corpora leaves Qwen2.5 susceptible to data contamination in widely used benchmarks. Consequently, conclusions derived from contaminated benchmarks on Qwen2.5 series may be unreliable. To obtain trustworthy evaluation results, we introduce a generator that creates fully clean arithmetic problems of arbitrary length and difficulty, dubbed RandomCalculation. Using this leakage-free dataset, we show that only accurate reward signals yield steady improvements that surpass the base model's performance boundary in mathematical reasoning, whereas random or incorrect rewards do not. Moreover, we conduct more fine-grained analyses to elucidate the factors underlying the different performance observed on the MATH-500 and RandomCalculation benchmarks. Consequently, we recommend that future studies evaluate models on uncontaminated benchmarks and, when feasible, test various model series to ensure trustworthy conclusions about RL and related methods.

cs.LG↗

arXiv2025

SignRAG: A Retrieval-Augmented System for Scalable Zero-Shot Road Sign Recognition

Automated road sign recognition is a critical task for intelligent transportation systems, but traditional deep learning methods struggle with the sheer number of sign classes and the impracticality of creating exhaustive labeled datasets. This paper introduces a novel zero-shot recognition framework that adapts the Retrieval-Augmented Generation (RAG) paradigm to address this challenge. Our method first uses a Vision Language Model (VLM) to generate a textual description of a sign from an input image. This description is used to retrieve a small set of the most relevant sign candidates from a vector database of reference designs. Subsequently, a Large Language Model (LLM) reasons over the retrieved candidates to make a final, fine-grained recognition. We validate this approach on a comprehensive set of 303 regulatory signs from the Ohio MUTCD. Experimental results demonstrate the framework's effectiveness, achieving 95.58% accuracy on ideal reference images and 82.45% on challenging real-world road data. This work demonstrates the viability of RAG-based architectures for creating scalable and accurate systems for road sign recognition without task-specific training.

cs.CV↗

arXiv2025

The Role of Entropy in Visual Grounding: Analysis and Optimization

Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.

cs.CV↗

arXiv2025

From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation

Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health measures. Recent advancements in generative AI, capable of producing realistic, human like text and images, have significantly accelerated the spread and expanded the reach of health misinformation, resulting in an alarming surge in its dissemination. To combat the infodemics, most existing work has focused on developing misinformation datasets from social media and fact checking platforms, but has faced limitations in topical coverage, inclusion of AI generation, and accessibility of raw content. To address these issues, we present MM Health, a large scale multimodal misinformation dataset in the health domain consisting of 34,746 news article encompassing both textual and visual information. MM Health includes human-generated multimodal information (5,776 articles) and AI generated multimodal information (28,880 articles) from various SOTA generative AI models. Additionally, We benchmarked our dataset against three tasks (reliability checks, originality checks, and fine-grained AI detection) demonstrating that existing SOTA models struggle to accurately distinguish the reliability and origin of information. Our dataset aims to support the development of misinformation detection across various health scenarios, facilitating the detection of human and machine generated content at multimodal levels.

cs.CL↗

arXiv2025

Models for the Electric Dipole Moment and Anomalous Magnetic Moment of the Tau Lepton

The Belle II experiment and other ongoing and projected lepton facilities are expected to greatly enhance the sensitivity to the electric dipole moment (EDM) and anomalous magnetic moment ($g-2$) for the tau lepton, making it timely to explore models that predict these observables. We present a class of models that generate a sizable EDM and $g-2$ of the tau lepton via radiative tau mass generation. Two benchmark models with different hypercharge assignments are investigated. The first model contains neutral fermions and charged scalars. We find that the model can predict a large signal of the tau EDM, $d_τ = \mathcal{O}(10^{-19}) \, e \, {\rm cm}$, and $g-2$, $a_τ = \mathcal{O}(10^{-5})$, which are within the reach of future updates of their measurements. In contrast, the second model, containing a charged fermion and neutral scalars, yields a similar magnitude for the $g-2$ but predicts a comparatively smaller EDM signal. Our models serve as benchmarks for new physics generating sizable EDM and $g-2$ of the tau lepton.

hep-ph↗

arXiv2025

AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions based on environmental feedback. Previous work for LLM agents typically relies on elaborate prompt engineering or fine-tuning with expert trajectories to improve performance. In this work, we take a different perspective: we explore constructing process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process. Unlike LLM reasoning, where each step is scored based on correctness, actions in agent tasks do not have a clear-cut correctness. Instead, they should be evaluated based on their proximity to the goal and the progress they have made. Building on this insight, we propose a re-defined PRM for agent tasks, named AgentPRM, to capture both the interdependence between sequential decisions and their contribution to the final goal. This enables better progress tracking and exploration-exploitation balance. To scalably obtain labeled data for training AgentPRM, we employ a Temporal Difference-based (TD-based) estimation method combined with Generalized Advantage Estimation (GAE), which proves more sample-efficient than prior methods. Extensive experiments across different agentic tasks show that AgentPRM is over $8\times$ more compute-efficient than baselines, and it demonstrates robust improvement when scaling up test-time compute. Moreover, we perform detailed analyses to show how our method works and offer more insights, e.g., applying AgentPRM to the reinforcement learning of LLM agents.

cs.CL↗

arXiv2025

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios--including sample replay and partial rollout--BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking.

cs.LG↗

arXiv2025

Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process

Terrain analysis is critical for the practical ap- plication of ground mobile robots in real-world tasks, espe- cially in outdoor unstructured environments. In this paper, we propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to effectively navigate through complex terrains. Our approach utilizes sparse Gaussian processes (SGP) to extract geometric features (curvature, gradient, elevation, etc.) directly from point cloud scans. These features are then used to construct a high- resolution local traversability map. Then, we design a spatial- temporal Bayesian Gaussian kernel (BGK) inference method to dynamically evaluate traversability scores, integrating historical and real-time data while considering factors such as slope, flatness, gradient, and uncertainty metrics. GPU acceleration is applied in the feature extraction step, and the system achieves real-time performance. Extensive simulation experiments across diverse terrain scenarios demonstrate that our method outper- forms SOTA approaches in both accuracy and computational efficiency. Additionally, we develop an autonomous navigation framework integrated with the traversability map and validate it with a differential driven vehicle in complex outdoor envi- ronments. Our code will be open-source for further research and development by the community, https://github.com/ZJU-FAST-Lab/FSGP_BGK.

cs.RO↗

arXiv2025

Postsphaleron darkogenesis

A supercooled phase transition in a nearly conformal dark sector can provide a natural setting for darkogenesis via its out-of-equilibrium dynamics, where a particle-antiparticle number asymmetry in the dark sector can be reprocessed into the visible sector, yielding the observed baryon asymmetry and an asymmetric dark matter. We consider a scenario where the number asymmetry is generated from the decay of a mother particle produced via parametric resonance during the phase transition induced due to its coupling to the dilaton associated with spontaneous breaking of scale invariance. It is shown that the correct baryon asymmetry and dark matter abundance can be realized for a dark phase transition at $\mathcal{O}(1) \, \rm GeV$, which can also explain the nano-Hz gravitational wave signal reported by pulsar timing array experiments. The scenario will be tested further in neutron-antineutron oscillation experiments.

hep-ph↗

arXiv2025

EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection

Recent advances in foundation models have driven remarkable progress in image editing, yet their extension to 3D editing remains underexplored. A natural approach is to replace the image editing modules in existing workflows with foundation models. However, their heavy computational demands and the restrictions and costs of closed-source APIs make plugging these models into existing iterative editing strategies impractical. To address this limitation, we propose EditCast3D, a pipeline that employs video generation foundation models to propagate edits from a single first frame across the entire dataset prior to reconstruction. While editing propagation enables dataset-level editing via video models, its consistency remains suboptimal for 3D reconstruction, where multi-view alignment is essential. To overcome this, EditCast3D introduces a view selection strategy that explicitly identifies consistent and reconstruction-friendly views and adopts feedforward reconstruction without requiring costly refinement. In combination, the pipeline both minimizes reliance on expensive image editing and mitigates prompt ambiguities that arise when applying foundation models independently across images. We evaluate EditCast3D on commonly used 3D editing datasets and compare it against state-of-the-art 3D editing baselines, demonstrating superior editing quality and high efficiency. These results establish EditCast3D as a scalable and general paradigm for integrating foundation models into 3D editing pipelines. The code is available at https://github.com/UNITES-Lab/EditCast3D

cs.CV↗

arXiv2025

SVAC: Scaling Is All You Need For Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment target objects in video sequences based on natural language descriptions. While recent advances in Multi-modal Large Language Models (MLLMs) have improved RVOS performance through enhanced text-video understanding, several challenges remain, including insufficient exploitation of MLLMs' prior knowledge, prohibitive computational and memory costs for long-duration videos, and inadequate handling of complex temporal dynamics. In this work, we propose SVAC, a unified model that improves RVOS by scaling up input frames and segmentation tokens to enhance video-language interaction and segmentation precision. To address the resulting computational challenges, SVAC incorporates the Anchor-Based Spatio-Temporal Compression (ASTC) module to compress visual tokens while preserving essential spatio-temporal structure. Moreover, the Clip-Specific Allocation (CSA) strategy is introduced to better handle dynamic object behaviors across video clips. Experimental results demonstrate that SVAC achieves state-of-the-art performance on multiple RVOS benchmarks with competitive efficiency. Our code is available at https://github.com/lizhang1998/SVAC.

cs.CV↗

arXiv2025

An Uncertainty-Weighted Decision Transformer for Navigation in Dense, Complex Driving Scenarios

Autonomous driving in dense, dynamic environments requires decision-making systems that can exploit both spatial structure and long-horizon temporal dependencies while remaining robust to uncertainty. This work presents a novel framework that integrates multi-channel bird's-eye-view occupancy grids with transformer-based sequence modeling for tactical driving in complex roundabout scenarios. To address the imbalance between frequent low-risk states and rare safety-critical decisions, we propose the Uncertainty-Weighted Decision Transformer (UWDT). UWDT employs a frozen teacher transformer to estimate per-token predictive entropy, which is then used as a weight in the student model's loss function. This mechanism amplifies learning from uncertain, high-impact states while maintaining stability across common low-risk transitions. Experiments in a roundabout simulator, across varying traffic densities, show that UWDT consistently outperforms other baselines in terms of reward, collision rate, and behavioral stability. The results demonstrate that uncertainty-aware, spatial-temporal transformers can deliver safer and more efficient decision-making for autonomous driving in complex traffic environments.

cs.RO↗

arXiv2025

Advancing Real-World Parking Slot Detection with Large-Scale Dataset and Semi-Supervised Baseline

As automatic parking systems evolve, the accurate detection of parking slots has become increasingly critical. This study focuses on parking slot detection using surround-view cameras, which offer a comprehensive bird's-eye view of the parking environment. However, the current datasets are limited in scale, and the scenes they contain are seldom disrupted by real-world noise (e.g., light, occlusion, etc.). Moreover, manual data annotation is prone to errors and omissions due to the complexity of real-world conditions, significantly increasing the cost of annotating large-scale datasets. To address these issues, we first construct a large-scale parking slot detection dataset (named CRPS-D), which includes various lighting distributions, diverse weather conditions, and challenging parking slot variants. Compared with existing datasets, the proposed dataset boasts the largest data scale and consists of a higher density of parking slots, particularly featuring more slanted parking slots. Additionally, we develop a semi-supervised baseline for parking slot detection, termed SS-PSD, to further improve performance by exploiting unlabeled data. To our knowledge, this is the first semi-supervised approach in parking slot detection, which is built on the teacher-student model with confidence-guided mask consistency and adaptive feature perturbation. Experimental results demonstrate the superiority of SS-PSD over the existing state-of-the-art (SoTA) solutions on both the proposed dataset and the existing dataset. Particularly, the more unlabeled data there is, the more significant the gains brought by our semi-supervised scheme. The relevant source codes and the dataset have been made publicly available at https://github.com/zzh362/CRPS-D.

cs.CV↗

arXiv2025

Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving

Automated vehicle control using reinforcement learning (RL) has attracted significant attention due to its potential to learn driving policies through environment interaction. However, RL agents often face training challenges in sample efficiency and effective exploration, making it difficult to discover an optimal driving strategy. To address these issues, we propose guiding the RL driving agent with a demonstration policy that need not be a highly optimized or expert-level controller. Specifically, we integrate a rule-based lane change controller with the Soft Actor Critic (SAC) algorithm to enhance exploration and learning efficiency. Our approach demonstrates improved driving performance and can be extended to other driving scenarios that can similarly benefit from demonstration-based guidance.

cs.RO↗

arXiv2025

Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective

Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic features facilitate effective knowledge transfer. In contrast, for non-Latin script language (NSL), such as Chinese and Japanese, performance often degrades due to deep structural differences. To address these challenges, we propose an entity-aligned translation (EAT) approach. Leveraging large language models (LLMs), EAT employs a dual-translation strategy to align entities between NSL and English. In addition, we fine-tune LLMs using multilingual Wikipedia data to enhance the entity alignment from source to target languages.

cs.CL↗

arXiv2025

Asymmetric stress engineering of dense dislocations in brittle superconductors for strong vortex pinning

Large lossless currents in high-temperature superconductors (HTS) critically rely on dense defects with suitable size and dimensionality to pin vortices, with dislocations being particularly effective due to their one-dimensional geometry to interact extensively with vortex lines. However, in non-metallic compounds such as HTS with rigid lattices, conventional deformation methods typically lead to catastrophic fracture rather than dislocation-mediated plasticity, making it a persistent challenge to introduce dislocations at high density. Here, we propose an asymmetric stress field strategy using extrusion to directly nucleate a high-density of dislocations in HTS by activating shear-driven lattice slip and twisting under superimposed hydrostatic compression. As demonstrated in iron-based superconductors (IBS), atomic displacements of nearly one angstrom trigger the formation of tilted dislocation lines with a density approaching that of metals. With further structural refinement, these dislocations serve as strong pinning centers that lead to a fivefold enhancement in the current-carrying capacity of IBS at 33 T, along with low anisotropy and a large irreversibility field. This work not only establishes a scalable route to engineer pinning landscapes in HTS, but also offers a generalizable framework for manipulating dislocation structures in rigid crystalline systems.

cond-mat.supr-con↗

arXiv2025

CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector

Monocular 3D object detectors, while effective on data from one ego camera height, struggle with unseen or out-of-distribution camera heights. Existing methods often rely on Plucker embeddings, image transformations or data augmentation. This paper takes a step towards this understudied problem by first investigating the impact of camera height variations on state-of-the-art (SoTA) Mono3D models. With a systematic analysis on the extended CARLA dataset with multiple camera heights, we observe that depth estimation is a primary factor influencing performance under height variations. We mathematically prove and also empirically observe consistent negative and positive trends in mean depth error of regressed and ground-based depth models, respectively, under camera height changes. To mitigate this, we propose Camera Height Robust Monocular 3D Detector (CHARM3R), which averages both depth estimates within the model. CHARM3R improves generalization to unseen camera heights by more than $45\%$, achieving SoTA performance on the CARLA dataset. Codes and Models at https://github.com/abhi1kumar/CHARM3R

cs.CV↗