Publications (34)
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment
Songlin Li, Zhiqing Guo, Dan Ma +2
Although some existing image manipulation localization (IML) methods incorporate authenticity-related supervision, this information is typically utilized merely as an auxiliary tra…
GIFGuard: Proactive Forensics against Deepfakes in Facial GIFs via Spatiotemporal Watermarking
Shupeng Che, Zhiqing Guo, Changtao Miao +2
The rapid evolution of deepfake technology poses an unprecedented threat to the authenticity of Graphics Interchange Format (GIF) imagery, which serves as a representative of short…
Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization
Songlin Li, Guofeng Yu, Zhiqing Guo +3
Deep learning-based image manipulation localization (IML) methods have achieved remarkable performance in recent years, but typically rely on large-scale pixel-level annotated data…
WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
Ziyuan He, Zhiqing Guo, Liejun Wang +3
Deepfake technology poses increasing risks such as privacy invasion and identity theft. To address these threats, we propose WaveGuard, a proactive watermarking framework that enha…
Game of Learning Bloch Equation Simulations for MR Fingerprinting
Mingrui Yang, Yun Jiang, Dan Ma +2
Purpose: This work proposes a novel approach to efficiently generate MR fingerprints for MR fingerprinting (MRF) problems based on the unsupervised deep learning model generative a…
Step-DeepResearch Technical Report
Chen Hu, Haikuo Du, Heng Wang +64
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands f…
SL() contravariant tensor valuations of small orders
Jin Li, Dan Ma
A complete classification of \(\mathrm{SL}(n)\) contravariant, \(p\)-order tensor valuations on convex polytopes in \( \mathbb{R}^n \) for \( n \geq p \) is established without imp…
Motion robust MR fingerprinting scan to image neonates with prenatal opioid exposure
Dan Ma, Chaitra Badve, Jessie EP Sun +10
Background: A noninvasive and sensitive imaging tool is needed to assess the fast-evolving baby brain. However, using MRI to study non-sedated babies faces roadblocks, including hi…
Optimal Experiment Design for Magnetic Resonance Fingerprinting: Cramér-Rao Bound Meets Spin Dynamics
Bo Zhao, Justin P. Haldar, Congyu Liao +5
Magnetic resonance (MR) fingerprinting is a new quantitative imaging paradigm, which simultaneously acquires multiple MR tissue parameter maps in a single experiment. In this paper…
Entity-Aspect-Opinion-Sentiment Quadruple Extraction for Fine-grained Sentiment Analysis
Dan Ma, Jun Xu, Zongyu Wang +2
Product reviews often contain a large number of implicit aspects and object-attribute co-existence cases. Unfortunately, many existing studies in Aspect-Based Sentiment Analysis (A…
Twins:Device-free Object Tracking using Passive Tags
Jinsong Han, Chen Qian, Dan Ma +5
Without requiring objects to carry any transceiver, device-free based object tracking provides a promising solution for many localization and tracking systems to monitor non-cooper…
A Fast MR Fingerprinting Simulator for Direct Error Estimation and Sequence Optimization
Siyuan Hu, Stephen Jordan, Rasim Boyacioglu +5
MR Fingerprinting is a novel quantitative MR technique that could simultaneously provide multiple tissue property maps. When optimizing MRF scans, modeling undersampling errors and…
A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
Peng Ding, Jun Kuang, Dan Ma +4
Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safegu…
DiffMark: Diffusion-based Robust Watermark Against Deepfakes
Chen Sun, Haiyang Sun, Zhiqing Guo +5
Deepfakes pose significant security and privacy threats through malicious facial manipulations. While robust watermarking can aid in authenticity verification and source tracking,…
Conformational change-modulated spin transport at the single-molecule level in carbon systems --Invited for the Third Carbon Special Topic
Yan-Dong Guo, Xue Zhao, Hong-Ru Zhao +6
Controlling the spin transport at the single-molecule level, especially without the use of ferromagnetic contacts, becomes a focus of research in spintronics. Inspired by the progr…
Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
Peng Ding, Jingyu Wu, Jun Kuang +6
Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on various visual-language understanding and generation tasks. However, MLLMs occasionally genera…
3D MR Fingerprinting for Dynamic Contrast-Enhanced Imaging of Whole Mouse Brain
Yuran Zhu, Guanhua Wang, Yuning Gu +9
Quantitative MRI enables direct quantification of contrast agent concentrations in contrast-enhanced scans. However, the lengthy scan times required by conventional methods are ina…
General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
Junlin Liu, Shengnan An, Shuang Zhou +10
Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their abil…
SL() contravariant vector valuations
Jin Li, Dan Ma, Wei Wang
All SL() contravariant vector valuations on polytopes in are completely classified without any additional assumptions. The facet vector is defined. It turns out to…
Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
Dan Ma, Bin Liu, Zhao Kang +3
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications. Although a number of generative models have been developed to…
Laplace transforms and valuations
Jin Li, Dan Ma
It is proved that the classical Laplace transform is a continuous valuation which is positively GL covariant and logarithmic translation covariant. Conversely, these propertie…
Asymmetric anisotropic fractional Sobolev norms
Dan Ma
Bourgain, Brezis & Mironescu showed that (with suitable scaling) the fractional Sobolev -seminorm of a function converges to the Sobolev seminorm of…
Automatic Intent-Slot Induction for Dialogue Systems
Zengfeng Zeng, Dan Ma, Haiqin Yang +2
Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional metho…
Whether, Which, and Whose: Solving the Triple Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios
Lei Zhang, Zhiqing Guo, Dan Ma +2
Unlike single-face forgeries, deepfakes in complex multi-person interaction scenarios (such as group photos and multi-person meetings) more closely reflect real-world threats. Alth…
When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry
Guofeng Yu, Zhiqing Guo, Dan Ma +1
Existing image manipulation localization (IML) methods rely heavily on 2D forensic cues, such as low-level artifacts, noise traces, and semantic inconsistencies in the manipulated…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…
Real-valued valuations on Sobolev spaces
Dan Ma
Continuous, SL() and translation invariant real-valued valuations on Sobolev spaces are classified.
AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
Shengnan An, Xunliang Cai, Xuezhi Cao +8
We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have wid…
DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection
Joymallya Chakraborty, Wei Xia, Anirban Majumder +3
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fra…
Color-map recommendation for MR relaxometry maps
Miha Fuderer, Barbara Wichtmann, Fabio Crameri +15
Purpose: To harmonize the use of color for MR relaxometry maps and therefore recommend the use of specific color-maps for representing T1 and T2 maps. Methods: Perceptually lineari…
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
Lixin Jia, Haiyang Sun, Zhiqing Guo +3
With the rapid evolution of deepfake technologies and the wide dissemination of digital media, personal privacy is facing increasingly serious security threats. Deepfake proactive…
Stability and slicing inequalities for intersection bodies
Alexander Koldobsky, Dan Ma
We prove a generalization of the hyperplane inequality for intersection bodies, where volume is replaced by an arbitrary measure with even continuous density and sections are…
Automated Design of Pulse Sequences for Magnetic Resonance Fingerprinting using Physics-Inspired Optimization
Stephen P. Jordan, Siyuan Hu, Ignacio Rozada +9
Magnetic Resonance Fingerprinting (MRF) is a method to extract quantitative tissue properties such as T1 and T2 relaxation rates from arbitrary pulse sequences using conventional m…