arXiv subjects

Zikang Zhang

Publications and source records attributed to Zikang Zhang.

7 recordsLinked to original sources

arXiv2026

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21, 2026 release. Leveraging the Twitter API v2 and a multi-stage curation pipeline spanning multilingual text heuristics (English, Japanese, and Chinese), browser-automated Twitter "Made with AI" badge verification, and model name variant matching, we curate 10,217 confirmed GPT-image-2 images from 27,662 collected records over a six-day window. We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters). A key negative result is that C2PA content credentials are systematically stripped by Twitter's CDN on upload, rendering cryptographic provenance verification infeasible for social-media-sourced AI images. The dataset and all curation code are released publicly.

cs.CV↗

arXiv2026

Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies for safety intervention across diverse tasks. To better understand and control LLM safety, we propose the Expected Safety Impact (ESI) framework for quantifying how different parameters affect LLM safety. Based on ESI, we reveal distinct safety-critical patterns across different LLM architectures: In dense LLMs, many safety-critical parameters are located in value matrices (V) and MLPs in middle layers, whereas in Mixture-of-Experts (MoE) models, they shift to the late-layer MLPs. Leveraging ESI, we further introduce two targeted intervention paradigms for safety enhancement and preservation, i.e., Safety Enhancement Tuning (SET) and Safety Preserving Adaptation (SPA). SET can align unsafe LLMs by updating only a few safety-critical parameters, effectively enhancing safety while preserving original performance. SPA safeguards well-aligned LLMs during capability-oriented intervention (e.g., instruction tuning) by preventing disruption of safety-critical weights, allowing the LLM to acquire new abilities and maintain safety capabilities. Extensive evaluations on different LLMs demonstrate that SET can reduce the attack success rates of unaligned LLMs by over 50% with only a 100-iteration update on 1% of model weights. SPA can limit the safety degradation of aligned LLMs within 1% after a 1,000-iteration instruction fine-tuning on different tasks. Our code is available at: https://github.com/ZJU-LLM-Safety/SafeWeights-ACL.

cs.CR↗

arXiv2026

CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations

Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robust spatial mental model. We identify three core cognitive challenges hindering this transition: spatial reasoning, long-horizon state tracking via mental simulation, and active exploration under partial observation. To isolate and evaluate these faculties, we introduce CubeBench, a novel generative benchmark centered on the Rubik's Cube. CubeBench uses a three-tiered diagnostic framework that progressively assesses agent capabilities, from foundational state tracking with full symbolic information to active exploration with only partial visual data. Our experiments on leading LLMs reveal critical limitations, including a uniform 0.00% pass rate on all long-horizon tasks, exposing a fundamental failure in long-term planning. We also propose a diagnostic framework to isolate these cognitive bottlenecks by providing external solver tools. By analyzing the failure modes, we provide key insights to guide the development of more physically-grounded intelligent agents.

cs.AI↗

arXiv2025

Efficient Implementation of Arbitrary Two-Qubit Gates via Unified Control

The native gate set is fundamental to the performance of quantum devices, as it governs the accuracy of basic quantum operations and dictates the complexity of implementing quantum algorithms. Traditional approaches to extending gate sets often require accessing multiple transitions within an extended Hilbert space, leading to increased control complexity while offering only a limited set of gates. Here, we experimentally demonstrate a unified and highly versatile gate scheme capable of natively generating arbitrary two-qubit gates using only exchange interaction and qubit driving on a superconducting quantum processor, achieving maximum expressivity. Using a state-of-the-art transmon-coupler-transmon architecture, we achieve high fidelities averaging $99.37 \pm 0.07\%$ across a wide range of commonly used two-qubit unitaries. This outstanding performance, combined with reduced complexity, enables precise multipartite entangled state preparation, as demonstrated. To further enhance its applicability, we also show the high-fidelity realization of the unique B gate, which efficiently synthesizes the entire family of two-qubit gates. Our results highlight that fully exploiting the capabilities of a single interaction can yield a comprehensive and highly accurate gate set. With maximum expressivity, gate-time optimality, demonstrated high fidelity, and easy adaptability to other quantum platforms, our unified control scheme paves the way for optimal performance in quantum devices, offering exciting prospects for advancing quantum hardware and algorithm development.

quant-ph↗

arXiv2024

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning

Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities.However, their massive number of parameters leads to high deployment requirements and incurs significant inference costs, which impedes their practical applications. Training smaller models is an effective way to address this problem. Therefore, we introduce OpenBA-V2, a 3.4B model derived from multi-stage compression and continual pre-training from the original 15B OpenBA model. OpenBA-V2 utilizes more data, more flexible training objectives, and techniques such as layer pruning, neural pruning, and vocabulary pruning to achieve a compression rate of 77.3\% with minimal performance loss. OpenBA-V2 demonstrates competitive performance compared to other open-source models of similar size, achieving results close to or on par with the 15B OpenBA model in downstream tasks such as common sense reasoning and Named Entity Recognition (NER). OpenBA-V2 illustrates that LLMs can be compressed into smaller ones with minimal performance loss by employing advanced training objectives and data strategies, which may help deploy LLMs in resource-limited scenarios.

cs.CL↗

arXiv2023

A large-scale multimodal dataset of human speech recognition

Nowadays, non-privacy small-scale motion detection has attracted an increasing amount of research in remote sensing in speech recognition. These new modalities are employed to enhance and restore speech information from speakers of multiple types of data. In this paper, we propose a dataset contains 7.5 GHz Channel Impulse Response (CIR) data from ultra-wideband (UWB) radars, 77-GHz frequency modulated continuous wave (FMCW) data from millimetre wave (mmWave) radar, and laser data. Meanwhile, a depth camera is adopted to record the landmarks of the subject's lip and voice. Approximately 400 minutes of annotated speech profiles are provided, which are collected from 20 participants speaking 5 vowels, 15 words and 16 sentences. The dataset has been validated and has potential for the research of lip reading and multimodal speech recognition.

eess.SP↗

arXiv2019

Bias-free reconfigurable magnonic phase shifter based on a spin-current controlled ferromagnetic resonator

Controllable phase modulation plays a pivotal role in the researches of magnonic logic gates. Here we propose a reconfigurable spin-current controlled magnonic phase shifter based on a ferromagnetic resonator. The proposed phase shifter requires no magnetic bias field during operation. The device is directly configured over the waveguide while keeping the original structure of the waveguide unaffected. Numerical micromagnetic simulations show that the phase shifter could yield either a π-phase or no shift depending on the magnetization status of the resonator, which can be controlled by a current pulse. Moreover, the phase-shifting operation could be affected by spin current. At different input current density, the device could be either used as a dynamic controlled phase shifter or a spin-wave valve. Finally, a XNOR magnonic logic gate is demonstrated using the proposed phase shifter. Our work can be a beneficial step to enhance the functionality and compatibility of the magnonic logic circuits.

physics.app-ph↗