arXiv subjects

Kaiwen Zheng

Publications and source records attributed to Kaiwen Zheng.

At least 19 recordsLinked to original sources

arXiv2026

Joint Transceiver and Group Index Modulation Design for Wideband Integrated Sensing and Communications Under Beam Squint

The combination of ultra-wide bandwidth and large-scale multiple-input multiple-output arrays with frequency-independent phase shifters induces beam squint, causing frequency and distance dependent array gain variations across subcarriers and degrading integrated sensing and communications performance. Transceiver beamforming and group index modulation (GIM) can alleviate the impact of beam squint on communication and sensing performance. However, their designs are coupled in the frequency domain, as beamforming shapes the subcarrier responses on which GIM grouping and activation depend. To address this coupling, we propose a joint transceiver beamforming and GIM design that maximizes a weighted combination of normalized worst-case communication and sensing distances. An alternating optimization algorithm jointly refines the transceiver beamformers and GIM configuration. Simulation results show that the proposed joint design reduces bit error rate in the high signal-to-noise ratio region and achieves a more favorable communication-sensing trade-off, while maintaining an average sensing AUC comparable to that of the considered GIM based benchmark schemes.

eess.SP↗

arXiv2026

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipeline that converts existing bidirectional T2V/TI2V video foundation models into camera-controllable few-step autoregressive world models. Specifically, minWM first fine-tunes a bidirectional video diffusion model with camera control, and then applies the Causal Forcing / Causal Forcing++ pipeline, including AR diffusion training, causal ODE or causal consistency distillation, and asymmetric DMD, to distill it into a few-step autoregressive generator for low-latency rollout. The framework is modular and architecture-extensible: we instantiate it on representative open backbones, including Wan2.1-T2V-1.3B and HY1.5-TI2V-8B, covering both cross-attention-based condition injection and MMDiT-style architectures. minWM also supports adapting existing video world models, such as HY-WorldPlay, to new data distributions, training recipes, and latency targets. Beyond releasing runnable scripts, checkpoints, documentation, and inference code, we provide practical ablations on camera trajectory quality, controllability training steps, and minimal batch-size requirements. We hope minWM serves as a reproducible and extensible recipe for building and adapting real-time interactive video world models. Project Page: [https://github.com/shengshu-ai/minWM](https://github.com/shengshu-ai/minWM)

cs.CV↗

arXiv2026

Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One

Language generation is almost universally treated as a sequential process: autoregressive models emit one token at a time, while diffusion language models replace token-level seriality with a long trajectory of iterative refinement. In this work, we introduce PlaidQ, a 0.7B continuous diffusion language model for code generation, and show that its trajectory can be aggressively distilled into only a few denoising steps---or even one, enabling efficient code generation. PlaidQ repurposes a pretrained autoregressive model as a bidirectional denoiser over continuous token embeddings. We distill PlaidQ with distribution matching for few-step generation and paired-trajectory supervision for one-step generation. At matched model scale, PlaidQ is competitive with discrete diffusion language models on code generation. Distillation then shifts the quality--compute frontier: a 16-step student reaches 31.78 and 40.49 pass@10 on HumanEval and MBPP+, surpassing the same PlaidQ teacher sampled for 512 steps. At the extreme, paired-trajectory distillation achieves 7.07 pass@1 on HumanEval with a single denoising step, producing functionally correct programs. Together, these results establish continuous diffusion as a viable path to few-step and one-step code generation. Broadly, continuous diffusion is not merely another representation for language: it provides an interface through which language models can inherit the acceleration and distillation machinery of continuous diffusion modeling. Training and inference code and model checkpoints are available at https://github.com/pengzhangzhi/plaidq.

cs.LG↗

arXiv2026

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

cs.CV↗

arXiv2026

TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation

Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal computation of large models make inference prohibitively expensive. We present TurboT2VA, a distillation and inference framework for accelerating a 19B-parameter joint video-audio model. Large-scale T2VA distillation is challenged by modality-imbalanced optimization, the difficulty of continuous-time consistency training at scale, and the quality--diversity trade-off. TurboT2VA addresses these issues with per-modality normalization and a progressive curriculum comprising discrete consistency warm-up, continuous consistency refinement, and joint consistency--distribution matching. The curriculum first establishes a stable, diverse generation trajectory and only then introduces distribution-level refinement. On LTX-2, four-step distillation reduces generator latency from 50.52s to 2.51s at the standard evaluation resolution of 512$\times$768, achieving a 20.1$\times$ speedup while maintaining strong visual quality, audio fidelity, diversity, and video-audio synchronization. We further develop an architecture-aware inference stack that combines guarded W8A8 and fused operators, padded-text compaction, and modality-aware sparse attention while preserving dense cross-modal and text-conditioning paths. Under the high-resolution deployment setting at 1024$\times$1792, the complete stack reduces generator latency from 318.74s to 5.83s on one NVIDIA H20, achieving a 54.67$\times$ generator-only speedup. Inference code and generation demos are available at https://github.com/thu-ml/TurboDiffusion/tree/main/turbot2va.

cs.CV↗

arXiv2026

A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources

Facial state analysis plays a crucial role in understanding human expressions, psychological modeling, and human computer interaction. Traditional unimodal vision-based methods are often limited by environmental sensitivity and weak interpretability. Multimodal facial state analysis addresses these issues by integrating complementary cues from visual, audio, textual, physiological, and other related modalities. This survey emphasizes two key aspects: on one hand, multimodal learning enables contextual semantic understanding for improved facial state reasoning and leverages interpretable language generation to enhance model explainability; on the other hand, multi-task learning allows simultaneous analysis of expressions, action units (AUs), and face-based soft biometrics (e.g., age, gender), effectively capturing fine-grained expressions and improving cross-scene generalization. This survey reviews core tasks, representative methods, and datasets in multimodal facial state analysis, focusing on facial expression recognition, AU detection, and face-based soft biometric estimation, and emphasizing the unique value of language in providing contextual semantics, enhancing reasoning, and generating explanations. The survey aims to provide an up-to-date overview of the literature and to highlight future research directions for multimodal, interpretable, and multi-task adaptive facial state analysis.

cs.CV↗

arXiv2026

Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models

Quantization is widely used to deploy large language models, but its effect on uncertainty behavior, such as confidence, margins, and abstention, is rarely treated as a primary objective. We frame calibration-data selection for quantization as a target-dependent uncertainty-preservation problem. Different deployments emphasize different regions of the input distribution, yet prior work mainly optimizes accuracy-oriented compression metrics or adjusts scores after quantization. We formalize this goal with distributional and boundary preservation risks, and provide a simple mixture-mismatch argument explaining why no single calibration recipe should be expected to fit all targets. We introduce Doubt-Preserving Quantization (DPQ), a lightweight pre-quantization recipe family that uses full-precision predictions to construct target-aligned calibration mixtures of high-doubt examples and generic anchors. Across 8 language models, 9 NLP benchmarks, and 22 comparison methods, the leading fixed recipe changes with the preservation target: DPQ-r75 leads on SQuAD2 answerability-boundary preservation, while milder or single-signal variants, including DPQ-r50, confidence-only, and entropy-only, better preserve broad multiple-choice QA behavior. These results show that calibration data should be selected for the specific full-precision score behavior a deployment needs to preserve, rather than treated as a fixed quantization detail.

cs.CL↗

arXiv2026

Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?

Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.g, at least 7B), which simultaneously incurs high computational costs and reduces inference efficiency, thereby hindering real-time deployment on resource-constrained platforms such as robots and mobile devices. This raises a fundamental question: do we really need the multimodal MER model larger than 1B parameters for high-quality MER? In this paper, we challenge the assumption that larger models are inherently necessary and proposes a lightweight MER framework (called Light-MER), which achieves better and faster multimodal sentiment understanding and recognition through knowledge distillation. It can transfer knowledge from a strong, large-scale teacher model to a lightweight sub-billion-parameter student model, aiming to preserve rich multimodal emotion reasoning and recognition while substantially improving deployment efficiency. Specifically, we introduce two new optimization strategies to enhance knowledge transfer: (1) a new optimal transport loss that combines Sliced Wasserstein Distance with hidden-state alignment, and (2) a new multi-reward optimization strategy based on GRPO that balances MER performance and efficiency, aimed at further enhancing the learning capabilities of student models. Extensive experiments on nine benchmark datasets demonstrate that Light-MER achieves state-of-the-art performance while significantly improving inference efficiency. This highlights the strong potential of small multimodal emotion language models for future research. Code is available at https://github.com/GAIR-Lab/Light-MER.

cs.AI↗

arXiv2026

Anomalous Microwave Response in YBCO Resonators beyond the Two-Level-System Model

We report the microwave response of coplanar-waveguide (CPW) resonators fabricated from $\mathrm{YBa_2Cu_3O_{7-δ}}$ (YBCO) thin films over temperatures from approximately $70~\mathrm{mK}$ to $40~\mathrm{K}$. The resonators exhibit internal quality factors $Q_\mathrm{i}$ in the range of $4\times10^3$ to $10^4$ at 70 mK, which increase to a maximum of approximately $8\times10^3$ to $1.2\times10^4$ near $6~\mathrm{K}$. At low temperatures, both $Q_\mathrm{i}$ and the fractional shift of the resonance frequency $Δf_\mathrm{r}/f_\mathrm{r}$ increases with temperature, qualitatively resembling behavior commonly associated with two-level-system (TLS) defects. However, neither response saturates on the temperature scale set by the resonator frequency, and the loss exhibits no observable microwave-power dependence. We show that low-temperature frequency upturn may be better described by an additional paramagnetic response associated with defect-induced local moments or Andreev bound states, while the low-temperature loss follows an approximately logarithmic temperature dependence whose microscopic origin remains unresolved. These measurements establish the millikelvin performance of patterned YBCO resonators and show that their low-temperature response cannot be understood within the conventional TLS framework alone.

cond-mat.supr-con↗

arXiv2026

Vidu S1: A Real-Time Interactive Video Generation Model

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.

cs.CV↗

arXiv2026

RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation

Sequential recommender systems rely on a single forward pass to encode user interaction histories and predict the next item. Increasing inference-time computation through latent reasoning, with the model proceeding step by step before the final prediction, has been recently explored in sequential recommendation with promising results. However, how to structure the reasoning process for sequential recommendation remains an open question. Existing approaches couple reasoning and prediction in a single $d$-dimensional state, limiting reasoning depth and often relying on multi-stage pipelines with reinforcement learning (RL). We propose RecRec (Recursive Reasoning for Recommendation), an RL-free framework that decouples reasoning from prediction, overcoming the fixed $d$-dimensional state bottleneck of prior methods. RecRec consists of a Context Compressor and a Recursive Reasoner, trained in two simple supervised stages. The Context Compressor distills the backbone's hidden states into a small set of latent interests, with an Interest Diversity Regularizer encouraging each interest to capture a distinct aspect of user behavior. The Recursive Reasoner then refines these interests by reasoning in a separate intermediate latent space. Deep supervision lets the reasoning depth be freely adjusted at inference without retraining. On four real-world datasets, RecRec outperforms state-of-the-art reasoning-enhanced methods, and on three of four datasets, gains extend past the training-time depth. Our findings point to a decoupled, multi-vector recipe that unleashes latent reasoning from the single-state bottleneck of prior methods, suggesting reasoning-state structure as a design axis to explore further in sequential recommendation.

cs.IR↗

arXiv2026

Stream-aware Side Adaptation for Large Pre-trained Multimodal Embedding Models in Sequential Recommendation

Recently, large pretrained multimodal embedding models such as Qwen3-VL Embedding have shown strong promise for sequential recommendation, as they provide reusable semantic item representations across modalities and domains. However, directly using these embeddings often leads to suboptimal performance because of domain misalignment. Efficient side adaptation is therefore an attractive solution. Although adapting all backbone layers should help, existing side adapters often degrade with depth, prompting layer dropping despite the loss of useful hidden states. This is due to two major challenges: (1) the lack of modeling in selecting fused representations during residual addition, and (2) the insufficient preservation of earlier representations during progressive sigmoid fusion. This paper therefore asks a practical question: How can we design a side adaptation approach that effectively unlocks the potential of large pre-trained multimodal embedding models? To address this question, we propose Stresa, a stream-aware side-adaptation framework for frozen large pre-trained multimodal embedding models in sequential recommendation. Stresa introduces Stream-aware Hidden-Adapter Fusion (SHAF) to preserve historical side memory during fusion and Residual Stream Adapter (ReSA) to produce selective residual updates across layers. Empirically, Stresa consistently outperforms standard side adapters and state-of-the-art baselines on public datasets across multiple backbone embedding models. These results highlight the promise of adapting large embedding models for sequential recommendation. Our code is publicly available at https://github.com/GAIR-Lab/Stresa.

cs.IR↗

arXiv2026

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work, we extend rCM, an advanced diffusion distillation framework, to autoregressive video diffusion. The core philosophy of rCM lies in the complementarity between forward and reverse divergences, represented by consistency models (CMs) and distribution matching distillation (DMD), respectively, in diffusion distillation. This philosophy naturally carries over to the autoregressive setting, where teacher-forcing (TF) provides an offline, forward-divergence causal training paradigm, while self-forcing (SF) corresponds to an on-policy, reverse-divergence refinement. Our contributions are: (1) through extensive experiments, we show that teacher-forcing CM is currently the best complement to self-forcing DMD as an initialization strategy (2) we present the first implementation of teacher-forcing-based continuous-time CMs (e.g., sCM/MeanFlow) for autoregressive video diffusion, enabled by our custom-mask FlashAttention-2 JVP kernel, achieving 10$\times$ faster convergence compared to discrete-time CMs (dCMs) (3) we introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training (4) we achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training. Notably, our distilled 2-step causal Wan2.1-1.3B model achieves a VBench-T2V score of 84.63 with only 1 or 2 sampling steps. We further apply Causal-rCM to Cosmos 3, an advanced omnimodal world foundation model for physical AI with action-conditioned generation capability, enabling an interactive world model.

cs.CV↗

arXiv2026

GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance

Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced a data-to-data generative process that can exploit an instructive clean prior. In this work, inspired by previous methods creating quality difference between denoising results as guidance, we propose a training-free bridge guidance method, termed Prior Guidance (PG). Specifically, we introduce a weak prior, which is unseen during bridge pre-training, hindering prior exploitation and thereby degrading denoising result. Then, we contrast it with the seen prior to highlight and enhance prior exploitation via a scaling factor. Moreover, we analyze the underlying mechanism of prior exploitation in the bridge process and design frequency-modulated prior guidance (FMPG), which tailors the guidance scale to low- and high-frequency bands coherent with bridge generative dynamics. To address prior exploitation in image in-painting, we develop a cascaded framework, CFG-FMPG, which first generates a noisy hidden representation via CFG and then exploits it as a generative prior with FMPG, fulfilling their complementary strengths without compromising inference efficiency. Experiments demonstrate that our PG methods consistently improve pre-trained bridge models across diverse image translation tasks.

cs.CV↗

arXiv2026

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies are either target-misaligned, incapable of few-step generation, or too costly to scale. We propose \textbf{Causal Forcing++}, a principled and scalable pipeline that uses \emph{causal consistency distillation} (causal CD) for few-step AR initialization. The core idea is that causal CD learns the same AR-conditional flow map as causal ODE distillation, but obtains supervision from a single online teacher ODE step between adjacent timesteps, avoiding the need to precompute and store full PF-ODE trajectories. This makes the initialization both more efficient and easier to optimize. The resulting pipeline, \ours, surpasses the SOTA 4-step chunk-wise Causal Forcing under the \textit{\textbf{frame-wise 2-step setting}} by 0.1 in VBench Total, 0.3 in VBench Quality, and 0.335 in VisionReward, while reducing first-frame latency by 50\% and Stage 2 training cost by $\sim$$4\times$. We further extend the pipeline to action-conditioned world model generation in the spirit of Genie3. Project Page: https://github.com/thu-ml/Causal-Forcing and https://github.com/shengshu-ai/minWM .

cs.CV↗

arXiv2026

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of evaluation benchmarks like FID. This work represents the first effort to scale up continuous-time consistency to general application-level image and video diffusion models, and to make JVP-based distillation effective at large scale. We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks. Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the "mode-covering" nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. This integration complements sCM with the "mode-seeking" reverse divergence, effectively improving visual quality while maintaining high generation diversity. Validated on large-scale models (Cosmos-Predict2, Wan2.1) up to 14B parameters and 5-second videos, rCM generally matches the state-of-the-art distillation method DMD2 on quality metrics while mitigating mode collapse and offering notable advantages in diversity, all without GAN tuning or extensive hyperparameter searches. The distilled models generate high-fidelity samples in only $1\sim4$ steps, accelerating diffusion sampling by $15\times\sim50\times$. These results position rCM as a practical and theoretically grounded framework for advancing large-scale diffusion distillation. Code is available at https://github.com/NVlabs/rcm.

cs.CV↗

arXiv2026

Training-Free Test-Time Contrastive Learning for Large Language Models

Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods rely on gradient-based updates that require white-box access and need substantial overhead, while training-free alternatives are either static or depend on external guidance. In this paper, we propose Training-Free Test-Time Contrastive Learning TF-TTCL, a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences. Specifically, TF-TTCL implements a dynamic "Explore-Reflect-Steer" loop through three core modules: 1) Semantic Query Augmentation first diversifies problem views via multi-agent role-playing to generate different reasoning trajectories; 2) Contrastive Experience Distillation then captures the semantic gap between superior and inferior trajectories, distilling them into explicit textual rules; and 3) Contextual Rule Retrieval finally activates these stored rules during inference to dynamically steer the frozen LLM toward robust reasoning patterns while avoiding observed errors. Extensive experiments on closed-ended reasoning tasks and open-ended evaluation tasks demonstrate that TF-TTCL consistently outperforms strong zero-shot baselines and representative TTA methods under online evaluation. Code is available at https://github.com/KevinSCUTer/TF-TTCL.

cs.CL↗

arXiv2026

AudioMoG: Guiding Audio Generation with Mixture-of-Guidance

The design of diffusion-based audio generation systems has been investigated from diverse perspectives, such as data space, network architecture, and conditioning techniques, while most of these innovations require model re-training. In sampling, classifier-free guidance (CFG) has been uniformly adopted to enhance generation quality by strengthening condition alignment. However, CFG often compromises diversity, resulting in suboptimal performance. Although the recent autoguidance (AG) method proposes another direction of guidance that maintains diversity, its direct application in audio generation has so far underperformed CFG. In this work, we introduce AudioMoG, an improved sampling method that enhances text-to-audio (T2A) and video-to-audio (V2A) generation quality without requiring extensive training resources. We start with an analysis of both CFG and AG, examining their respective advantages and limitations for guiding diffusion models. Building upon our insights, we introduce a mixture-of-guidance framework that integrates diverse guidance signals with their interaction terms (e.g., the unconditional bad version of the model) to maximize cumulative advantages. Experiments show that, given the same inference speed, our approach consistently outperforms single guidance in T2A generation across sampling steps, concurrently showing advantages in V2A, text-to-music, and image generation. Demo samples are available at: https://audiomog.github.io.

cs.SD↗