arXiv subjects

Yan Ma

Publications and source records attributed to Yan Ma.

At least 37 records · Page 2Linked to original sources

arXiv2025

Mechanistic insights into hydrogen reduction of multicomponent oxides via in-situ high-energy X-ray diffraction

Co-reduction of multicomponent oxides with hydrogen provides a carbon-neutral approach toward sustainable alloy design. Herein, we investigate the hydrogen-based direct reduction, using in-situ high-energy X-ray diffraction of two precursor variants: mechanically mixed powders and pre-sintered oxide mixtures, targeting an equiatomic CoFeMnNi alloy. We find distinct reduction pathways and microstructure evolution depending on initial precursors. Mixed powders at 700 °C are reduced to body-centered-cubic, face-centered-cubic, and MnO phases via halite, spinel, and Mn3O4 intermediates, whereas the pre-sintered material directly transforms into a mixture of metallic and oxide phases. The post-reduction microstructures are also different: mixed oxides show loosely packed morphology, whereas pre-sintered material reveals metallic nanoparticles supported on nanoporous MnO. The formation of nanoporous metallic networks is strongly governed by the precursor state, highlighting the role of initial precursors on the final microstructure. This precursor design strategy offers a single-step route to nanoporous alloys with potential applications in catalysis and energy technologies.

cond-mat.mtrl-sci↗

arXiv2025

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools, making them brittle and constrained by a predefined toolkit, while others fine-tune specialist models that often adopt a single reasoning strategy, such as text-based chain-of-thought (CoT). The intermediate steps of text-based reasoning are difficult to verify, which complicates the use of reinforcement-learning signals that reward factual accuracy. To address this, we propose a Code-as-Thought (CaT) approach to represent the visual information of a chart in a verifiable, symbolic format. Our key insight is that this strategy must be adaptive: a fixed, code-only implementation consistently fails on complex charts where symbolic representation is unsuitable. This finding leads us to introduce Visual Programmability: a learnable property that determines if a chart-question pair is better solved with code or direct visual analysis. We implement this concept in an adaptive framework where a VLM learns to choose between the CaT pathway and a direct visual reasoning pathway. The selection policy of the model is trained with reinforcement learning using a novel dual-reward system. This system combines a data-accuracy reward to ground the model in facts and prevent numerical hallucination, with a decision reward that teaches the model when to use each strategy, preventing it from defaulting to a single reasoning mode. Experiments demonstrate strong and robust performance across diverse chart-understanding benchmarks. Our work shows that VLMs can be taught not only to reason but also how to reason, dynamically selecting the optimal reasoning pathway for each task.

cs.CV↗

arXiv2025

Robust End-to-End FSO Transmission with Joint Coding Modulation and BiLSTM-Based Channel Modeling under Atmospheric Turbulence

Free space optical (FSO) communication is considered a promising solution in next_generation communication networks. However, its performance is significantly influenced by atmospheric turbulence. To enhance system robustness to turbulence, we propose a turbulence_robust end_to_end FSO communication system (TRFSO) that integrates a data-driven channel model with joint source_channel coding modulation (JSCCM). Specifically, a bidirectional long short-term memory (BiLSTM)_based channel model is developed and trained on data collected over a physical FSO link under varying turbulence conditions. This model accurately captures real_world channel distortions, achieving a minimum Kullback_Leibler (KL) divergence of 0.0019 in amplitude distribution matching. Experimental results show that the TRFSO system trained with the BiLSTM_based channel model outperforms the same architecture trained under the additive white Gaussian noise (AWGN) channel, achieving an average 3.5 dB improvement in multi-scale structural similarity (MS_SSIM) under strong atmospheric turbulence. These results demonstrate the effectiveness of the proposed TRFSO in achieving robust and reliable transmission under dynamic atmospheric turbulence.

physics.optics↗

arXiv2025

Interaction as Intelligence: Deep Research With Human-AI Partnership

This paper introduces "Interaction as Intelligence" research series, presenting a reconceptualization of human-AI relationships in deep research tasks. Traditional approaches treat interaction merely as an interface for accessing AI capabilities-a conduit between human intent and machine output. We propose that interaction itself constitutes a fundamental dimension of intelligence. As AI systems engage in extended thinking processes for research tasks, meaningful interaction transitions from an optional enhancement to an essential component of effective intelligence. Current deep research systems adopt an "input-wait-output" paradigm where users initiate queries and receive results after black-box processing. This approach leads to error cascade effects, inflexible research boundaries that prevent question refinement during investigation, and missed opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a system that transforms the human role from giving instructions to cognitive oversight-a mode of engagement where humans guide AI thinking processes through strategic intervention at critical junctures. Deep cognition implements three key innovations: (1)Transparent, controllable, and interruptible interaction that reveals AI reasoning and enables intervention at any point; (2)Fine-grained bidirectional dialogue; and (3)Shared cognitive context where the system observes and adapts to user behaviors without explicit instruction. User evaluation demonstrates that this cognitive oversight paradigm outperforms the strongest baseline across six key metrics: Transparency(+20.0%), Fine-Grained Interaction(+29.2%), Real-Time Intervention(+18.5%), Ease of Collaboration(+27.7%), Results-Worth-Effort(+8.8%), and Interruptibility(+20.7%). Evaluations on challenging research problems show 31.8% to 50.0% points of improvements over deep research systems.

cs.CL↗

arXiv2025

Sustainable Pre-reduction of Ferromanganese Oxides with Hydrogen: Heating Rate-Dependent Reduction Pathways and Microstructure Evolution

The reduction of ferromanganese ores into metallic feedstock is an energy-intensive process with substantial carbon emissions, necessitating sustainable alternatives. Hydrogen-based pre-reduction of manganese-rich ores offers a low-emission pathway to augment subsequent thermic Fe-Mn alloy production. However, reduction dynamics and microstructure evolution under varying thermal conditions remain poorly understood. This study investigates the influence of heating rate on the hydrogen-based direct reduction of natural Nchwaning ferromanganese ore and a synthetic analog. Non-isothermal thermogravimetric analysis revealed a complex multistep reduction process with overlapping kinetic regimes. Isoconversional kinetic analysis showed increased activation energy with reduction degree, indicating a transition from surface-reaction to diffusion-controlled reduction mechanisms. Interrupted X-ray diffraction experiments suggested that slow heating enables complete conversion to MnO and metallic Fe, while rapid heating promotes Fe- and Mn-oxides intermixing. Thermodynamic calculations for the Fe-Mn-O system predicted the equilibrium phase evolution, indicating Mn stabilized Fe-containing spinel and halite phases. Microstructural analysis revealed that slow heating rate yields fine and dispersed Fe particles in a porous MnO matrix, while fast heating leads to sporadic Fe-rich agglomerates. These findings suggest heating rate as a critical parameter governing reduction pathway, phase distribution, and microstructure evolution, thus offering key insights for optimizing hydrogen-based pre-reduction strategies towards more efficient and sustainable ferromanganese production.

cond-mat.mtrl-sci↗

arXiv2025

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers

Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial context, creating a fundamental "semantic gap" between rich perceptual data and discrete symbolic thought. Human cognition often transcends language, utilizing vision as a dynamic mental sketchpad. A similar evolution is now unfolding in AI, marking a fundamental paradigm shift from models that merely think about images to those that can truly think with images. This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace. In this survey, we chart this evolution of intelligence along a trajectory of increasing cognitive autonomy, which unfolds across three key stages: from external tool exploration, through programmatic manipulation, to intrinsic imagination. To structure this rapidly evolving field, our survey makes four key contributions. (1) We establish the foundational principles of the think with image paradigm and its three-stage framework. (2) We provide a comprehensive review of the core methods that characterize each stage of this roadmap. (3) We analyze the critical landscape of evaluation benchmarks and transformative applications. (4) We identify significant challenges and outline promising future directions. By providing this structured overview, we aim to offer a clear roadmap for future research towards more powerful and human-aligned multimodal AI.

cs.CV↗

arXiv2025

Hydrogen-based direct reduction of multicomponent oxides: Insights from powder and pre-sintered precursors toward sustainable alloy design

The co-reduction of metal oxide mixtures using hydrogen as a reductant in conjunction with compaction and sintering of the evolving metallic blends offers a promising alternative toward sustainable alloy production through a single, integrated, and synergistic process. Herein, we provide fundamental insights into hydrogen-based direct reduction (HyDR) of distinct oxide precursors that differ by phase composition and morphology. Specifically, we investigate the co-reduction of multicomponent metal oxides targeting a 25Co-25Fe-25Mn-25Ni (at.%) alloy, by using either a compacted powder (mechanically mixed oxides) comprising Co3O4-Fe2O3-Mn2O3-NiO or a pre-sintered compound (chemically mixed oxides) comprising a Co,Ni-rich halite and a Fe,Mn-rich spinel. Thermogravimetric analysis (TGA) at a heating rate of 10 °C/min reveals that the reduction onset temperature for the compacted powder was ~175 °C, whereas it was significantly delayed to ~525 °C for the pre-sintered sample. Nevertheless, both sample types attained a similar reduction degree (~80%) after isothermal holding for 1 h at 700 °C. Phase analysis and microstructural characterization of reduced samples confirmed the presence of metallic Co, Fe, and Ni alongside MnO. A minor fraction of Fe remains unreduced, stabilized in the (Fe,Mn)O halite phase, in accord with thermodynamic calculations. Furthermore, ~1 wt.% of BCC phase was found only in the reduced pre-sintered sample, owing to the different reduction pathways. The kinetics and thermodynamics effects were decoupled by performing HyDR experiments on pulverized pre-sintered samples. These findings demonstrate that initial precursor states influence both the reduction behavior and the microstructural evolution, providing critical insights for the sustainable production of multicomponent alloys.

cond-mat.mtrl-sci↗

arXiv2025

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. The M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSeek R1. Furthermore, the lightning attention mechanism in MiniMax-M1 enables efficient scaling of test-time compute. These properties make M1 particularly suitable for complex tasks that require processing long inputs and thinking extensively. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems including sandbox-based, real-world software engineering environments. In addition to M1's inherent efficiency advantage for RL training, we propose CISPO, a novel RL algorithm to further enhance RL efficiency. CISPO clips importance sampling weights rather than token updates, outperforming other competitive RL variants. Combining hybrid-attention and CISPO enables MiniMax-M1's full RL training on 512 H800 GPUs to complete in only three weeks, with a rental cost of just $534,700. We release two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively, where the 40K model represents an intermediate phase of the 80K training. Experiments on standard benchmarks show that our models are comparable or superior to strong open-weight models such as the original DeepSeek-R1 and Qwen3-235B, with particular strengths in complex software engineering, tool utilization, and long-context tasks. We publicly release MiniMax-M1 at https://github.com/MiniMax-AI/MiniMax-M1.

cs.CL↗

arXiv2025

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework

High-quality math datasets are crucial for advancing the reasoning abilities of large language models (LLMs). However, existing datasets often suffer from three key issues: outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation. To address these, we introduce STORM-BORN, an ultra-challenging dataset of mathematical derivations sourced from cutting-edge academic papers, which includes dense human-like approximations and heuristic cues. To ensure the reliability and quality, we propose a novel human-in-the-loop, multi-agent data generation framework, integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians' evaluations. We curated a set of 2,000 synthetic samples and deliberately selected the 100 most difficult problems. Even most advanced models like GPT-o1 solved fewer than 5% of them. Fine-tuning on STORM-BORN boosts accuracy by 7.84% (LLaMA3-8B) and 9.12% (Qwen2.5-7B). As AI approaches mathematician-level reasoning, STORM-BORN provides both a high-difficulty benchmark and a human-like reasoning training resource. Our code and dataset are publicly available at https://github.com/lwhere/STORM-BORN.

cs.CL↗

arXiv2025

Thinking with Generated Images

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through spontaneous generation of intermediate visual thinking steps. Current visual reasoning with LMMs is constrained to either processing fixed user-provided images or reasoning solely through text-based chain-of-thought (CoT). Thinking with Generated Images unlocks a new dimension of cognitive capability where models can actively construct intermediate visual thoughts, critique their own visual hypotheses, and refine them as integral components of their reasoning process. We demonstrate the effectiveness of our approach through two complementary mechanisms: (1) vision generation with intermediate visual subgoals, where models decompose complex visual tasks into manageable components that are generated and integrated progressively, and (2) vision generation with self-critique, where models generate an initial visual hypothesis, analyze its shortcomings through textual reasoning, and produce refined outputs based on their own critiques. Our experiments on vision generation benchmarks show substantial improvements over baseline approaches, with our models achieving up to 50% (from 38% to 57%) relative improvement in handling complex multi-object scenarios. From biochemists exploring novel protein structures, and architects iterating on spatial designs, to forensic analysts reconstructing crime scenes, and basketball players envisioning strategic plays, our approach enables AI models to engage in the kind of visual imagination and iterative refinement that characterizes human creative, analytical, and strategic thinking. We release our open-source suite at https://github.com/GAIR-NLP/thinking-with-generated-images.

cs.CV↗

arXiv2025

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

The first generation of Large Language Models - what might be called "Act I" of generative AI (2020-2023) - achieved remarkable success through massive parameter and data scaling, yet exhibited fundamental limitations such as knowledge latency, shallow reasoning, and constrained cognitive processes. During this era, prompt engineering emerged as our primary interface with AI, enabling dialogue-level communication through natural language. We now witness the emergence of "Act II" (2024-present), where models are transitioning from knowledge-retrieval systems (in latent space) to thought-construction engines through test-time scaling techniques. This new paradigm establishes a mind-level connection with AI through language-based thoughts. In this paper, we clarify the conceptual foundations of cognition engineering and explain why this moment is critical for its development. We systematically break down these advanced approaches through comprehensive tutorials and optimized implementations, democratizing access to cognition engineering and enabling every practitioner to participate in AI's second act. We provide a regularly updated collection of papers on test-time scaling in the GitHub Repository: https://github.com/GAIR-NLP/cognition-engineering

cs.CL↗

arXiv2025

Unraveling the thermodynamics and mechanism behind the lowering of reduction temperatures in oxide mixtures

Hydrogen-based direct reduction offers a sustainable pathway to decarbonize the metal production industry. However, stable metal oxides, like Cr$_2$O$_3$, are notoriously difficult to reduce, requiring extremely high temperatures (above 1300 $^\circ$C). Herein, we show how reducing mixed oxides can be leveraged to lower hydrogen-based reduction temperatures of stable oxides and produce alloys in a single process. Using a newly developed thermodynamic framework, we predict the precise conditions (oxygen partial pressure, temperature, and oxide composition) needed for co-reduction. We showcase this approach by reducing Cr$_2$O$_3$ mixed with Fe$_2$O$_3$ at 1100 $^\circ$C, significantly lowering reduction temperatures (by $\geq$200 $^\circ$C). Our model and post-reduction atom probe tomography analysis elucidate that the temperature-lowering effect is driven by the lower chemical activity of Cr in the metallic phase. This strategy achieves low-temperature co-reduction of mixed oxides, dramatically reducing energy consumption and CO$_2$ emissions, while unlocking transformative pathways toward sustainable alloy design.

cond-mat.mtrl-sci↗

arXiv2025

Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Reinforcement learning (RL) has recently shown strong potential in improving the reasoning capabilities of large language models and is now being actively extended to vision-language models (VLMs). However, existing RL applications in VLMs often rely on heavily engineered frameworks that hinder reproducibility and accessibility, while lacking standardized evaluation protocols, making it difficult to compare results or interpret training dynamics. This work introduces a transparent, from-scratch framework for RL in VLMs, offering a minimal yet functional four-step pipeline validated across multiple models and datasets. In addition, a standardized evaluation scheme is proposed to assess training dynamics and reflective behaviors. Extensive experiments on visual reasoning tasks uncover key empirical findings: response length is sensitive to random seeds, reflection correlates with output length, and RL consistently outperforms supervised fine-tuning (SFT) in generalization, even with high-quality data. These findings, together with the proposed framework, aim to establish a reproducible baseline and support broader engagement in RL-based VLM research.

cs.LG↗

arXiv2025

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

cs.CL↗

arXiv2025

SpellRing: Recognizing Continuous Fingerspelling in American Sign Language using a Ring

Fingerspelling is a critical part of American Sign Language (ASL) recognition and has become an accessible optional text entry method for Deaf and Hard of Hearing (DHH) individuals. In this paper, we introduce SpellRing, a single smart ring worn on the thumb that recognizes words continuously fingerspelled in ASL. SpellRing uses active acoustic sensing (via a microphone and speaker) and an inertial measurement unit (IMU) to track handshape and movement, which are processed through a deep learning algorithm using Connectionist Temporal Classification (CTC) loss. We evaluated the system with 20 ASL signers (13 fluent and 7 learners), using the MacKenzie-Soukoref Phrase Set of 1,164 words and 100 phrases. Offline evaluation yielded top-1 and top-5 word recognition accuracies of 82.45% (9.67%) and 92.42% (5.70%), respectively. In real-time, the system achieved a word error rate (WER) of 0.099 (0.039) on the phrases. Based on these results, we discuss key lessons and design implications for future minimally obtrusive ASL recognition wearables.

cs.HC↗

arXiv2025

Study on the structure of the $Z_{c}(3900)$ state

In this work, we studied the $Z_{c}(3900)$ state within the framework of effective field theory. We firstly show the construction of the Lagrangian describing meson-meson-meson and meson-diquark-diquark interactions. By using the Feynman rule, we calculate the effective potentials corresponding to the coupled channels of $D\bar{D}^{*}/D^{*}\bar{D}$ and $S_{cq}\bar{A}_{cq}/A_{cq}\bar{S}_{cq}$ with $S_{cq}$ ($A_{cq}$) the scalar (axial vector) diquark composed of $c$ and $q$ quarks. After solving the Bethe-Salpeter equation of the on-shell parametrized form and compare our numerical results with the experimental mass and width of $Z_{c}(3900)$, we find that the $Z_{c}(3900)$ state can be explained as the mixture of $D\bar{D}^{*}/D^{*}\bar{D}$ and $S_{cq}\bar{A}_{cq}/A_{cq}\bar{S}_{cq}$ components.

hep-ph↗

arXiv2024

A Model-free Biomimetics Algorithm for Deterministic Partially Observable Markov Decision Process

Partially Observable Markov Decision Process (POMDP) is a mathematical framework for modeling decision-making under uncertainty, where the agent's observations are incomplete and the underlying system dynamics are probabilistic. Solving the POMDP problem within the model-free paradigm is challenging for agents due to the inherent difficulty in accurately identifying and distinguishing between states and observations. We define such a difficult problem as a DETerministic Partially Observable Markov Decision Process (DET-POMDP) problem, which is a specific setting of POMDP. In this problem, states and observations are in a many-to-one relationship. The state is obscured, and its relationship is less apparent to the agent. This creates obstacles for the agent to infer the state through observations. To effectively address this problem, we convert DET-POMDP into a fully observable MDP using a model-free biomimetics algorithm called BIOMAP. BIOMAP is based on the MDP Graph Automaton framework to distinguish authentic environmental information from fraudulent data. Thus, it enhances the agent's ability to develop stable policies against DET-POMDP. The experimental results highlight the superior capabilities of BIOMAP in maintaining operational effectiveness and environmental reparability in the presence of environmental deceptions when compared with existing POMDP solvers. This research opens up new avenues for the deployment of reliable POMDP-based systems in fields that are particularly susceptible to DET-POMDP problems.

eess.SY↗

arXiv2024

MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Understanding documents with rich layouts and multi-modal components is a long-standing and practical task. Recent Large Vision-Language Models (LVLMs) have made remarkable strides in various tasks, particularly in single-page document understanding (DU). However, their abilities on long-context DU remain an open problem. This work presents MMLongBench-Doc, a long-context, multi-modal benchmark comprising 1,062 expert-annotated questions. Distinct from previous datasets, it is constructed upon 130 lengthy PDF-formatted documents with an average of 49.4 pages and 20,971 textual tokens. Towards comprehensive evaluation, answers to these questions rely on pieces of evidence from (1) different sources (text, image, chart, table, and layout structure) and (2) various locations (i.e. page number). Moreover, 33.2% of the questions are cross-page questions requiring evidence across multiple pages. 22.8% of the questions are designed to be unanswerable for detecting potential hallucinations. Experiments on 14 LVLMs demonstrate that long-context DU greatly challenges current models. Notably, the best-performing model, GPT-4o, achieves an F1 score of only 42.7%, while the second-best, GPT-4V, scores 31.4%. Furthermore, 12 LVLMs (all except GPT-4o and GPT-4V) even present worse performance than their LLM counterparts which are fed with lossy-parsed OCR documents. These results validate the necessity of future research toward more capable long-context LVLMs. Project Page: https://mayubo2333.github.io/MMLongBench-Doc

cs.CV↗