Search arXiv⌕ Search

arXiv subjects

Ding Ding

Publications and source records attributed to Ding Ding.

At least 19 recordsLinked to original sources
arXiv2026

Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs

Large Language Models (LLMs) have made remarkable progress on solving competition-level mathematics, yet their ability to verify natural-language mathematical proofs remains relatively underexplored. This gap is especially pronounced for Olympiad-level proofs, which require meticulous assessment of each claim in a long reasoning chain. Current proof verification thus primarily relies on expert inspection, which is costly to scale. In this paper, we present a systematic study of LLM-based verification in this setting. Specifically, we introduce a human-curated dataset of USAMO 2025 candidate solutions with expert grading, and conduct a broad evaluation of existing LLM verifiers across frontier models. We also propose TROJAN, an iterative self-critique pipeline for generating high-fidelity adversarial proofs at scale. Our comprehensive evaluation covers 20 models spanning seven metrics, two prompt styles, three inference methods, and three prompt templates, showing that state-of-the-art models still leave considerable room for improvement. To narrow this gap, we propose MABGrader, a Multi-Armed Bandit framework that reframes grading as arm selection over the discrete score space. MABGrader outperforms the SOTA ProofGrader by 26.4% in Quadratic Weighted Kappa and reduces grading error by 14%. Code and dataset are available at https://github.com/aziksh-ospanov/TROJAN.

cs.AI↗
arXiv2026

ResGVC: Residual Coding for High-fidelity Generative Video Compression

Generative video compression (GVC) methods usually employ decoder-side diffusion models to denoise reconstructed signals based on generative priors. Besides, most of these methods perform denoising in latent space rather than directly in pixel domain. In this paper, we propose ResGVC, a residual coding framework for GVC that guides denoising toward original pictures by transmitting residual signals. ResGVC first encodes the original pictures within a learned video codec, and then decomposes the distortion between the codec reconstruction and the original pictures into a sequence of residual segments, where each residual segment is acquired at each denoising step. Residual segments can further be compressed by a novel residual codec with a diffusion transformer as an entropy model. Unlike prior methods, ResGVC introduces explicit source constraints throughout denoising rather than relying on decoder-side generation alone. The diffusion-based entropy model also enables more effective distribution modeling capability based on the powerful generative priors. Moreover, denoising directly in pixel space avoids the irreversible information loss caused by latent representation bottlenecks. Experimental results show that, compared with the previous state-of-the-art method, ResGVC achieves 63.7% and 83.8% BD-rate reductions in terms of LPIPS and PSNR, respectively, while also delivering superior visual quality.

cs.CV↗
arXiv2026

Less Uniform Discrete Diffusion is More Powerful and Scalable

Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM framework. Specifically, we (i) introduce a less uniform loss that directs each reverse transition toward the clean token, and (ii) equip the model with per-token time embeddings that supply token-level corruption hints, enabling confidence-based few-step sampling. Experiments across scales show that LUDI yields cleaner supervision and improves few-step generation. We further continue-train a 7B autoregressive model into LUDI-7B, resulting in a UDLM capable of complex reasoning. It achieves a 3-token-per-step speedup over AR decoding and competitive performance compared with masked diffusion baselines, revealing that the full potential of UDLMs for complex generation remains to be unlocked.

cs.CL↗
arXiv2026

Dense-Prior-Guided Generative Video Compression

Diffusion-based generative video compression offers a promising paradigm for low-bitrate reconstruction, but existing keyframe-based controllable approaches rely on sparse priors for non-keyframes, which often lack sufficient low-level details for faithful reconstruction and require non-trivial training to adapt generative models to specialized controls. We propose Dense-Prior-Guided Generative Video Compression (DGVC), a training-free framework that uses codec-compressed luminance components of non-keyframes as dense priors to guide reconstruction. Unlike sparse controls, the dense luminance priors are compatible with modern fidelity-oriented video codecs and remain sufficiently faithful after compression, eliminating the need for prior-specific codec training and making additional generative-model adaptation unnecessary in practice. Moreover, luminance priors preserve richer structural and textural information, thereby providing more reliable guidance for controllable video generation. DGVC further introduces a color-distance-guided keyframe selection strategy to capture color variations for chrominance recovery. Extensive experiments show that DGVC consistently surpasses prior controllable compression methods in both signal fidelity and perceptual quality, while remaining competitive with representative post-enhancement approaches.

cs.CV↗
arXiv2026

ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their generative modules are weakly coupled with entropy coding, limiting bitrate reduction. Inspired by the next-scale prediction in the Visual Auto-Regressive (VAR) models, we propose ProGVC, a Progressive-based Generative Video Compression framework that unifies progressive transmission, efficient entropy coding, and detail synthesis within a single codec. ProGVC encodes videos into hierarchical multi-scale residual token maps, enabling flexible rate adaptation by transmitting a coarse-to-fine subset of scales in a progressive manner. A Transformer-based multi-scale autoregressive context model estimates token probabilities, utilized both for efficient entropy coding of the transmitted tokens and for predicting truncated fine-scale tokens at the decoder to restore perceptual details. Extensive experiments demonstrate that as a new coding paradigm, ProGVC delivers promising perceptual compression performance at low bitrates while offering practical scalability at the same time.

cs.CV↗
arXiv2026

Bouncing cosmologies from Born-Infeld-type gravity

We construct a Born-Infeld-type $f(R,{\cal G})$ modification of gravity, where ${\cal G}$ is the Gauss-Bonnet term, by embedding Born-Infeld electrodynamics in a five-dimensional pure modified gravity. This method leads to the correspondence between curvature scalars and electromagnetic field strength scalars -- $R\leftrightarrow F_{μν}F^{μν}$ and ${\cal G}\leftrightarrow (ε_{μνρσ}F^{μν}F^{ρσ})^2$ -- allowing us to replicate the structure of Born-Infeld electrodynamics in the gravitational sector. The resulting Born-Infeld-type gravity is a ghost-free $f(R,{\cal G})$ theory which reduces to Einstein gravity in the low energy limit. In this work we focus on bouncing cosmological solutions of such a theory, which require positive spatial curvature. By using both the Jordan and Einstein frame analyses, we find a vast space of bouncing solutions with different asymptotic behaviors, including solutions with multiple bounces grouped together. Observational consequences of such solutions will be investigated in the future.

gr-qc↗
arXiv2026

Generative Video Compression Based on Hierarchical Referencing

Diffusion-based generative video compression has emerged as a promising paradigm to improve perceptual quality, where latent frames are required to be encoded efficiently while serving as denoising conditions. However, existing methods neither carefully design reference and quality structures during latent coding nor account for the impact of frame-level quality variation on denoising procedure, which limits coding efficiency and aggravates artifact propagation during generative reconstruction. In this paper, we propose GVCHR, Generative Video Compression based on Hierarchical Referencing. The key idea is to organize latent frames hierarchically, where the selected high-quality references benefit both latent coding and generative reconstruction. In latent coding, GVCHR couples a hierarchical reference structure with a hierarchical quality structure, assigning more bits to lower-layer frames that are reused more frequently as references. Built on this design, we introduce Hierarchical Temporal Context Mining to exploits complementary short- and long-term temporal context for effective latent coding. In generative reconstruction, the coding-side hierarchy is incorporated into a Hierarchical Attentive Adapter which is attached to a video diffusion transformer. This adapter uses hierarchical attention to restrict each latent frame to attend only to the same- or lower-layer references, thereby reducing artifact propagation during denoising. Experiments validate GVCHR on multiple benchmarks. Compared with the previous state-of-the-art method, GVCHR achieves 50.5% and 54.0% BD-rate gains in terms of LPIPS and DISTS, respectively, while also delivering clearly improved visual quality.

cs.CV↗
arXiv2026

CellPrism: A Visual Analytics System for Exploring AI-Driven Virtual Cells in Drug Discovery

Gene perturbation analysis plays a critical role in drug discovery by enabling researchers to investigate how interventions on specific genes influence global gene expression patterns within cells. Recent advances in artificial intelligence-driven virtual cell models have made it possible to predict gene expression outcomes for a wide range of perturbation strategies in silico, substantially reducing reliance on costly and time-consuming biological experiments. However, effectively exploring and interpreting the high-dimensional perturbation spaces produced by these models remains challenging because of the combinatorial nature of perturbations and the complex cell-specific gene expression responses they generate. In this work, we present CellPrism, a visual analytics system designed to support the systematic exploration of gene perturbation strategies for drug discovery. Specifically, CellPrism integrates clustering-based overviews to summarize perturbation outcomes, a glyph-based representation to compactly encode gene expression patterns across cell types, and coordinated views that enable fine-grained comparison and interpretation of perturbation effects. We demonstrate the effectiveness of CellPrism through a real-world case study and expert interviews. This work highlights the value of visual analytics in bridging virtual cell modeling with expert-driven decision making in drug discovery.

cs.HC↗
arXiv2026

QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration

All-in-one image restoration aims to recover clean images degraded by multiple corruption types using a single unified model. Existing methods typically rely on image-level prompts or shared guidance to handle diverse degradations. However, such a paradigm becomes inadequate when degradations are spatially heterogeneous or even coexist in mixed forms within a single image. Yet spatially adaptive guidance alone is not sufficient, since accurate restoration also requires each spatial query to reliably aggregate complementary information from local neighborhoods and global contexts. To this end, we propose QuReC, a unified framework for all-in-one image restoration. QuReC consists of a Degradation-Guided Query Reconstruction Module (DQRM) and a Local-Global Response Calibration Module (LGRCM). Specifically, DQRM matches each spatial query against a degradation prototype space to reconstruct a query-specific degradation-aware representation, thereby providing fine-grained spatially adaptive restoration guidance. To further stabilize this query-wise matching process, we introduce a weakly supervised prototype matching learning strategy to improve optimization stability and degradation semantic consistency. Meanwhile, LGRCM performs local-global dual-branch aggregation and calibrates the aggregated responses with learnable priors, improving the reliability of feature aggregation and the coordination between local detail modeling and global context modeling. Extensive experiments demonstrate that QuReC achieves superior performance on multiple all-in-one image restoration benchmarks. The code is released at https://github.com/zhoushen1/QuReC.

cs.CV↗
arXiv2026

Towards Stochastic Inflation in Higher-Curvature Gravity

We study stochastic inflation in the presence of higher-curvature terms non-minimally coupled to the inflaton. Focusing on quadratic curvature invariants, we single out the Gauss-Bonnet term which is known to avoid ghosts, while having non-trivial effects on the background and scalar mode evolution when coupled to the scalar field. Stochastic Klein-Gordon and Langevin equations are derived in the presence of the Gauss-Bonnet coupling, and their slow-roll and ultra-slow-roll limits are studied. By using first-passage time method, scalar power spectrum and PBH mass fraction are estimated in these limits. Stochastic evolution of a Gauss-Bonnet-coupled spectator field in de Sitter vacuum is also discussed.

gr-qc↗
arXiv2026

Beyond Compliance: A Resistance-Informed Motivation Reasoning Framework for Challenging Psychological Client Simulation

Psychological client simulators have emerged as a scalable solution for training and evaluating counselor trainees and psychological LLMs. Yet existing simulators exhibit unrealistic over-compliance, leaving counselors underprepared for the challenging behaviors common in real-world practice. To bridge this gap, we present ResistClient, which systematically models challenging client behaviors grounded in Client Resistance Theory by integrating external behaviors with underlying motivational mechanisms. To this end, we propose Resistance-Informed Motivation Reasoning (RIMR), a two-stage training framework. First, RIMR mitigates compliance bias via supervised fine-tuning on RPC, a large-scale resistance-oriented psychological conversation dataset covering diverse client profiles. Second, beyond surface-level response imitation, RIMR models psychologically coherent motivation reasoning before response generation, jointly optimizing motivation authenticity and response consistency via process-supervised reinforcement learning. Extensive automatic and expert evaluations show that ResistClient substantially outperforms existing simulators in challenge fidelity, behavioral plausibility, and reasoning coherence. Moreover, ResistClient facilities evaluation of psychological LLMs under challenging conditions, offering new optimization directions for mental health dialogue systems.

cs.AI↗
arXiv2026

Reinforcement Learning-Guided NSGA-II Enhanced with Gray Relational Coefficient for Multi-Objective Optimization: Application to NASDAQ Portfolio Optimization

In modern financial markets, decision-makers increasingly rely on quantitative methods to navigate complex trade-offs among multiple, often conflicting objectives. This paper addresses constrained multi-objective optimization (MOO) with an application to portfolio optimization for minimizing risk and maximizing return. To address existing gaps, we propose a novel reinforcement learning (RL)-guided non-dominated sorting genetic algorithm II (NSGA-II) enhanced with gray relational coefficients (GRC), termed RL-NSGA-II-GRC, which combines an RL agent controller and GRC-based selection to improve convergence and diversity of Pareto fronts. The agent adapts evolutionary parameters online using metrics of hypervolume, feasibility, and diversity, while the GRC tournament operator ranks parents via a unified score considering dominance rank, crowding distance, and proximity to ideal reference. We evaluate the framework on the Kursawe and CONSTR benchmarks and a NASDAQ portfolio application. On the benchmarks, RL-NSGA-II-GRC achieves convergence improvements of about 5.8% and 4.4% over NSGA-II, while preserving well-distributed non-dominated solutions. In the portfolio application, it produces a smooth, densely populated efficient frontier supporting identification of the maximum Sharpe ratio portfolio (annualized Sharpe =1.92) and utility-optimal portfolios for different risk-aversion levels. The main contributions are three-fold: 1) we propose an RL-NSGA-II-GRC method integrating an RL agent into the evolutionary framework to adaptively control parameters via generational feedback; 2) we design a GRC-enhanced binary tournament operator providing a comprehensive indicator to guide the search toward the Pareto front; 3) we demonstrate, on benchmark MOO and a NASDAQ case study, that the method delivers improved convergence and well-populated frontiers supporting actionable insights.

cs.LG↗
arXiv2026

Stabilizing Reinforcement Learning for Diffusion Language Models

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two sources of incompatibility. First, GRPO relies on importance ratios defined by sequence probabilities, which are intractable in dLLMs and must be estimated (e.g., via ELBO-based or mean-field likelihood proxies), yielding inherently noisy ratios. Second, standard GRPO's formulation is not designed for estimated ratios: its conditional clipping can be anomalously bypassed by model-agnostic estimation noise, producing gradient spikes, while its fixed group-size normalization amplifies gradient-magnitude fluctuations under high-variance ratio estimates. We show these effects form a self-reinforcing instability loop that drives policy drift and further increases ratio variance. To break this loop, we propose StableDRL, a reformulation of GRPO tailored for dLLMs that uses (i) unconditional clipping to suppress outlier-induced spikes and (ii) self-normalization to constrain updates within the convex hull of per-sample gradients. We further extend StableDRL to block-wise diffusion models via a staircase attention mechanism.

cs.LG↗
arXiv2026

Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes

While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this paper, we propose Deletion-Insertion Diffusion language models (DID) that rigorously formulate token deletion and insertion as discrete diffusion processes, replacing the masking and unmasking processes in current MDLMs. DID improves training and inference efficiency by eliminating two major sources of computational overhead in MDLMs: the computations on non-informative 1) tokens inherent to the paradigm, and 2) tokens introduced in variable-length settings. Furthermore, DID offers greater flexibility by: 1) natively supporting variable-length sequences without requiring fixed-length padding, and 2) an intrinsic self-correction mechanism during generation due to insertion that dynamically adjusts token positions. To train DID, we design a score-based approach that assigns scores to token insertion operations and derive appropriate training objectives. The objectives involve subsequence counting problems, which we efficiently solve via a parallelized dynamic programming algorithm. Our experiments across fixed and variable-length settings demonstrate the advantage of DID over baselines of MDLMs and existing insertion-based LMs, in terms of modeling performance, sampling quality, and training/inference speed, without any hyperparameter tuning.

cs.CL↗
arXiv2026

Subjective-Objective Median-based Importance Technique (SOMIT) to Aid Multi-Criteria Renewable Energy Evaluation

Accelerating the renewable energy transition requires informed decision-making that accounts for the diverse financial, technical, environmental, and social trade-offs across different renewable energy technologies. A critical step in this multi-criteria decision-making (MCDM) process is the determination of appropriate criteria weights. However, deriving these weights often solely involves either subjective assessment from decision-makers or objective weighting methods, each of which has limitations in terms of cognitive burden, potential bias, and insufficient contextual relevance. This study proposes the subjective-objective median-based importance technique (SOMIT), a novel hybrid approach for determining criteria weights in MCDM. By tailoring SOMIT to renewable energy evaluation, the method directly supports applied energy system planning, policy analysis, and technology prioritization under carbon neutrality goals. The practical utility of SOMIT is demonstrated through two MCDM case studies on renewable energy decision-making in India and Saudi Arabia. Using the derived weights from SOMIT, the TOPSIS method ranks the renewable energy alternatives, with solar power achieving the highest performance scores in both cases. The main contributions of this work are five-fold: 1) the proposed SOMIT reduces the number of required subjective comparisons from the conventional quadratic order to a linear order; 2) SOMIT is more robust to outliers in the alternatives-criteria matrix (ACM); 3) SOMIT balances subjective expert knowledge with objective data-driven insights, thereby mitigating bias; 4) SOMIT is inherently modular, allowing both its individual parts and the complete approach to be seamlessly coupled with a wide range of MCDM methods commonly applied in energy systems and policy analysis; 5) a dedicated Python library, pysomit, is developed for SOMIT.

math.OC↗
arXiv2025

Aqueous Preparation of CsPbBr3 Perovskite Nanocrystals Under Ambient Conditio

Metal halide perovskites (MHPs) have had a profound impact on numerous emerging optoelectronic technologies, achieving performance metrics that rival or exceed incumbent materials. This impact is underpinned by the exceptional properties of MHPs, including tuneable band gaps, high absorption coefficients, long carrier diffusion lengths and combined with uncomplicated synthesis methods. However, current MHP production relies on the toxic solvents, which pose significant environmental and health risks. Moreover, these methods often require complex multi component solvent systems and thermal processing to achieve the desired material phases, further hindering scalability and sustainability. Overcoming these challenges is critical to the future development of MHP-based technologies. Overcoming these challenges is critical to the future development of MHP-based technologies. Here, we present a novel water-based solvent system and synthetic approach for the preparation of size-controlled CsPbBr3 perovskite nanocrystals in ambient air and at room temperature. The photoluminescence quantum yield (PLQY) of CsPbBr3 erovskite nanocrystals (PNCs) exceeds 60 precent. To demonstrate the light to current conversion ability of our PNCs a series of photoconductors were prepared, with the best performing devices achieving a specific detectivity (D*) of 1.2 x 10^11 Jones. Thus, this green, scalable, and low-cost approach offers a sustainable pathway for precise size and compositional control of MHP nanocrystals, opening new possibilities for environmentally friendly optoelectronic applications.

cond-mat.mtrl-sci↗
arXiv2025

Mixup Helps Understanding Multimodal Video Better

Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, multimodal models are prone to overfitting strong modalities, which can dominate learning and suppress the contributions of weaker ones. To address this challenge, we first propose Multimodal Mixup (MM), which applies the Mixup strategy at the aggregated multimodal feature level to mitigate overfitting by generating virtual feature-label pairs. While MM effectively improves generalization, it treats all modalities uniformly and does not account for modality imbalance during training. Building on MM, we further introduce Balanced Multimodal Mixup (B-MM), which dynamically adjusts the mixing ratios for each modality based on their relative contributions to the learning objective. Extensive experiments on several datasets demonstrate the effectiveness of our methods in improving generalization and multimodal robustness.

cs.CV↗
arXiv2025

Verify Distributed Deep Learning Model Implementation Refinement with Iterative Relation Inference

Distributed machine learning training and inference is common today because today's large models require more memory and compute than can be provided by a single GPU. Distributed models are generally produced by programmers who take a sequential model specification and apply several distribution strategies to distribute state and computation across GPUs. Unfortunately, bugs can be introduced in the process, and a distributed model implementation's outputs might differ from the sequential model's outputs. In this paper, we describe an approach to statically identify such bugs by checking model refinement, that is, can the sequential model's outputs be reconstructed from the distributed model's outputs? Our approach, implemented in GraphGuard, uses iterative rewriting to prove model refinement. Our approach can scale to today's large models and deployments: we evaluate it using GPT and Llama-3. Further, it provides actionable output that aids in bug localization.

cs.DC↗