Haibo Liu

Jingchao Wu, Zejian Kang, Haibo Liu et al.

Generating dynamic 3D facial animation from natural language requires understanding both temporally structured semantics and fine-grained expression changes. Existing datasets and methods mainly focus on speech-driven animation or unstructured expression sequences and therefore lack the semantic grounding and temporal structures needed for expressive human performance generation. In this work, we introduce KeyframeFace, a large-scale multimodal dataset designed for text-to-animation research through keyframe-level supervision. KeyframeFace provides 2,100 expressive scripts paired with monocular videos, per-frame ARKit coefficients, contextual backgrounds, complex emotions, manually defined keyframes, and multi-perspective annotations based on ARKit coefficients and images via Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Beyond the dataset, we propose the first text-to-animation framework that explicitly leverages LLM priors for interpretable facial motion synthesis. This design aligns the semantic understanding capabilities of LLMs with the interpretable structure of ARKit's coefficients, enabling high-fidelity expressive animation. KeyframeFace and our LLM-based framework together establish a new foundation for interpretable, keyframe-guided, and context-aware text-to-animation. Code and data are available at https://github.com/wjc12345123/KeyframeFace.

Xin Shen, Zhishu Jiang, Jiaye Yang et al. · baidu, tsinghua

Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightweight turns, but requests involving planning and tool invocation (e.g., search and media generation) produce heavy-tail execution latency that degrades turn-taking, persona consistency, and user trust. To address this challenge, we propose DuCCAE (Conversation while Collaboration with Augmentation and Evolution), a hybrid engine for immersive conversation deployed within Baidu Search, serving millions of users. DuCCAE decouples real-time response generation from asynchronous agentic execution and synchronizes them via a shared state that maintains session context and execution traces, enabling asynchronous results to be integrated back into the ongoing dialogue. The system orchestrates five subsystems-Info, Conversation, Collaboration, Augmentation, and Evolution-to support multi-agent collaboration and continuous improvement. We evaluate DuCCAE through a comprehensive framework that combines offline benchmarking on the Du-Interact dataset and large-scale production evaluation within Baidu Search. Experimental results demonstrate that DuCCAE outperforms strong baselines in agentic execution reliability and dialogue quality while reducing latency to fit strict real-time budgets. Crucially, deployment metrics since June 2025 confirm substantial real-world effectiveness, evidenced by a tripling of Day-7 user retention to 34.2% and a surge in the complex task completion rate to 65.2%. Our hybrid architecture successfully preserves conversational continuity while enabling reliable agentic execution, offering practical guidelines for deploying scalable agentic systems in industrial settings.

Ruyang Liu, Haoran Tang, Haibo Liu et al. · tencent-ai

The past year has witnessed the significant advancement of video-based large language models. However, the challenge of developing a unified model for both short and long video understanding remains unresolved. Most existing video LLMs cannot handle hour-long videos, while methods custom for long videos tend to be ineffective for shorter videos and images. In this paper, we identify the key issue as the redundant content in videos. To address this, we propose a novel pooling strategy that simultaneously achieves token compression and instruction-aware visual feature aggregation. Our model is termed Prompt-guided Pooling LLaVA, or PPLLaVA for short. Specifically, PPLLaVA consists of three core components: the CLIP-based visual-prompt alignment that extracts visual information relevant to the user's instructions, the prompt-guided pooling that compresses the visual sequence to arbitrary scales using convolution-style pooling, and the clip context extension designed for lengthy prompt common in visual dialogue. Moreover, our codebase also integrates the most advanced video Direct Preference Optimization (DPO) and visual interleave training. Extensive experiments have validated the performance of our model. With superior throughput and only 1024 visual context, PPLLaVA achieves better results on image benchmarks as a video LLM, while achieving state-of-the-art performance across various video benchmarks, excelling in tasks ranging from caption generation to multiple-choice questions, and handling video lengths from seconds to hours. Codes have been available at https://github.com/farewellthree/PPLLaVA.

Haibo Liu, Chengzhi Wei, Qunying Liao

In this paper, a class of linear authentication codes with secrecy are constructed, which have simple encoding rules and are easy to implement. Based on the special Weil sum, the maximum success probabilities of substitution attack and impersonation attack are calculated, and these codes are proven to be asymptotically optimal with respect to certain bounds.

Haibo Liu, Xin Guo, Qunying Liao

Recently, minimal linear codes have been extensively studied due to their applications in secret sharing schemes, secure two-party computations, and so on. Constructing minimal linear codes violating the Ashikhmin-Barg condition and then determining their weight distributions have been interesting in coding theory and cryptography. In this paper, a generic construction for ternary linear codes with dimension $m+2$ is presented, where $m$ is an integer, and a necessary and sufficient condition for this ternary linear code to be minimal is derived. Based on this condition and exponential sums, a new class of minimal ternary linear codes violating the Ashikhmin-Barg condition are obtained, and then their complete weight enumerators are determined.

Haibo Liu, Guang Lin

Diffusion models have emerged as powerful generative priors for solving PDE-constrained inverse problems. Compared to end-to-end approaches relying on massive paired datasets, explicitly decoupling the prior distribution of physical parameters from the forward physical model, a paradigm often formalized as Plug-and-Play (PnP) priors, offers enhanced flexibility and generalization. To accelerate inference within such decoupled frameworks, fast neural operators are employed as surrogate solvers. However, directly integrating them into standard diffusion sampling introduces a critical bottleneck: evaluating neural surrogates on partially denoised, non-physical intermediate states forces them into out-of-distribution (OOD) regimes. To eliminate this, the physical surrogate must be evaluated exclusively on the fully denoised parameter, a principle we formalize as the Manifold Consistency Requirement. To satisfy this requirement, we present Diffusion Latent Optimization (DiLO), which transforms the stochastic sampling process into a deterministic latent trajectory, enabling stable backpropagation of measurement gradients to the initial latent state. By keeping the trajectory on the physical manifold, it ensures physically valid updates and improves reconstruction accuracy. We provide theoretical guarantees for the convergence of this optimization trajectory. Extensive experiments across Electrical Impedance Tomography, Inverse Scattering, and Inverse Navier-Stokes problems demonstrate DiLO's accuracy, efficiency, and robustness to noise.

Junqing Chen, Haibo Liu

We propose an alternating direction method of multipliers (ADMM) to solve an optimization problem stemming from inverse lithography. The objective functional of the optimization problem includes three terms: the misfit between the imaging on wafer and the target pattern, the penalty term which ensures the mask is binary and the total variation regularization term. By variable splitting, we introduce an augmented Lagrangian for the original objective functional. In the framework of ADMM method, the optimization problem is divided into several subproblems. Each of the subproblems can be solved efficiently. We give the convergence analysis of the proposed method. Specially, instead of solving the subproblem concerning sigmoid, we solve directly the threshold truncation imaging function which can be solved analytically. We also provide many numerical examples to illustrate the effectiveness of the method.

Junqing Chen, Haibo Liu

We present a novel implicit neural shape optimization framework for 3D high-contrast Electrical Impedance Tomography (EIT), addressing scenarios where conductivity exhibits sharp discontinuities across material interfaces. These high-contrast cases, prevalent in metallic implant monitoring and industrial defect detection, challenge traditional reconstruction methods due to severe ill-posedness. Our approach synergizes shape optimization with implicit neural representations, introducing key innovations including a shape derivative-based optimization scheme that explicitly incorporates high-contrast interface conditions and an efficient latent space representation that reduces variable dimensionality. Through rigorous theoretical analysis of algorithm convergence and extensive numerical experiments, we demonstrate substantial performance improvements, establishing our framework as promising for practical applications in medical imaging with metallic implants and industrial non-destructive testing.