arXiv subjects

Jindong Wang

Publications and source records attributed to Jindong Wang.

At least 19 recordsLinked to original sources

arXiv2026

UniMore: Fine-Grained Supervision for Unified Understanding and Generation

Unified multimodal models combine image understanding and generation within one system, creating an opportunity to improve both capabilities through paired image--text supervision. We examine the outputs of a pretrained unified model in both directions and observe a loss of specificity: generated images can contain the requested objects with incorrect attributes, while captions identify a scene without expressing its distinguishing details. These failures call for supervision that specifies both the visual content to realize and the descriptive differences to distinguish. We propose UniMore, a post-training method that derives these complementary learning tasks from the fine-grained content of image--text pairs. The generation route predicts grounded crops from their corresponding phrases, matching the scope of the condition and visual target while using the native visual objective. The understanding route combines positive-caption fitting with ranking against captions that omit or alter details, conditioned on the full image. The two routes are optimized independently, and their learned updates are combined into a single unified model without changing its inference procedure. Experiments show gains across multiple understanding and generation benchmarks.

cs.MM↗

arXiv2026

Temporal Pair Consistency for Flow Matching

Flow-matching-style generative models learn time-dependent vector fields, but standard objectives supervise each timestep independently, leaving shared-path temporal structure unused. We introduce Temporal Pair Consistency (TPC), a simple training-time objective that couples velocity predictions at paired timesteps along the same probability path. TPC leaves the architecture, probability path, sampler, and inference-time computation unchanged. Under matched backbones, training budgets, solvers, and numbers of function evaluations, TPC improves sample quality across flow matching, OT-CFM, rectified flow, DiT-style backbones, and MeanFlow. On CIFAR-10, TPC improves FM from 6.35 to 3.19 FID and OT-CFM from 3.58 to 2.90 FID at the same NFE. Mechanism diagnostics show lower measured gradient variance, higher paired-gradient correlation, and reduced temporal roughness, while random and local pairing controls are substantially weaker. Higher-resolution ImageNet experiments further show consistent gains for DiT-XL/2 at 256 and 512 resolution and for MeanFlow at 256 resolution, all at matched inference cost.

cs.LG↗

arXiv2026

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains challenging because self-generated trajectories are free-form, correctness is task-dependent, and plausible rationales can still provide unstable or unreliable supervision. Existing methods mainly examine isolated design choices, leaving their effectiveness, roles, and interactions unclear. In this paper, we propose UniSD, a unified framework to systematically study self-distillation. UniSD integrates complementary mechanisms that address supervision reliability, representation alignment, and training stability, including multi-teacher agreement, EMA teacher stabilization, token-level contrastive learning, feature matching, and divergence clipping. Across six benchmarks and six models from three model families, UniSD reveals when self-distillation improves over static imitation, which components drive the gains, and how these components interact across tasks. Guided by these insights, we construct UniSDfull, an integrated pipeline that combines complementary components and achieves the strongest overall performance, improving over the base model by +5.4 points and the strongest baseline by +2.8 points. Extensive evaluation highlights self-distillation as a practical and steerable approach for efficient LLM adaptation without stronger external teachers.

cs.CL↗

arXiv2026

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.

cs.AI↗

arXiv2026

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we systematically reviewed nearly 250 scholarly sources, capturing the state of the art from various venues of publication, and establishing a solid foundation for our analysis. Our study offers a structured approach by developing two interrelated taxonomy systems: one that defines \emph{what to evaluate} and another that explains \emph{how to evaluate}. The first taxonomy identifies key components of LLM-based agents for multi-turn conversations and their evaluation dimensions, including task completion, response quality, user experience, memory and context retention, as well as planning and tool integration. These components ensure that the performance of conversational agents is assessed in a holistic and meaningful manner. The second taxonomy system focuses on the evaluation methodologies. It categorizes approaches into annotation-based evaluations, automated metrics, hybrid strategies that combine human assessments with quantitative measures, and self-judging methods utilizing LLMs. This framework not only captures traditional metrics derived from language understanding, such as BLEU and ROUGE scores, but also incorporates advanced techniques that reflect the dynamic, interactive nature of multi-turn dialogues.

cs.CL↗

arXiv2026

RealComm: Benchmarking and Adapting Audio Deepfake Detection over Real Communication Channels

Acoustic capture, device processing, and transmission coding in real calls jointly alter speech signals and may affect the reliability of audio deepfake detection. To systematically evaluate these effects, we introduce RealComm, a dataset pairing digital speech with recordings of the same utterances transmitted through real mobile calls. The acquisition design covers acoustic and wired injection, handset and speakerphone operation, and caller-side denoising, with bona fide and synthetic speech recorded under matched conditions. The dataset includes RealCommBench for evaluation and RealCommTrain for adaptation. We further develop RealComm-Aug, a staged waveform augmentation pipeline for simulating acquisition and transmission effects, and investigate its combination with real-call training. Experiments with existing detectors reveal substantial degradation after call transmission, even for models with strong digital-domain performance; acoustic injection is particularly challenging. Paired quality and spectral analyses show that quality degradation is associated with poorer detection across recording conditions for the evaluated detectors, while high-frequency attenuation alone does not explain detection difficulty. Simulated augmentation and real-call training provide complementary benefits, with their combination achieving the lowest call-domain error for each of three evaluated detectors. For Teffic-Audio, the equal error rate decreases from 37.94% to 22.37%. The demo and benchmark access information are provided through the project repository.

eess.AS↗

arXiv2026

Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents

Computational social science has developed descriptive, interpretative, and predictive modeling, but comprehensive modeling combining in-world human intervention with outcome forecasting remains underexplored. Generative agent-based platforms scale populations or reproduce complex scenarios, but researchers typically act through setup, external controls, or post-hoc analysis rather than in-world roles. We introduce Computational Multi-Agent Society Experiments (CMASE), a generative agent-based framework for in-world researcher participation and traceable interventions at runtime. Treating simulation as a simulated ethnographic field, CMASE supports (1) real-time human-computer interaction to study intervention processes; (2) controlled experiments with ethnography-inspired observation, interviewing, and interpretation; and (3) forward exploration of intervention trajectories and downstream responses. CMASE combines LLM-driven perception, memory, and emotion; a composable environment built from texture and area maps; and researcher roles spanning observation, interviewing, participation, and intervention, so that interventions enter as social events rather than exogenous parameters. We replicate two published field studies from different disciplines: urban greenery and social fragmentation, and cooperation in a public goods game, using two substantially different language models. CMASE reproduces reported statistical patterns and provides process-level records for mechanism-oriented interpretation. A controlled comparison shows that embedded social interventions leave observable, auditable processes that parametric manipulation does not. These findings highlight CMASE's methodological value for studying interventions in small- and medium-scale social settings and its interdisciplinary potential. The official code is available at: https://github.com/armihia/CMASE.

cs.AI↗

arXiv2026

FlexUMM: Flexible Representation Learning for Unified Multimodal Models

Unified multimodal models (UMMs) can integrate understanding and generation within a single backbone. However, it is commonly known that these two capabilities can cause conflicting representations, leading to a central question: how representation and computation should be shared across functionalities? Existing UMMs often rely on a largely fixed structure, where different inputs and functionalities follow the same depth and parameter-sharing pattern. We argue that this assumption is too restrictive: more effective unification requires sharing the computation that supports cross-functional communication while specializing the capacity that becomes task- or input-specific. We introduce FlexUMM, a flexible UMM framework that dynamically decides when to preserve shared computation, when to route specialized capacity, and when to stop further processing. Evidence shows that this flexible allocation improves UMMs along two complementary axes. It improves accuracy by reducing harmful competition between functionalities, and it improves efficiency by avoiding unnecessary computation once an input representation is sufficiently mature. Beyond simple architectural unification from the pre-trained models, FlexUMM works as a model-agnostic, functional plug-in to make existing UMMs more unified, stronger, and efficient. Code is available at: https://github.com/AIFrontierLab/TorchUMM/tree/main/src/umm/post_training/flexumm.

cs.AI↗

arXiv2026

Lluna: Collaborative Unimodal Models for Missing-Modality Inference

Pretrained unimodal models offer a flexible route to multimodal prediction through collaboration, but this collaboration can become less accurate than a surviving unimodal model when modalities are missing. We study this setting using fixed surviving-model anchors and find that collaborative gains can weaken or reverse as inputs disappear, even when the anchor's own input is unchanged. Our diagnostics further reveal reduced recovery of modality-specific information after aggregation and state-dependent collaborative representations. We propose Lluna, which combines a direct private prediction path from adapted unimodal features with a common graph-based collaboration branch that provides a residual correction. Progressive Collaboration Consistency organizes richer-to-poorer guidance along single-modality removals, aligning normalized common representations while task supervision adapts predictions to the available evidence. Across eight datasets spanning affective computing, scene understanding, and medical prediction, Lluna achieves the best evaluated average performance over non-full input states, improving Mean-Missing by 4.26\% on average relative to the strongest evaluated baseline. The fixed-anchor diagnostic also shows positive gains in mean collaboration under minimal inputs on all eight tasks. Code is available at https://github.com/AIFrontierLab/Lluna.

cs.MM↗

arXiv2026

Beyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies

Generative agent societies simulate people with assigned roles, preferences and relationships. As agents exchange arguments and choose partners, they can revise their positions and reorganise discussion. Understanding these changes requires examining what they accept and how they continue to interact. Stance-change scores and communication totals describe the extent of change. However, the same stance movement can preserve or reverse an assigned preference, and frequent communication can support either agreement or continuing disagreement. We therefore examine the content of changed positions and the exchanges that strengthen particular partnerships. Using Computational Multi-Agent Society Experiments (CMASE), we combine stance measures, source evaluations and temporal networks with individual answers and messages. Study 1 compares seven conditions across ten GPT-4o runs per condition, with a separate interview collection covering four models. Study 2 follows one 75-step GPT-4o café simulation. Environmental rational persuasion yields the largest mean stance departure ($1.30\pm0.08$ on a 7-point scale), whereas economic emotional persuasion yields the highest low-trust stance-shift rate ($17.3\%\pm11.2\%$, with standard deviations across runs). In the separate interviews, eight environmental agents shift from 7 to 6, acknowledge economic concerns and rate the source 3. Their partial acceptance preserves the assigned environmental preference. In the café, a pair with zero earlier exchanges becomes the most frequent final-phase partnership, with 25 messages. Its members develop coordination proposals while disputing their implementation. These results show that partial acceptance can coexist with low source trust, and sustained coordination with continuing disagreement.

cs.AI↗

arXiv2026

Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems

Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve. As AI becomes increasingly involved throughout the scientific research cycle, understanding these interconnected and evolving processes becomes increasingly important. We introduce SciUtopia, a persistent, closed-loop LLM-agent simulation framework for studying academic research ecosystems. SciUtopia models interconnected scientific processes such as research-direction choice, collaboration, submission, peer review, resubmission, citation, funding, and researcher attrition, while maintaining evolving states across simulated years. Its configurable institutional mechanisms and information channels provide a controlled testbed for matched counterfactual experiments and targeted interventions. Across 61 simulation worlds, SciUtopia simulates over 40,000 researchers from 8,000 institutions, producing around 400,000 publication decisions and 1.2 million LLM-generated peer reviews. Using these longitudinal simulations, we find that rejection-driven resubmission substantially amplifies reviewer burden beyond population growth alone, cautious exploration balances citation impact with career success and long-term topic diversity, and resource inequality can emerge even without detectable cumulative advantage from narrowly winning early funding. Code is available at https://github.com/Ahren09/ScienceUtopia.

cs.CL↗

arXiv2026

Beyond Structural Unification: A Perspective and Roadmap on Unified Multimodal Models

Unified Multimodal Models (UMMs) emerge as a promising way to combine understanding and generation within a single architecture. We argue that current approaches mainly achieve structural unification, which can create a Unification Paradox: shared interfaces, token spaces, and parameters do not guarantee an overall capability gain and may degrade individual capabilities. In this position paper, we identify five critical layers in which unification must be rethought: (1) Asymmetric Input Unification, where models must estimate the utility and reliability of each modality rather than treating all modalities equally; (2) Factorized Representation Unification, where semantic abstraction and fine-grained reconstruction should use separate but coordinated capacity; (3) Stateful Reasoning Unification, where models should maintain and revise a shared multimodal belief state across understanding and generation; (4) Synergistic Optimization Unification, where conflicting understanding and generation objectives require coordinated optimization; and (5) Multi-Centric Systemic Evaluation, where benchmarks must evaluate systemic competence, capability preservation, and cross-task robustness rather than isolated outcomes. We argue that progress requires moving beyond structural unification toward functional unification across the full system.

cs.MM↗

arXiv2026

Beyond End-to-End Black Box Mapping: An Intentional Agent Framework for Cognitive-driven Facial Reaction Generation

Automatic human-like facial reaction generation (FRG) is essential for building intelligent systems that can engage in human-computer interaction (HCI). While diverse and context-appropriate facial reactions can reflect latent appraisal and affective processes in human interaction, most existing FRG methods rely on end-to-end architectures that directly map speaker behaviours to listener expressions without an explicit intermediate internal state. We reformulate FRG as generation mediated by a structured internal-state process and propose the \textbf{Intentional Agent}, which shifts FRG from direct stimulus-response mapping to stimulus-grounded generation through explicit intermediate states. To represent temporal internal-state evolution, we propose an internal dynamics model that integrates emotional drives with an iterative Inner Thought Flow (ITF) within a structured intermediate state used for subsequent generation. This state can continue to update during conversational silences. Furthermore, to bridge abstract internal states with physiological actions, we formulate FRG as a downstream affective mapping from this latent thought flow to facial expressions. Experiments on the REACT 2025 dataset show an FRDist of 72.39 and an FRDiv of 0.5057; perceptual plausibility is evaluated separately through blinded human ratings. A blinded human evaluation of 96 reactions found no significant difference in mean score between Full and ground truth ($5.527$ vs.\ $5.195$, $p_{\mathrm{Holm}}=.076$), while Full significantly outperformed Event-Triggered and Heuristic-Only (both $p_{\mathrm{Holm}}<.001$). The Reaction Quality Scorer (RQS) correlated strongly with human judgements (Pearson $r=.855$; Spearman $ρ=.821$, both $p<.05$), supporting its use as an automatic metric. These results underscore the immense potential of endogenous dynamics in building highly autonomous, human-like agents.

cs.AI↗

arXiv2026

Multiscale modeling of host-pathogen interactions and mucociliary clearance during non-tuberculous mycobacterial pulmonary infection

Non-tuberculous mycobacterial (NTM) infections are a clinical challenge in cystic fibrosis (CF), where impaired mucociliary clearance and altered mucus rheology promote bacterial colonization despite host immune responses. Understanding how bacterial growth, immune cell dynamics, and mucus transport regulate infection progression is difficult because these processes interact across spatial and temporal scales. We develop a computational framework bridging a mechanistic agent-based model (ABM) of NTM infection with a spatially resolved partial differential equation (PDE) model. The PDE model couples bacterial proliferation, macrophage chemotaxis, immune-mediated clearance, mucus degradation, and viscoelastic transport in a two-compartment geometry representing mucus and lung tissue. Parameters are calibrated using data from the established ABM, yielding an efficient continuum representation while preserving cellular mechanisms. The PDE model reproduces bacterial and macrophage dynamics and enables analyses of mucus-related mechanisms and therapies. Sensitivity analysis identifies mucus viscosity, bacterial diffusivity, and macrophage mobility as key regulators of bacterial persistence through mucociliary clearance and tissue colonization. Simulations reveal nonlinear effects of mucolytic therapies: enhanced clearance reduces bacterial burden in mucus, whereas excessive viscosity reduction may promote migration into lung tissue, supporting combination with antibacterial treatment. This framework provides a quantitative platform for studying pulmonary infections, evaluating therapies, and developing patient-specific digital twins.

q-bio.QM↗

arXiv2026

When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs

Vision-language models (VLMs) are increasingly deployed in high-stakes settings, where a response that is reasonable in general may still be unsafe for a particular user whose medical, emotional, or situational context is unknown to the model. We study this problem of personalized safety in multimodal systems and introduce MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images across 12 high-risk domains, each paired with a hidden user profile. Evaluating eight frontier VLMs, we find that they almost always respond directly (86-99%) rather than seek missing context, and none exceeds 2.6/5 on personalized safety. To understand why these failures arise, we analyze multimodal interactions and identify visual dominance: visual information enters text representations early and suppresses textual risk signals during multimodal fusion. Causal interventions reveal a two-stage mechanism in which visual affect is first transferred into the text stream in early layers and then shapes the final decision through this altered text representation, making late-stage internal remediation unreliable. Motivated by this mechanism, we propose PRISM, a lightweight input monitor that uses bidirectional cross-modal modulation to predict when a query is likely to require deferral. PRISM achieves 0.978 AUC and strictly dominates the safety-utility Pareto frontier across all tested models.

cs.CV↗

arXiv2026

OISD: On-Policy Internal Self-Distillation of Language Models

Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive signals encoded in intermediate representations. In this paper, we introduce a new paradigm called on-policy internal self-distillation and propose the OISD framework, which improves reasoning by transferring on-policy predictive signals from the final layer to intermediate representations. During rollout and Group Relative Policy Optimization (GRPO) optimization, the final layer acts as both the policy and a detached internal teacher for selected intermediate layers, which are guided to align with it through two complementary mechanisms: logit alignment, which transfers high-level reasoning behaviors (how to think), and attention alignment, which enforces consistent attention patterns (where to look) from the final layer to the selected intermediate layer, both without requiring external privileged information. Our OISD, together with GRPO, employs signed advantage-weighted Jensen--Shannon alignment to distill informative intermediate representations while preserving policy consistency under a unified acting policy. Experimental results demonstrate the effectiveness of OISD, with substantial and consistent improvements over strong reasoning RL baselines across four mathematical reasoning tasks. The code will be released at https://github.com/THE-MALT-LAB/OISD

cs.LG↗

arXiv2026

Teffic-Audio: Tell Fact from Fiction

Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mechanisms, including speech synthesis, voice conversion, vocoder reconstruction, and neural-codec resynthesis. The resulting spoofing artifacts can be further shaped by variability in source speech, recording environments, and transmission channels. This variability makes robust generalization across heterogeneous conditions a central requirement for practical detection systems. This report presents Teffic-Audio, a general speech deepfake detection system designed for comprehensive evaluation environment. Teffic-Audio adopts a straightforward detector architecture consisting of a Conformer-based speech encoder, multi-head attentive statistics pooling, and a binary classifier. Rather than relying on additional architectural complexity, the system improves generalization through its training recipe, which integrates multi-source data, attack- and source-balanced sampling, and diverse audio augmentation. Trained only with open-source data, Teffic-Audio achieves a pooled EER of 1.454% on the 14 test sets of Speech-DF-Arena, outperforming all currently public systems on the leaderboard. It also obtains the lowest EER on five individual test sets and shows a favorable performance-complexity trade-off compared with larger leading systems. Overall, Teffic-Audio provides a strong and practical reference system for general speech deepfake detection.

cs.SD↗

arXiv2026

AI-AI co-creation outperforms human pairs in creative tasks

Prior research often finds that AI creativity is limited: single systems rarely outperform humans, and human-AI collaboration does not exceed human output. We argue these conclusions underestimate AI's potential because most studies do not allow iterative, multi-agent exchanges that mirror the social processes underpinning human creativity. We conducted an experiment comparing four conditions: (i) AI-AI co-creation with complementary generator-evaluator roles, (ii) AI-AI co-creation with identical roles, (iii) single-AI creation, and (iv) human-human co-creation. Across three open-ended tasks, 1,212 ideas were rated by trained judges on creativity, novelty, and usefulness. Both AI-AI co-creation conditions consistently outperformed single-AI creation and human pairs on creativity and novelty. Usefulness varied by task: complementary roles yielded the most useful solutions in the broadest and most socially complex task, suggesting role differentiation is advantageous when problems require both imaginative ideation and practical refinement. Human pairs performed worst, consistent with production losses in group creativity. These findings indicate that structured, iterative multi-agent AI co-creation can exceed single-AI and human-human ideation.

cs.CY↗