arXiv subjects

Di Zhang

Publications and source records attributed to Di Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2025

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Understanding and predicting emotion from videos has gathered significant attention in recent studies, driven by advancements in video large language models (VideoLLMs). While advanced methods have made progress in video emotion analysis, the intrinsic nature of emotions poses significant challenges. Emotions are characterized by dynamic and cues-dependent properties, making it difficult to understand complex and evolving emotional states with reasonable rationale. To tackle these challenges, we propose a novel affective cues-guided reasoning framework that unifies fundamental attribute perception, expression analysis, and high-level emotional understanding in a stage-wise manner. At the core of our approach is a family of video emotion foundation models (VidEmo), specifically designed for emotion reasoning and instruction-following. These models undergo a two-stage tuning process: first, curriculum emotion learning for injecting emotion knowledge, followed by affective-tree reinforcement learning for emotion reasoning. Moreover, we establish a foundational data infrastructure and introduce a emotion-centric fine-grained dataset (Emo-CFG) consisting of 2.1M diverse instruction-based samples. Emo-CFG includes explainable emotional question-answering, fine-grained captions, and associated rationales, providing essential resources for advancing emotion understanding tasks. Experimental results demonstrate that our approach achieves competitive performance, setting a new milestone across 15 face perception tasks.

cs.CV↗

arXiv2025

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious visual or factual evidence. Currently, training-based solutions, like direct preference optimization (DPO), leverage paired preference data to suppress hallucinations. However, they risk sacrificing general reasoning capabilities due to the likelihood displacement. Meanwhile, training-free solutions, like contrastive decoding, achieve this goal by subtracting the estimated hallucination pattern from a distorted input. Yet, these handcrafted perturbations (e.g., add noise to images) may poorly capture authentic hallucination patterns. To avoid these weaknesses of existing methods, and realize robust hallucination mitigation (i.e., maintaining general reasoning performance), we propose a novel framework: Decoupling Contrastive Decoding (DCD). Specifically, DCD decouples the learning of positive and negative samples in preference datasets, and trains separate positive and negative image projections within the MLLM. The negative projection implicitly models real hallucination patterns, which enables vision-aware negative images in the contrastive decoding inference stage. Our DCD alleviates likelihood displacement by avoiding pairwise optimization and generalizes robustly without handcrafted degradation. Extensive ablations across hallucination benchmarks and general reasoning tasks demonstrate the effectiveness of DCD, i.e., it matches DPO's hallucination suppression while preserving general capabilities and outperforms the handcrafted contrastive decoding methods.

cs.LG↗

arXiv2025

GameFactory: Creating New Games with Generative Interactive Videos

Generative videos have the potential to revolutionize game development by autonomously creating new content. In this paper, we present GameFactory, a framework for action-controlled scene-generalizable game video generation. We first address the fundamental challenge of action controllability by introducing GF-Minecraft, an action-annotated game video dataset without human bias, and developing an action control module that enables precise control over both keyboard and mouse inputs. We further extend to support autoregressive generation for unlimited-length interactive videos. More importantly, GameFactory tackles the critical challenge of scene-generalizable action control, which most existing methods fail to address. To enable the creation of entirely new and diverse games beyond fixed styles and scenes, we leverage the open-domain generative priors from pre-trained video diffusion models. To bridge the domain gap between open-domain priors and small-scale game datasets, we propose a multi-phase training strategy with a domain adapter that decouples game style learning from action control. This decoupling ensures that action control learning is no longer bound to specific game styles, thereby achieving scene-generalizable action control. Experimental results demonstrate that GameFactory effectively generates open-domain action-controllable game videos, representing a significant step forward in AI-driven game generation.

cs.CV↗

arXiv2025

Learning Geometry: A Framework for Building Adaptive Manifold Models through Metric Optimization

This paper proposes a novel paradigm for machine learning that moves beyond traditional parameter optimization. Unlike conventional approaches that search for optimal parameters within a fixed geometric space, our core idea is to treat the model itself as a malleable geometric entity. Specifically, we optimize the metric tensor field on a manifold with a predefined topology, thereby dynamically shaping the geometric structure of the model space. To achieve this, we construct a variational framework whose loss function carefully balances data fidelity against the intrinsic geometric complexity of the manifold. The former ensures the model effectively explains observed data, while the latter acts as a regularizer, penalizing overly curved or irregular geometries to encourage simpler models and prevent overfitting. To address the computational challenges of this infinite-dimensional optimization problem, we introduce a practical method based on discrete differential geometry: the continuous manifold is discretized into a triangular mesh, and the metric tensor is parameterized by edge lengths, enabling efficient optimization using automatic differentiation tools. Theoretical analysis reveals a profound analogy between our framework and the Einstein-Hilbert action in general relativity, providing an elegant physical interpretation for the concept of "data-driven geometry". We further argue that even with fixed topology, metric optimization offers significantly greater expressive power than models with fixed geometry. This work lays a solid foundation for constructing fully dynamic "meta-learners" capable of autonomously evolving their geometry and topology, and it points to broad application prospects in areas such as scientific model discovery and robust representation learning.

cs.LG↗

arXiv2025

The Singularity Theory of Concurrent Programs: A Topological Characterization and Detection of Deadlocks and Livelocks

This paper introduces a novel paradigm for the analysis and verification of concurrent programs -- the Singularity Theory. We model the execution space of a concurrent program as a branched topological space, where program states are points and state transitions are paths. Within this framework, we characterize deadlocks as attractors and livelocks as non-contractible loops in the execution space. By employing tools from algebraic topology, particularly homotopy and homology groups, we define a series of concurrent topological invariants to systematically detect and classify these concurrent "singularities" without exhaustively traversing all states. This work aims to establish a geometric and topological foundation for concurrent program verification, transcending the limitations of traditional model checking.

cs.PL↗

arXiv2025

The Neural Differential Manifold: An Architecture with Explicit Geometric Structure

This paper introduces the Neural Differential Manifold (NDM), a novel neural network architecture that explicitly incorporates geometric structure into its fundamental design. Departing from conventional Euclidean parameter spaces, the NDM re-conceptualizes a neural network as a differentiable manifold where each layer functions as a local coordinate chart, and the network parameters directly parameterize a Riemannian metric tensor at every point. The architecture is organized into three synergistic layers: a Coordinate Layer implementing smooth chart transitions via invertible transformations inspired by normalizing flows, a Geometric Layer that dynamically generates the manifold's metric through auxiliary sub-networks, and an Evolution Layer that optimizes both task performance and geometric simplicity through a dual-objective loss function. This geometric regularization penalizes excessive curvature and volume distortion, providing intrinsic regularization that enhances generalization and robustness. The framework enables natural gradient descent optimization aligned with the learned manifold geometry and offers unprecedented interpretability by endowing internal representations with clear geometric meaning. We analyze the theoretical advantages of this approach, including its potential for more efficient optimization, enhanced continual learning, and applications in scientific discovery and controllable generative modeling. While significant computational challenges remain, the Neural Differential Manifold represents a fundamental shift towards geometrically structured, interpretable, and efficient deep learning systems.

cs.LG↗

arXiv2025

Improving Video Generation with Human Feedback

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human feedback to mitigate these problems and refine the video generation model. Specifically, we begin by constructing a large-scale human preference dataset focused on modern video generation models, incorporating pairwise annotations across multi-dimensions. We then introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy. From a unified reinforcement learning perspective aimed at maximizing reward with KL regularization, we introduce three alignment algorithms for flow-based models. These include two training-time strategies: direct preference optimization for flow (Flow-DPO) and reward weighted regression for flow (Flow-RWR), and an inference-time technique, Flow-NRG, which applies reward guidance directly to noisy videos. Experimental results indicate that VideoReward significantly outperforms existing reward models, and Flow-DPO demonstrates superior performance compared to both Flow-RWR and supervised fine-tuning methods. Additionally, Flow-NRG lets users assign custom weights to multiple objectives during inference, meeting personalized video quality needs.

cs.CV↗

arXiv2025

Flow-GRPO: Training Flow Matching Models via Online RL

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation (ODE) into an equivalent Stochastic Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps, enabling statistical sampling for RL exploration; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps, significantly improving sampling efficiency without sacrificing performance. Empirically, Flow-GRPO is effective across multiple text-to-image tasks. For compositional generation, RL-tuned SD3.5-M generates nearly perfect object counts, spatial relations, and fine-grained attributes, increasing GenEval accuracy from $63\%$ to $95\%$. In visual text rendering, accuracy improves from $59\%$ to $92\%$, greatly enhancing text generation. Flow-GRPO also achieves substantial gains in human preference alignment. Notably, very little reward hacking occurred, meaning rewards did not increase at the cost of appreciable image quality or diversity degradation.

cs.CV↗

arXiv2025

ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area

Large Language Models (LLMs) have achieved remarkable success and have been applied across various scientific fields, including chemistry. However, many chemical tasks require the processing of visual information, which cannot be successfully handled by existing chemical LLMs. This brings a growing need for models capable of integrating multimodal information in the chemical domain. In this paper, we introduce \textbf{ChemVLM}, an open-source chemical multimodal large language model specifically designed for chemical applications. ChemVLM is trained on a carefully curated bilingual multimodal dataset that enhances its ability to understand both textual and visual chemical information, including molecular structures, reactions, and chemistry examination questions. We develop three datasets for comprehensive evaluation, tailored to Chemical Optical Character Recognition (OCR), Multimodal Chemical Reasoning (MMCR), and Multimodal Molecule Understanding tasks. We benchmark ChemVLM against a range of open-source and proprietary multimodal large language models on various tasks. Experimental results demonstrate that ChemVLM achieves competitive performance across all evaluated tasks. Our model can be found at https://huggingface.co/AI4Chem/ChemVLM-26B.

cs.LG↗

arXiv2025

Physically Interpretable Descriptors Drive the Materials Design of Metal Hydrides for Hydrogen Storage

Designing metal hydrides for hydrogen storage remains a longstanding challenge due to the vast compositional space and complex structure-property relationships. Herein, for the first time, we present physically interpretable models for predicting two key performance metrics, gravimetric hydrogen density $w$ and equilibrium pressure $P_{\rm eq,RT}$ at room temperature, based on a minimal set of chemically meaningful descriptors. Using a rigorously curated dataset of $5,089$ metal hydride compositions from our recently developed Digital Hydrogen Platform (\it{DigHyd}) based on large-scale data mining from available experimental literature of solid-state hydrogen storage materials, we systematically constructed over $1.6$ million candidate models using combinations of scalar transformations and nonlinear link functions. The final closed-form models, derived from $2$-$3$ descriptors each, achieve predictive accuracies on par with state-of-the-art machine learning methods, while maintaining full physical transparency. Strikingly, descriptor-based design maps generated from these models reveal a fundamental trade-off between $w$ and $P_{\rm eq,RT}$: saline-type hydrides, composed of light electropositive elements, offer high $w$ but low $P_{\rm eq,RT}$, whereas interstitial-type hydrides based on heavier electronegative transition metals show the opposite trend. Notably, Be-based systems, such as Be-Na alloys, emerge as rare candidates that simultaneously satisfy both performance metrics, attributed to the unique combination of light mass and high molar density for Be. Our models indicate that Be-based systems may offer renewed prospects for approaching these benchmarks. These results provide chemically intuitive guidelines for materials design and establish a scalable framework for the rational discovery of materials in complex chemical spaces.

cond-mat.mtrl-sci↗

arXiv2025

MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Hypothesis ranking is vital for automated scientific discovery, especially in cost-intensive, throughput-limited natural science domains. Current methods focus on pre-experiment ranking, relying solely on language model reasoning without empirical feedback. We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests. Due to the impracticality of real experiments, we propose a simulator grounded in domain-specific concepts that models hypothesis performance as a function of similarity to a hidden ground truth, perturbed by noise. Validated against 124 hypotheses with experimentally reported outcomes, the simulator approximates real results with consistent trend alignment. Although deviations exist, they mimic wet-lab noise, promoting more robust ranking strategies. We frame experiment-guided ranking as a sequential decision-making problem and propose an in-context reinforcement learning (ICRL) framework. Our LLM-based policy decomposes hypotheses into functional elements, clusters them by mechanistic roles, and prioritizes recombinations based on feedback. Experiments show our approach significantly outperforms pre-experiment baselines and strong ablations. Our toolkit, comprising the simulator and ICRL framework, enables systematic research on experiment-guided ranking, with the policy serving as a strong proof of concept.

cs.CL↗

arXiv2025

Chem-R: Learning to Reason as a Chemist

Although large language models (LLMs) have significant potential to advance chemical discovery, current LLMs lack core chemical knowledge, produce unreliable reasoning trajectories, and exhibit suboptimal performance across diverse chemical tasks. To address these challenges, we propose Chem-R, a generalizable Chemical Reasoning model designed to emulate the deliberative processes of chemists. Chem-R is trained through a three-phase framework that progressively builds advanced reasoning capabilities, including: 1) Chemical Foundation Training, which establishes core chemical knowledge. 2) Chemical Reasoning Protocol Distillation, incorporating structured, expert-like reasoning traces to guide systematic and reliable problem solving. 3) Multi-task Group Relative Policy Optimization that optimizes the model for balanced performance across diverse molecular- and reaction-level tasks. This structured pipeline enables Chem-R to achieve state-of-the-art performance on comprehensive benchmarks, surpassing leading large language models, including Gemini-2.5-Pro and DeepSeek-R1, by up to 32% on molecular tasks and 48% on reaction tasks. Meanwhile, Chem-R also consistently outperforms the existing chemical foundation models across both molecular and reaction level tasks. These results highlight Chem-R's robust generalization, interpretability, and potential as a foundation for next-generation AI-driven chemical discovery. The code and model are available at https://github.com/davidweidawang/Chem-R.

cs.CE↗

arXiv2025

Communication-Efficient and Memory-Aware Parallel Bootstrapping using MPI

Bootstrapping is a powerful statistical resampling technique for estimating the sampling distribution of an estimator. However, its computational cost becomes prohibitive for large datasets or a high number of resamples. This paper presents a theoretical analysis and design of parallel bootstrapping algorithms using the Message Passing Interface (MPI). We address two key challenges: high communication overhead and memory constraints in distributed environments. We propose two novel strategies: 1) Local Statistic Aggregation, which drastically reduces communication by transmitting sufficient statistics instead of full resampled datasets, and 2) Synchronized Pseudo-Random Number Generation, which enables distributed resampling when the entire dataset cannot be stored on a single process. We develop analytical models for communication and computation complexity, comparing our methods against naive baseline approaches. Our analysis demonstrates that the proposed methods offer significant reductions in communication volume and memory usage, facilitating scalable parallel bootstrapping on large-scale systems.

cs.DC↗

arXiv2025

Efficient Triangular Arbitrage Detection via Graph Neural Networks

Triangular arbitrage is a profitable trading strategy in financial markets that exploits discrepancies in currency exchange rates. Traditional methods for detecting triangular arbitrage opportunities, such as exhaustive search algorithms and linear programming solvers, often suffer from high computational complexity and may miss potential opportunities in dynamic markets. In this paper, we propose a novel approach to triangular arbitrage detection using Graph Neural Networks (GNNs). By representing the currency exchange network as a graph, we leverage the powerful representation and learning capabilities of GNNs to identify profitable arbitrage opportunities more efficiently. Specifically, we formulate the triangular arbitrage problem as a graph-based optimization task and design a GNN architecture that captures the complex relationships between currencies and exchange rates. We introduce a relaxed loss function to enable more flexible learning and integrate Deep Q-Learning principles to optimize the expected returns. Our experiments on a synthetic dataset demonstrate that the proposed GNN-based method achieves a higher average yield with significantly reduced computational time compared to traditional methods. This work highlights the potential of using GNNs for solving optimization problems in finance and provides a promising approach for real-time arbitrage detection in dynamic financial markets.

q-fin.TR↗

arXiv2025

On the Optimal Representation Efficiency of Barlow Twins: An Information-Geometric Interpretation

Self-supervised learning (SSL) has achieved remarkable success by learning meaningful representations without labeled data. However, a unified theoretical framework for understanding and comparing the efficiency of different SSL paradigms remains elusive. In this paper, we introduce a novel information-geometric framework to quantify representation efficiency. We define representation efficiency $η$ as the ratio between the effective intrinsic dimension of the learned representation space and its ambient dimension, where the effective dimension is derived from the spectral properties of the Fisher Information Matrix (FIM) on the statistical manifold induced by the encoder. Within this framework, we present a theoretical analysis of the Barlow Twins method. Under specific but natural assumptions, we prove that Barlow Twins achieves optimal representation efficiency ($η= 1$) by driving the cross-correlation matrix of representations towards the identity matrix, which in turn induces an isotropic FIM. This work provides a rigorous theoretical foundation for understanding the effectiveness of Barlow Twins and offers a new geometric perspective for analyzing SSL algorithms.

cs.LG↗

arXiv2025

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions. In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: Reasoning Misalignment -- the divergence between an LLM's internal reasoning trajectory and the evidential constraints provided by retrieval. To address this issue, we propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA). We further introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations. At the heart of AlignRAG lies a contrastive critique synthesis mechanism that generates retrieval-sensitive critiques while mitigating self-bias. This mechanism trains a dedicated retrieval-augmented Critic Language Model (CLM) using labeled critiques that distinguish between evidence-aligned and misaligned reasoning. Empirical evaluations show that our approach significantly improves reasoning fidelity. Our 8B-parameter CLM improves performance over the Self-Refine baseline by 12.1% on out-of-domain tasks and outperforms a standard 72B-parameter CLM by 2.2%. Furthermore, AlignRAG-auto achieves this state-of-the-art performance while dynamically determining the optimal number of refinement steps, enhancing efficiency and usability. AlignRAG remains compatible with existing RAG architectures as a plug-and-play module and demonstrates strong robustness under both informative and noisy retrieval scenarios.

cs.AI↗

arXiv2025

A Frequency-Domain Analysis of the Multi-Armed Bandit Problem: A New Perspective on the Exploration-Exploitation Trade-off

The stochastic multi-armed bandit (MAB) problem is one of the most fundamental models in sequential decision-making, with the core challenge being the trade-off between exploration and exploitation. Although algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling, along with their regret theories, are well-established, existing analyses primarily operate from a time-domain and cumulative regret perspective, struggling to characterize the dynamic nature of the learning process. This paper proposes a novel frequency-domain analysis framework, reformulating the bandit process as a signal processing problem. Within this framework, the reward estimate of each arm is viewed as a spectral component, with its uncertainty corresponding to the component's frequency, and the bandit algorithm is interpreted as an adaptive filter. We construct a formal Frequency-Domain Bandit Model and prove the main theorem: the confidence bound term in the UCB algorithm is equivalent in the frequency domain to a time-varying gain applied to uncertain spectral components, a gain inversely proportional to the square root of the visit count. Based on this, we further derive finite-time dynamic bounds concerning the exploration rate decay. This theory not only provides a novel and intuitive physical interpretation for classical algorithms but also lays a rigorous theoretical foundation for designing next-generation algorithms with adaptive parameter adjustment.

cs.LG↗

arXiv2025

PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multi-Layer Perceptrons (MLPs), offering enhanced interpretability and a solid mathematical foundation. However, their parameter efficiency remains a significant challenge for practical deployment. This paper introduces PolyKAN, a novel theoretical framework for KAN compression that provides formal guarantees on both model size reduction and approximation error. By leveraging the inherent piecewise polynomial structure of KANs, we formulate the compression problem as a polyhedral region merging task. We establish a rigorous polyhedral characterization of KANs, develop a complete theory of $ε$-equivalent compression, and design a dynamic programming algorithm that achieves approximately optimal compression under specified error bounds. Our theoretical analysis demonstrates that PolyKAN achieves provably near-optimal compression while maintaining strict error control, with guaranteed global optimality for univariate spline functions. This framework provides the first formal foundation for KAN compression with mathematical guarantees, opening new directions for the efficient deployment of interpretable neural architectures.

cs.LG↗