Searcharxiv⌕ Search

arXiv subjects

Cheng Chen

Publications and source records attributed to Cheng Chen.

At least 19 recordsLinked to original sources
arXiv2026

Unlocking the Potential of Contrastive Regularization for Diffusion Transformer Training

Representation regularization has emerged as an effective way to improve diffusion transformer training. Yet one of the most canonical regularizers--InfoNCE-style contrastive learning--remains largely underexplored in this setting. We naturally ask a question: can standard contrastive learning serve as an effective regularizer for diffusion transformers? Surprisingly, we find that naive InfoNCE regularization brings only marginal gains. Our analysis reveals that the objective is easily dominated by a shortcut: near-orthogonal noise components in diffusion inputs provide a bypass for enlarging negative-pair distances while weakening positive-pair alignment, especially at high noise levels. To unlock the benefit of contrastive regularization, we propose Clean Representation-ANchored Contrastive (CRAN) regularization. Specifically, CRAN anchors contrastive dispersion with clean-sample representation distances, transferring clean relational semantic structure to noisy diffusion representations to suppress the noise shortcut. Extensive experiments on ImageNet show that CRAN consistently improves diffusion transformer training across model scales and training budgets, outperforming internal feature-alignment and dispersive regularization baselines while matching external DINO-guided REPA. These results re-establish InfoNCE-based contrastive learning as an effective regularizer for diffusion training, once its noise-driven over-dispersion is properly constrained.

cs.CV↗
arXiv2026

RouteREPA: Routed Representation Alignment for Just Image Transformers

Representation alignment (REPA) is widely used to accelerate the training of latent-space diffusion transformers (DiTs). However, applying it to pixel-space models such as Just Image Transformers (JiT) is challenging. Our analysis reveals a pronounced representation conflict between discriminative alignment and pixel-space generation. Compared with its latent counterpart, JiT learns representations that are substantially less aligned with DINOv2. Applying REPA to JiT consistently reduces the reconstructability of its intermediate representations, whereas this effect is not observed in Latent JiT. We attribute this conflict to JiT directly reconstructing pixels, which requires its representations to hierarchically encode discriminative semantics and reconstruction-relevant visual information across network depths. To address these challenges, we propose Routed Representation Alignment (RouteREPA), which uses lightweight, representation-dependent routers to adaptively route task-oriented representations for alignment and generation. We further apply routing across multiple network depths to accommodate their depth-dependent representation requirements. Extensive experiments on ImageNet-1K at 256x256 resolution show that RouteREPA consistently improves JiT across model scales and training budgets, outperforming standard REPA. On JiT-H/16, RouteREPA further surpasses PixelREPA using only one-third of its training epochs without classifier-free guidance.

cs.CV↗
arXiv2026

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

cs.CL↗
arXiv2026

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, including the limited number of data samples, fine-grained text descriptions, and detailed visual attributes. To address these limitations, we introduce a large-scale, video-text dataset featuring rich, in-the-wild visual attributes tailored for complex marine environments. Our dataset comprises 2,000 video-text pairs annotated with 13 attributes covering up to four objects per scene, object visual/geometric properties, behaviors, environmental context, and camera motion, spanning diverse lighting conditions, times of day, and 7 countries. From these annotations, we generate 16,080 video-question pairs (12,080 multiple-choice, 4,000 open-ended). Furthermore, we benchmark both proprietary and open-source video-LLM models on video question answering and video captioning tasks. We find that (i) proprietary models often achieves superior performances; (ii) VLMs handle object motion well but struggle with complex camera motion; (iii) closed-source models struggle to perceive camera motion; and (iv) VLMs struggle to reason in static cameras.

cs.CV↗
arXiv2026

Electromagnetic form factors of singly charmed baryons $Σ_c$ and $Λ_c$ in a covariant quark-diquark model

We present a systematic study of the spacelike electromagnetic form factors of the ground-state singly charmed baryons, $Σ_c$ ($Σ_c^{++},Σ_c^+,Σ_c^0$) and $Λ_c^+$, within a covariant quark-diquark model. Based on this framework, we obtain their magnetic moments as well as electric charge and magnetic moment radii. Such observables are important to understand the internal structure and the inner dynamics of these heavy baryon states. Our theoretical calculations are in qualitative agreement with available lattice QCD results of $Σ_c^{++}$ and $Σ_c^0$ baryons. We also discuss the mechanism behind the dependence of the numerical results on the charm quark and light diquark. A key finding is that the electric form factors of the singly charmed baryons fall off much more slowly with momentum transfer $Q^2$ than that of the proton, indicating a more compact electric charge distribution, which is attributed to the heavy charm quark acting as a localized core. More importantly, we observe a striking difference in the magnetic structure: while the magnetic form factors of $Σ_c$ are dominated by the light axial-vector diquark, those of $Λ_c^+$ are unexpectedly governed by the charm quark due to the vanishing contribution of the scalar diquark. This highlights the decisive role of the light-diquark spin configuration in determining the magnetic properties. Finally, using an empirical asymptotic relation connecting the spacelike and timelike regions, we predict the total cross section for $e^+e^-\toΣ_c\barΣ_c$. Our findings can be tested at existing facilities including the BESIII, Belle II and LHCb, as well as the proposed Super Tau-Charm Facility.

hep-ph↗
arXiv2026

Reggeized $K^*(892)$ exchange in $π^- p \to K^0 Λ$ and implications for fixed-target measurements

The two-body $π^- p \to K^0 Λ$ reaction provides a clean channel for studying strangeness production and producing tagged hyperon $Λ$ samples. We describe its total cross section over the $π^-$ beam momentum $2.6 \leq p_{π, {\rm lab}} \leq 6.0~{\rm GeV}/c$ using a single Reggeized $t$-channel $K^*(892)$ exchange without polarization. We also examine the implications for future fixed-target measurements. An idealized event sample is used to determine the laboratory momentum and polar-angle distributions of the charged particles from $K_S^0 \to π^+ π^-$ and $Λ\to p π^-$. The $K_S^0$ decayed two pions are strongly forward, whereas the proton and pion from the $Λ$ decay extend to larger angles and lower momenta. These distributions provide a kinematic baseline for future acceptance and tracking studies.

hep-ph↗
arXiv2026

Generic distinction of induced representations: the case of symmetric spaces

Let H be the fixed-point subgroup of an involution of a reductive group G over a local field F of characteristic zero. We give a necessary condition for a parabolically induced representation of G(F) to admit a non-zero family of H(F)-equivariant linear forms depending holomorphically on the induction parameter. By works of Blanc-Delorme and Brylinski-Delorme, this condition is essentially sufficient. As a global consequence, we obtain vanishing results for regularized periods of Eisenstein series. We illustrate this on symplectic periods, where we extend Offen's computation of truncated periods of certain cuspidal Eisenstein series to inner forms of GL(2n).

math.RT↗
arXiv2026

Extending Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection

While Hyperspectral Anomaly Detection (HAD) excels at identifying sparse targets in complex scenes, existing models remain trapped in a scalar "reconstruction-as-endpoint" paradigm. This reliance on ambiguous scalar residuals consistently triggers sub-pixel anomaly vanishing during spatial downsampling, alongside severe confirmation bias when unpurified anomalies corrupt training weights. In this paper, we propose Reconstruction-to-Vector Diffusion (R2VD), which fundamentally redefines reconstruction as a manifold purification origin to establish a novel residual-guided generative dynamics paradigm. Our framework introduces a four-stage pipeline: (1) a Physical Prior Extraction (PPE) stage that mitigates early confirmation bias via dual-stream statistical guidance; (2) a Guided Manifold Purification (GMP) stage utilizing an OmniContext Autoencoder (OCA) to extract purified residual maps while preserving fragile sub-pixel topologies; (3) a Residual Score Modeling (RSM) stage where a Diffusion Transformer (DiT), guarded by a Physical Spectral Firewall (PSF), effectively isolates cross-spectral leakage; and (4) a Vector Dynamics Inference (VDI) stage that robustly decouples targets from backgrounds by evaluating high-dimensional vector interference patterns instead of conventional scalar errors. Comprehensive evaluations on eight datasets confirm that R2VD establishes a new state-of-the-art, delivering exceptional target detectability and background suppression. The code is available at https://github.com/Bondojijun/R2VD.

cs.CV↗
arXiv2026

Cowork-Gym: Synthesizing Interactive Work Environments at Scale

Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that synthesizes Cowork environments through a build-execute-revise loop that uses execution evidence and review feedback to validate and repair generated environments. To capture realistic Cowork dynamics, a stateful user simulator responds to the agent's actions through dialogue and direct edits to the shared workspace. We synthesize 64.9K environments across 14 application scenarios and use them to post-train 9B, 27B, and 35B-A3B Qwen models with supervised fine-tuning, reinforcement learning, and on-policy distillation. Averaged across six agentic benchmarks, these models outperform their corresponding base checkpoints by 8.7, 6.4, and 4.1 points, respectively. Ours-27B ranks second overall among the evaluated models and achieves the highest average scores on PawBench and ClawEval, outperforming models with over 100B total parameters on both benchmarks.

cs.AI↗
arXiv2026

FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation

Graph fraud explanation generation emerges as an important task, which requires jointly leveraging graph structure and content information to produce human-readable explanations for a given risk label. An intuitive approach is to adapt existing graph-enhanced large language models (LLMs), which inject graph structure into LLMs via graph-conditioned instruction tuning or structure-aware embeddings. However, existing methods face two key challenges in graph fraud explanation generation: a lack of evaluation protocols tailored to explanation quality, and a mismatch between the granularity of graph information they provide and what explanation generation requires. In this paper, we propose FRaud Explanation Generation via Agentic Graph Context NavigaTION (FRACTION), a framework for graph fraud explanation generation. To evaluate explanation quality, we introduce a task-specific rubric that assesses faithfulness, graph grounding, helpfulness, consistency, and conciseness, and validate it against human judgments. To focus on fine-grained details of relevant neighbors without reading the entire neighborhood, we equip a language model with graph tools that progressively disclose neighbor records. To train our graph agent, we propose a rubric-guided trajectory distillation strategy through which the agent learns both tool-use behavior and structured explanation generation. Experimental results on three fraud datasets demonstrate consistent improvements over state-of-the-art baselines under a human-aligned rubric.

cs.LG↗
arXiv2026

Enhancing Quasi-Two-Dimensional Electronic Structure in Bi2O2Se via Chlorine Substitution

Bismuth oxyselenide (Bi2O2Se) has emerged as a leading semiconductor candidate for next-generation electronics and quantum phenomena research. However, its strong ionic interlayer bonding of Se layers fundamentally restricts the full potential of this otherwise promising quasi-two-dimensional (2D) material. In this work, we demonstrate chlorine substitution as an effective strategy to introduce van der Waals gaps and modify the electronic structure of the system. Through comprehensive transport and angle-resolved photoemission spectroscopy (ARPES) measurements on Bi6O6Se2Cl2 single crystal, an optimal Cl-doping compound, we show that the key electronic features, including indirect band gap, high electron mobility, and carrier effective mass, are well preserved, while the 2D character of the system is sufficiently enhanced. First-principles calculations attribute this selective tunability to the unique spatial separation between conductive Bi-O layers and dopant Se/Cl layers, which enables independent optimization of interlayer coupling and intralayer transport. Remarkably, our theoretical calculations combined with experimental observations project a broad bandgap engineering across a wide range (0.8 ~ 3.5 eV) within the Bi2O2Se system. Our findings not only expand the application potential of Bi2O2Se-based materials in optoelectronics, nanoelectronics, and fundamental research but also highlight spatial decoupling as a viable strategy for modifying detailed electronic structure of quasi-2D quantum systems.

cond-mat.mtrl-sci↗
arXiv2026

WorldWeave: Growing Persistent Geometric Worlds for Video Generation

Despite rapid progress, world models still lack explicit, persistent structural memory, making it difficult to preserve consistent world structure during continual scene expansion and cross-view revisits. To address this limitation, we present WorldWeave, a world generation framework that decouples world-state maintenance from visual rendering. Specifically, WorldWeave combines continual elevation-map generation with agent-guided scene organization and stitching to build an expandable explicit 3D world that incrementally extends structural memory while preserving existing structure. First, its terrain module uses diffusion-based image outpainting to generate continuous metric elevation maps under neighborhood conditioning and boundary constraints. Next, an agent integrates user intent, terrain evidence, and cross-region connectivity constraints to construct scenes through hierarchical semantic planning, deterministic geometry compilation, and local revision. Finally, during visual generation, planned camera trajectories query world geometry through a read-only interface, producing depth sequences that guide video synthesis without writing the generated results back into the world state. As a result, structural memory remains independent of short-window video generation, enabling continual expansion without predefined map boundaries and providing a consistent geometric basis for observations across trajectories and repeated visits.

cs.CV↗
arXiv2026

COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning

Asynchronous RL accelerates large language model post-training by decoupling rollout generation from optimization, but trains on stale trajectories. Existing methods primarily correct token-level policy mismatch through importance-ratio control in the actor objective. We show that this \emph{policy-side correction} alone is insufficient: advantage estimates also inherit mismatch from behavior-policy continuations, which we term \emph{advantage staleness}. We derive exact bias and variance decompositions for a general two-channel actor update, revealing nonseparable coupling between policy-weight and advantage-estimation errors: their interaction induces multiplicative bias terms, while squared policy weights amplify advantage uncertainty in gradient variance. This motivates the hypothesis that policy- and advantage-side correction should be coordinated. We introduce Coupled Off-Policy Correction (COPC), an actor--critic method combining token-level ratio masking with two-sided clipped-ratio weighting of TD residuals for return and advantage estimation. Joint parameter sweeps across staleness levels support this hypothesis: the effect of one correction parameter depends on, and can reverse with, the other. COPC achieves the highest reported performance on tool-integrated mathematical reasoning and search, outperforming the strongest reported asynchronous baseline in each setting. It also offers a broad high-performing parameter region and improved training stability. In search, COPC remains stable throughout training, while most evaluated asynchronous baselines collapse late in training. These gains persist at 64-step policy staleness. COPC adds minimal step-time overhead over asynchronous PPO and retains a $1.7\times$ step-time speedup over synchronous PPO.

cs.LG↗
arXiv2026

Decentralized Nonsmooth Nonconvex Optimization with Client-Data Sampling

This paper studies decentralized nonsmooth nonconvex optimization with Lipschitz-continuous local functions. We propose an efficient stochastic first-order method with a novel client-data sampling strategy in which the mini-batch sizes of the stochastic gradients on all clients follow a multinomial distribution. We show that our method can find a $(δ,ε)$-Goldstein stationary point on each client with the best-known dependence on $ε$~and $δ$ in both computational and communication complexity. Moreover, our results tighten the upper complexity bounds with respect to the Lipschitz parameter, the variance upper bound, the number of clients, and the spectral gap. We further conduct numerical experiments to demonstrate the empirical advantages of the proposed method.

math.OC↗
arXiv2026

OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One

Medical models are judged not only on correctness, but on whether reported confidence matches actual accuracy. Generalist multimodal medical models have expanded what a single model can perceive, yet they still express bounded decisions such as diagnoses, findings or cell counts as generated text, so the reported probability reflects the next token rather than the decision itself. Motivated by decision-native interfaces such as Jev, we introduce OmniMed-Jev, which represents each medical decision as a Choice, Noul or Score decision over a runtime-supplied candidate set and returns a full distribution over that set: mutually exclusive classes, binary presence of a finding, or a bounded ordered value. The design is omni in three respects: it accepts diverse imaging modalities, covers different prediction tasks, and expresses them through one candidate-conditioned probability model, so heterogeneous outputs become comparable probabilities rather than task-specific strings. In an interface-controlled comparison against a generative baseline trained on the same backbone, data and schedule, OmniMed-Jev's reported probabilities track observed correctness far more closely, reducing calibration error by up to an order of magnitude and reliability error by up to two, while point-prediction performance remains comparable; counting is the one family where the generative baseline stays ahead. Making the decision distribution the model's output is not a format change but what turns reported numbers into probabilities that mean what they say. These results support explicit decision modeling as a way to make reported confidence meaningful within the evaluated tasks, and they are not evidence of clinical readiness: the comparison cannot separate the interface from associated training differences, which we state alongside the results. Code is available at github.com/lytang63/OmniMed-Jev.

cs.LG↗
arXiv2026

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one another. We ask whether that appearance rests on a model of the partner's mind or on the surface record of what the partner said. We build a social simulation in which both questions have exact answers: 40 multi-issue negotiations whose hidden preference weights and whose full Pareto frontier are known by construction. Two model families negotiate across 160 dyads, every transcript is frozen before any measurement, and 2880 counterfactual probes then hold the evidence byte identical while moving one factor at a time: the reader's own stake, the partner's tone, an identity label, and the order of recursion. The agents are socially fluent and economically poor. They reach agreement in 96.2% of dyads with 0 protocol failures, yet only 0.7% of deals land on the Pareto frontier, they leave 20.5% of the available joint value unclaimed, and they miss the one issue on which their interests are perfectly aligned in 76.6% of deals; on the frontier and on that aligned issue, a package drawn at random from the set both sides would accept does as well. The probes locate the failure. Swapping only the reader's own payoff sheet, while the partner's words and offers stay identical, moves the inferred top priority by 15.0 percentage points, which is egocentric projection rather than inference, while a tone rewrite moves it by 5.3 percentage points and an identity label by 0.0. Most tellingly, an agent predicts what its partner believes about it 72.5% of the time while that partner's belief is itself correct only 51.2% of the time: the agents track the conversation far better than they track the mind behind it.

cs.LG↗
arXiv2026

NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities

Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains challenging. Existing benchmarks often target predefined capabilities, such as multi-hop retrieval or long-form synthesis, whereas users ask photo-grounded questions spanning a long tail of everyday scenarios. Despite advances in VLMs, users on Xiaohongshu, a mainstream Chinese image-sharing platform, continue to turn to other people for help with everyday visual questions. Motivated by this behaviour, we curate NoteVQA from these questions, yielding 252 items across 12 topical categories and 7 user intents. Each item includes a concise reference distilled from expert community responses and a human-audited interleaved reference answer that combines textual explanations with supporting visual evidence. We evaluate both short-answer correctness and interleaved-answer quality. To support the latter, we introduce AgenticInterleave, a single-agent ReAct framework for retrieval-supported answer generation, together with IVR-12, a 12-dimensional rubric for assessing the content, presentation, and image quality of interleaved references and model outputs. Across 9 frontier VLMs, the highest short-answer accuracy is 52.8\%, while adding agentic search to Qwen3.5-397B-A17B improves accuracy by only 2.0\%. For interleaved answers, the same model running AgenticInterleave scores 3.52 under IVR-12, compared with 4.65 for the human-audited references, with the largest gap in content quality. These results highlight the challenges that everyday visual questions pose for current VLMs in both answer accuracy and the quality of visually grounded explanations.

cs.AI↗