Searcharxiv⌕ Search

arXiv subjects

Kaiwen Zheng

Publications and source records attributed to Kaiwen Zheng.

At least 19 recordsLinked to original sources

From Token Bills to Benchmark Weeks: Making Auto-Research for Data Systems Verifiable and Affordable

AI auto-research is poised to forge bespoke data systems, from key-value stores and indexes to query engines, each engineered for a specific workload and hardware platform. Yet this promise rests on fragile ground. An agent optimizes what it can measure, not necessarily what users need. Natural-language requirements leave ample room for specification gaming, producing systems that blaze through benchmarks while silently losing updates or violating consistency. Worse, each research iteration consumes tokens, while validating a candidate under real concurrency, memory pressure, and failure conditions can stretch the entire research process into weeks. In this paper, we envision a more cost-efficient and verifiable approach to auto-research. Precise and composable specifications anchor the search, lightweight performance critics prune costly dead ends, and falsification and deductive verification make correctness an integral part of the process rather than an afterthought. By treating correctness, performance, research time, and token cost as equally important objectives, we aim to transform AI-generated data systems from plausible artifacts into trustworthy, production-grade systems whose behavior can be understood, audited, and ultimately relied upon.

cs.DB↗

Few-Step Streaming Video Generation via Condition Shifting

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory and computation and must track the evolving generator. We extend APEX to streaming video by using condition shifting to estimate the velocity field of the generated distribution within the generator. The original text condition selects generation, while a shifted condition selects fake estimation using the same parameters. This removes the independent fake network while retaining S2-Avatar's frozen reference teacher, Self-Replay Forcing, and perceptual regularization. We evaluate APEX on 180-second videos using three backbone evaluations per block and a one-step spatial Refiner, with a 70-case human study and a 320-case StreamAV-Bench comparison. Compared with S2-Avatar, APEX achieves higher video instruction fulfillment on the Progressive track (3.856 versus 3.831) and higher visual aesthetics across both tracks (0.641898 versus 0.632606). Human raters favor APEX most strongly on instruction following, with +30.0% net preference, followed by consistency and video quality at +4.3% each. Motion quality favors S2-Avatar, audiovisual synchronization is predominantly tied, and usability is unchanged. Separate measurements under matched training settings show 4.4% lower peak allocated GPU memory per GPU and 9.2% shorter mean iteration time than DMD.

cs.CV↗

Interactive World Simulation with Cosmos for Physical AI

We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI. By streaming visual observations in response to actions and scene controls, the framework enables users and embodied agents to interact with evolving virtual environments. It supports both predicting the visual consequences of actions and generating observations from physical state maintained by an external simulator. We demonstrate this approach across camera navigation and robot manipulation, controllable video transfer, and multi-view autonomous vehicle (AV) simulation. These examples provide a shared foundation for developing interactive virtual environments for Physical AI training and evaluation. Our code and model checkpoints are available at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3-examples. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation.

cs.AI↗

Intrinsic Distribution Matching

One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution matching distillation (DMD) uses score differences to bring the generated distribution closer to a reference distribution. Following prior work, we estimate this difference with internal velocity branches, avoiding a separate fake-score network. We ask whether an explicit moment constraint improves this learned score supervision. A decomposition of the reverse-KL field into a Gaussian moment component and a non-Gaussian residual identifies statistics that can be constrained explicitly. We introduce Intrinsic Distribution Matching (IDM), which retains the full DMD correction and matches feature means and per-coordinate standard deviations using the generator's exponential-moving-average (EMA) copy, requiring no external feature encoder. Experiments use full-parameter and low-rank adaptation (LoRA) tuning on Z-Image-Turbo 6B and Qwen-Image 20B. At two network evaluations, IDM reaches 94.25% and 90.20% on Chinese and English LongText-Bench, the highest scores among the compared methods at this budget. Controlled ablations show gains from the added moment loss, while generator EMA features perform competitively with an external DINOv2 encoder across the five reported metrics. Code is available at https://github.com/inclusionAI/IDM.

cs.CV↗

I$^2$-KAN: Interpretable Intra- and Inter-Modal Multi-Pathway Representation Learning for Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and cross-modal interactions into joint representations, making it difficult to determine whether predictive utility arises from a modality itself or from its interactions with others. More fundamentally, a modality's standalone predictive utility may not faithfully reflect its interaction-conditioned predictive utility. To address this issue, we propose I$^2$-KAN, an interpretable multi-pathway framework that explicitly maintains intra-modal and pairwise inter-modal information in separate structural pathways. Each pathway is refined by a Task-Decoupled Linear-Gated Denoising Bottleneck (TDL-GDB) to learn compact and task-relevant representations, followed by structured Kolmogorov-Arnold Network fusion that retains explicit pathway associations and supports multi-level interpretation. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS v2 demonstrate strong overall performance. Ablation and interpretability analyses consistently show across the three benchmarks that low standalone predictive utility does not necessarily imply low interaction-conditioned predictive utility: a modality that appears weak in isolation can remain informative through pairwise interactions. These findings highlight the interaction-dependent nature of multimodal utility and suggest that modality utility should be characterized from both standalone and interaction-conditioned perspectives.

cs.CV↗

SLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or linear branch based on attention-weight magnitude, which can be suboptimal. Additionally, (ii) after formally analyzing the attention error in SLA, we identify a mismatch between SLA and a direct decomposition into sparse and linear attention. We propose SLA2, which introduces (I) a learnable router that dynamically selects whether each attention computation should use sparse or linear attention, (II) a more faithful and direct sparse-linear attention formulation that uses a learnable ratio to combine the sparse and linear attention branches, and (III) a sparse + low-bit attention design, where low-bit attention is introduced via quantization-aware fine-tuning to reduce quantization error. Experiments show that on video diffusion models, SLA2 can achieve 97% attention sparsity and deliver an 18.6x attention speedup while preserving generation quality.

cs.LG↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗

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↗