Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs

Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource-constrained on-device settings, selecting an appropriate large language model (LLM) backbone is a critical challenge: models must balance accuracy with strict inference latency and hardware efficiency constraints. This makes hardware-software co-design a game-changing requirement for on-device LLM deployment, where each hardware platform demands a tailored architectural solution. We propose a hardware co-design law that jointly captures model accuracy and inference performance. Specifically, we model training loss as an explicit function of architectural hyperparameters and characterise inference latency via roofline modelling. We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin, training 170 selected models for 10B tokens each to fit a scaling law relating architecture to training loss. By coupling this scaling law with latency modelling, we establish a direct accuracy-latency correspondence and identify the Pareto frontier for hardware co-designed LLMs. We further formulate architecture search as a joint optimisation over precision and performance, deriving feasible design regions under industrial hardware and application budgets. Our approach reduces architecture selection from months to days. At the same latency as Qwen2.5-0.5B on the target hardware, our co-designed architecture achieves 19.42% lower perplexity on WikiText-2. To our knowledge, this is the first principled and operational framework for hardware co-design scaling laws in on-device LLM deployment. We will make the code and related checkpoints publicly available.

From $O(mn)$ to $O(r^2)$: Two-Sided Low-Rank Communication for Adam in Distributed Training with Memory Efficiency

As foundation models continue to scale, pretraining increasingly relies on data-parallel distributed optimization, making bandwidth-limited gradient synchronization a key bottleneck. Orthogonally, projection-based low-rank optimizers were mainly designed for memory efficiency, but remain suboptimal for communication-limited training: one-sided synchronization still transmits an $O(rn)$ object for an $m\times n$ matrix gradient and refresh steps can dominate peak communicated bytes. We propose TSR, which brings two-sided low-rank communication to Adam-family updates (TSR-Adam) by synchronizing a compact core $U^\top G V\in\mathbb{R}^{r\times r}$, reducing the dominant per-step payload from $O(mn)$ to $O(r^2)$ while keeping moment states in low-dimensional cores. To further reduce the peak communication from subspace refresh, TSR-Adam adopts a randomized SVD-based refresh that avoids full-gradient synchronization. We additionally extend low-rank communication to embedding gradients with embedding-specific ranks and refresh schedules, yielding additional communication and memory savings over keeping embeddings dense. Across pretraining from 60M to 1B model scales, TSR-Adam reduces average communicated bytes per step by $13\times$, and on GLUE fine-tuning it reduces communication by $25\times$, while achieving comparable performance; we further provide a theoretical stationarity analysis for the proposed update. Code is available at https://github.com/DKmiyan/TSR-Adam.

Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation

Fine-tuning large language models (LLMs) for specialized domains often necessitates a trade-off between acquiring domain expertise and retaining general reasoning capabilities, a phenomenon known as catastrophic forgetting. Existing remedies face a dichotomy: gradient surgery methods offer geometric safety but incur prohibitive computational costs via online projections, while efficient data selection approaches reduce overhead but remain blind to conflict-inducing gradient directions. In this paper, we propose Orthogonal Gradient Selection (OGS), a data-centric method that harmonizes domain performance, general capability retention, and training efficiency. OGS shifts the geometric insights of gradient projection from the optimizer to the data selection stage by treating data selection as a constrained decision-making process. By leveraging a lightweight Navigator model and reinforcement learning techniques, OGS dynamically identifies training samples whose gradients are orthogonal to a general-knowledge anchor. This approach ensures naturally safe updates for target models without modifying the optimizer or incurring runtime projection costs. Experiments across medical, legal, and financial domains demonstrate that OGS achieves excellent results, significantly improving domain performance and training efficiency while maintaining or even enhancing performance on general tasks such as GSM8K.

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation

Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet image-ungrounded pathological details. Existing methods primarily rely on external knowledge guidance to facilitate the alignment between generated text and visual information. However, these approaches often ignore the inherent decoding priors and vision-language alignment biases in pretrained models and lack robustness due to reliance on constructed guidance. In this paper, we propose Layer-wise Expert-aligned Decoding (LEAD), a novel method to inherently modify the LVLM decoding trajectory. A multiple experts module is designed for extracting distinct pathological features which are integrated into each decoder layer via a gating mechanism. This layer-wise architecture enables the LLM to consult expert features at every inference step via a learned gating function, thereby dynamically rectifying decoding biases and steering the generation toward factual consistency. Experiments conducted on multiple public datasets demonstrate that the LEAD method yields effective improvements in clinical accuracy metrics and mitigates hallucinations while preserving high generation quality.

GAT-NeRF: Geometry-Aware-Transformer Enhanced Neural Radiance Fields for High-Fidelity 4D Facial Avatars

High-fidelity 4D dynamic facial avatar reconstruction from monocular video is a critical yet challenging task, driven by increasing demands for immersive virtual human applications. While Neural Radiance Fields (NeRF) have advanced scene representation, their capacity to capture high-frequency facial details, such as dynamic wrinkles and subtle textures from information-constrained monocular streams, requires significant enhancement. To tackle this challenge, we propose a novel hybrid neural radiance field framework, called Geometry-Aware-Transformer Enhanced NeRF (GAT-NeRF) for high-fidelity and controllable 4D facial avatar reconstruction, which integrates the Transformer mechanism into the NeRF pipeline. GAT-NeRF synergistically combines a coordinate-aligned Multilayer Perceptron (MLP) with a lightweight Transformer module, termed as Geometry-Aware-Transformer (GAT) due to its processing of multi-modal inputs containing explicit geometric priors. The GAT module is enabled by fusing multi-modal input features, including 3D spatial coordinates, 3D Morphable Model (3DMM) expression parameters, and learnable latent codes to effectively learn and enhance feature representations pertinent to fine-grained geometry. The Transformer's effective feature learning capabilities are leveraged to significantly augment the modeling of complex local facial patterns like dynamic wrinkles and acne scars. Comprehensive experiments unequivocally demonstrate GAT-NeRF's state-of-the-art performance in visual fidelity and high-frequency detail recovery, forging new pathways for creating realistic dynamic digital humans for multimedia applications.

CAG-Avatar: Cross-Attention Guided Gaussian Avatars for High-Fidelity Head Reconstruction

Creating high-fidelity, real-time drivable 3D head avatars is a core challenge in digital animation. While 3D Gaussian Splashing (3D-GS) offers unprecedented rendering speed and quality, current animation techniques often rely on a "one-size-fits-all" global tuning approach, where all Gaussian primitives are uniformly driven by a single expression code. This simplistic approach fails to unravel the distinct dynamics of different facial regions, such as deformable skin versus rigid teeth, leading to significant blurring and distortion artifacts. We introduce Conditionally-Adaptive Gaussian Avatars (CAG-Avatar), a framework that resolves this key limitation. At its core is a Conditionally Adaptive Fusion Module built on cross-attention. This mechanism empowers each 3D Gaussian to act as a query, adaptively extracting relevant driving signals from the global expression code based on its canonical position. This "tailor-made" conditioning strategy drastically enhances the modeling of fine-grained, localized dynamics. Our experiments confirm a significant improvement in reconstruction fidelity, particularly for challenging regions such as teeth, while preserving real-time rendering performance.

Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model

Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained opinion understanding in social media. Existing approaches mainly rely on discriminative classification with complex multimodal fusion, yet lacking explicit sentiment explainability. In this paper, we reformulate MABSA as a generative and explainable task, proposing a unified framework that simultaneously predicts aspect-level sentiment and generates natural language explanations. Based on multimodal large language models (MLLMs), our approach employs a prompt-based generative paradigm, jointly producing sentiment and explanation. To further enhance aspect-oriented reasoning capabilities, we propose a dependency-syntax-guided sentiment cue strategy. This strategy prunes and textualizes the aspect-centered dependency syntax tree, guiding the model to distinguish different sentiment aspects and enhancing its explainability. To enable explainability, we use MLLMs to construct new datasets with sentiment explanations to fine-tune. Experiments show that our approach not only achieves consistent gains in sentiment classification accuracy, but also produces faithful, aspect-grounded explanations.

Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework

In the digital era, effective identification and analysis of verbal attacks are essential for maintaining online civility and ensuring social security. However, existing research is limited by insufficient modeling of conversational structure and contextual dependency, particularly in Chinese social media where implicit attacks are prevalent. Current attack detection studies often emphasize general semantic understanding while overlooking user response relationships, hindering the identification of implicit and context-dependent attacks. To address these challenges, we present the novel "Hierarchical Attack Comment Detection" dataset and propose a divide-and-conquer, fine-grained framework for verbal attack recognition based on spatiotemporal information. The proposed dataset explicitly encodes hierarchical reply structures and chronological order, capturing complex interaction patterns in multi-turn discussions. Building on this dataset, the framework decomposes attack detection into hierarchical subtasks, where specialized lightweight models handle explicit detection, implicit intent inference, and target identification under constrained context. Extensive experiments on the proposed dataset and benchmark intention detection datasets show that smaller models using our framework significantly outperform larger monolithic models relying on parameter scaling, demonstrating the effectiveness of structured task decomposition.

Chain-of-thought Reviewing and Correction for Time Series Question Answering

With the advancement of large language models (LLMs), diverse time series analysis tasks are reformulated as time series question answering (TSQA) through a unified natural language interface. However, existing LLM-based approaches largely adopt general natural language processing techniques and are prone to reasoning errors when handling complex numerical sequences. Different from purely textual tasks, time series data are inherently verifiable, enabling consistency checking between reasoning steps and the original input. Motivated by this property, we propose T3LLM, which performs multi-step reasoning with an explicit correction mechanism for time series question answering. The T3LLM framework consists of three LLMs, namely, a worker, a reviewer, and a student, that are responsible for generation, review, and reasoning learning, respectively. Within this framework, the worker generates step-wise chains of thought (CoT) under structured prompts, while the reviewer inspects the reasoning, identifies erroneous steps, and provides corrective comments. The collaboratively generated corrected CoT are used to fine-tune the student model, internalizing multi-step reasoning and self-correction into its parameters. Experiments on multiple real-world TSQA benchmarks demonstrate that T3LLM achieves state-of-the-art performance over strong LLM-based baselines.

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.