The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes

This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd context including the previewed Behemoth teacher model, (ii) architectural characteristics beyond a high-level MoE description covering routed/shared-expert structure, early-fusion multimodality, and long-context design elements reported for Scout (iRoPE and length generalization strategies), (iii) training disclosures spanning pre-training, mid-training for long-context extension, and post-training methodology (lightweight SFT, online RL, and lightweight DPO) as described in release materials, (iv) developer-reported benchmark results for both base and instruction-tuned checkpoints, and (v) practical deployment constraints observed across major serving environments, including provider-specific context limits and quantization packaging. The manuscript also summarizes licensing obligations relevant to redistribution and derivative naming, and reviews publicly described safeguards and evaluation practices. The goal is to provide a compact technical reference for researchers and practitioners who need precise, source-backed facts about Llama 4.

SketchAssist: A Practical Assistant for Semantic Edits and Precise Local Redrawing

Sketch editing is central to digital illustration, yet existing image editing systems struggle to preserve the sparse, style-sensitive structure of line art while supporting both high-level semantic changes and precise local redrawing. We present SketchAssist, an interactive sketch drawing assistant that accelerates creation by unifying instruction-guided global edits with line-guided region redrawing, while keeping unrelated regions and overall composition intact. To enable this assistant at scale, we introduce a controllable data generation pipeline that (i) constructs attribute-addition sequences from attribute-free base sketches, (ii) forms multi-step edit chains via cross-sequence sampling, and (iii) expands stylistic coverage with a style-preserving attribute-removal model applied to diverse sketches. Building on this data, SketchAssist employs a unified sketch editing framework with minimal changes to DiT-based editors. We repurpose the RGB channels to encode the inputs, enabling seamless switching between instruction-guided edits and line-guided redrawing within a single input interface. To further specialize behavior across modes, we integrate a task-guided mixture-of-experts into LoRA layers, routing by text and visual cues to improve semantic controllability, structural fidelity, and style preservation. Extensive experiments show state-of-the-art results on both tasks, with superior instruction adherence and style/structure preservation compared to recent baselines. Together, our dataset and SketchAssist provide a practical, controllable assistant for sketch creation and revision.

Geometry-Aware Scene-Consistent Image Generation

We study geometry-aware scene-consistent image generation: given a reference scene image and a text condition specifying an entity to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output image that preserves the same physical environment as the reference scene while correctly generating the entity according to the spatial relation described in the text. Existing methods struggle to balance scene preservation with prompt adherence: they either replicate the scene with high fidelity but poor responsiveness to the prompt, or prioritize prompt compliance at the expense of scene consistency. To resolve this trade-off, we introduce two key contributions: (i) a scene-consistent data construction pipeline that generates diverse, geometrically-grounded training pairs, and (ii) a novel geometry-guided attention loss that leverages cross-view cues to regularize the model's spatial reasoning. Experiments on our scene-consistent benchmark show that our approach achieves better scene alignment and text-image consistency than state-of-the-art baselines, according to both automatic metrics and human preference studies. Our method produces geometrically coherent images with diverse compositions that remain faithful to the textual instructions and the underlying scene structure.

Reframing Music-Driven 2D Dance Pose Generation as Multi-Channel Image Generation

Recent pose-to-video models can translate 2D pose sequences into photorealistic, identity-preserving dance videos, so the key challenge is to generate temporally coherent, rhythm-aligned 2D poses from music, especially under complex, high-variance in-the-wild distributions. We address this by reframing music-to-dance generation as a music-token-conditioned multi-channel image synthesis problem: 2D pose sequences are encoded as one-hot images, compressed by a pretrained image VAE, and modeled with a DiT-style backbone, allowing us to inherit architectural and training advances from modern text-to-image models and better capture high-variance 2D pose distributions. On top of this formulation, we introduce (i) a time-shared temporal indexing scheme that explicitly synchronizes music tokens and pose latents over time and (ii) a reference-pose conditioning strategy that preserves subject-specific body proportions and on-screen scale while enabling long-horizon segment-and-stitch generation. Experiments on a large in-the-wild 2D dance corpus and the calibrated AIST++2D benchmark show consistent improvements over representative music-to-dance methods in pose- and video-space metrics and human preference, and ablations validate the contributions of the representation, temporal indexing, and reference conditioning. See supplementary videos at https://hot-dance.github.io

SpecServe: Efficient and SLO-Aware Large Language Model Serving with Adaptive Speculative Decoding

Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for drafting and LLMs for verification, has emerged as a compelling technique to accelerate LLM inference. However, existing speculative decoding solutions often fail to adapt to varying workloads and system environments, resulting in performance variability and SLO violations. In this paper, we introduce SpecServe, an efficient LLM inference system that dynamically adjusts speculative strategies according to real-time request loads and system configurations. SpecServe proposes a theoretical model to understand and predict the efficiency of speculative decoding across diverse scenarios. Additionally, it implements intelligent drafting and verification algorithms to guarantee optimal performance while achieving high SLO attainment. Experimental results on real-world LLM traces demonstrate that SpecServe consistently meets SLOs and achieves substantial performance improvements, yielding 1.14$\times$-14.3$\times$ speedups over state-of-the-art speculative inference systems.

SerialGen: Personalized Image Generation by First Standardization Then Personalization

In this work, we are interested in achieving both high text controllability and overall appearance consistency in the generation of personalized human characters. We propose a novel framework, named SerialGen, which is a serial generation method consisting of two stages: first, a standardization stage that standardizes reference images, and then a personalized generation stage based on the standardized reference. Furthermore, we introduce two modules aimed at enhancing the standardization process. Our experimental results validate the proposed framework's ability to produce personalized images that faithfully recover the reference image's overall appearance while accurately responding to a wide range of text prompts. Through thorough analysis, we highlight the critical contribution of the proposed serial generation method and standardization model, evidencing enhancements in appearance consistency between reference and output images and across serial outputs generated from diverse text prompts. The term "Serial" in this work carries a double meaning: it refers to the two-stage method and also underlines our ability to generate serial images with consistent appearance throughout.

RecurFormer: Not All Transformer Heads Need Self-Attention

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe that certain attention heads exhibit a distribution where the attention weights concentrate on tokens near the query token, termed as recency aware, which focuses on local and short-range dependencies. Leveraging this insight, we propose RecurFormer, a novel architecture that replaces these attention heads with linear recurrent neural networks (RNNs), specifically the Mamba architecture. This replacement reduces the cache size without evicting tokens, thus maintaining generation quality. RecurFormer retains the ability to model long-range dependencies through the remaining attention heads and allows for reusing pre-trained Transformer-based LLMs weights with continual training. Experiments demonstrate that RecurFormer matches the original model's performance while significantly enhancing inference efficiency. Our approach provides a practical solution to the computational challenges of Transformer-based LLMs inference, making it highly attractive for tasks involving long inputs.

IoT-LLM: Enhancing Real-World IoT Task Reasoning with Large Language Models

Large Language Models (LLMs) have demonstrated remarkable capabilities across textual and visual domains but often generate outputs that violate physical laws, revealing a gap in their understanding of the physical world. Inspired by human cognition, where perception is fundamental to reasoning, we explore augmenting LLMs with enhanced perception abilities using Internet of Things (IoT) sensor data and pertinent knowledge for IoT task reasoning in the physical world. In this work, we systematically study LLMs capability to address real-world IoT tasks by augmenting their perception and knowledge base, and then propose a unified framework, IoT-LLM, to enhance such capability. In IoT-LLM, we customize three steps for LLMs: preprocessing IoT data into formats amenable to LLMs, activating their commonsense knowledge through chain-of-thought prompting and specialized role definitions, and expanding their understanding via IoT-oriented retrieval-augmented generation based on in-context learning. To evaluate the performance, We design a new benchmark with five real-world IoT tasks with different data types and reasoning difficulties and provide the benchmarking results on six open-source and close-source LLMs. Experimental results demonstrate the limitations of existing LLMs with naive textual inputs that cannot perform these tasks effectively. We show that IoT-LLM significantly enhances the performance of IoT tasks reasoning of LLM, such as GPT-4, achieving an average improvement of 65% across various tasks against previous methods. The results also showcase LLMs ability to comprehend IoT data and the physical law behind data by providing a reasoning process. Limitations of our work are claimed to inspire future research in this new era.

The Llama 3 Herd of Models

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition

Recent achievements in language models have showcased their extraordinary capabilities in bridging visual information with semantic language understanding. This leads us to a novel question: can language models connect textual semantics with IoT sensory signals to perform recognition tasks, e.g., Human Activity Recognition (HAR)? If so, an intelligent HAR system with human-like cognition can be built, capable of adapting to new environments and unseen categories. This paper explores its feasibility with an innovative approach, IoT-sEnsors-language alignmEnt pre-Training (TENT), which jointly aligns textual embeddings with IoT sensor signals, including camera video, LiDAR, and mmWave. Through the IoT-language contrastive learning, we derive a unified semantic feature space that aligns multi-modal features with language embeddings, so that the IoT data corresponds to specific words that describe the IoT data. To enhance the connection between textual categories and their IoT data, we propose supplementary descriptions and learnable prompts that bring more semantic information into the joint feature space. TENT can not only recognize actions that have been seen but also ``guess'' the unseen action by the closest textual words from the feature space. We demonstrate TENT achieves state-of-the-art performance on zero-shot HAR tasks using different modalities, improving the best vision-language models by over 12%.