Trending Papers

PersonaLive is a diffusion-based framework for real-time portrait animation that enhances speed and efficiency through multi-stage training, hybrid implicit signals, appearance distillation, and autoregressive micro-chunk streaming.

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.

The study reveals that in text-to-image generation, CFG Augmentation is the primary driver of few-step distillation in Distribution Matching Distillation (DMD), while the distribution matching term acts as a regularizer.

Z-Image, a 6B-parameter Scalable Single-Stream Diffusion Transformer (S3-DiT) model, achieves high-performance image generation with reduced computational cost, offering sub-second inference and compatibility with consumer hardware.

V-RGBX is an end-to-end framework for intrinsic-aware video editing that combines video inverse rendering, photorealistic synthesis, and keyframe-based editing to produce consistent and physically plausible edits.

Promptomatix automates prompt optimization for Large Language Models, improving performance and efficiency across various tasks.

A large-scale dataset collection, The Well, provides diverse numerical simulations for benchmarking machine learning models in physical systems simulation.

A novel GPT-based model, OmniFlatten, enables real-time natural full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original model's architecture.

Wan-Move enhances motion control in video generative models by integrating motion-aware features into latent space, enabling high-quality and scalable video synthesis.

SHARP synthesizes photorealistic views from a single image using a 3D Gaussian representation, achieving state-of-the-art results with rapid processing.

Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.

MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

MinerU is an open-source tool that enhances document content extraction using fine-tuned models and pre/postprocessing rules across diverse document types.

PaddleOCR-VL, a vision-language model combining NaViT-style dynamic resolution and ERNIE, achieves state-of-the-art performance in document parsing and element recognition with high efficiency.

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.

SVG-T2I, a scaled SVG framework, enables high-quality text-to-image synthesis directly in the Visual Foundation Model feature domain, achieving competitive performance in generative tasks.

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

IndexTTS, an enhanced text-to-speech system combining XTTS and Tortoise models, offers improved naturalness, enhanced voice cloning, and controllable usage through hybrid character-pinyin modeling and optimized vector quantization.

LlamaFactory is a unified framework enabling efficient fine-tuning of large language models across various tasks using a web-based user interface.

A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio.

Live Avatar uses a 14-billion-parameter diffusion model with Timestep-forcing Pipeline Parallelism and Rolling Sink Frame Mechanism to achieve real-time, high-fidelity avatar generation.

Fast-FoundationStereo achieves real-time zero-shot stereo generalization by combining knowledge distillation, blockwise neural architecture search, and structured pruning.

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

GigaBrain-0, a VLA foundation model, uses world model-generated data to enhance cross-task generalization and policy robustness, improving real-world performance on complex manipulation tasks.

PyTorch Fully Sharded Data Parallel (FSDP) enables efficient and scalable training of large models across hardware configurations.

The PyTorch distributed data parallel module optimizes large-scale model training using techniques like gradient bucketing, computation-communication overlap, and selective synchronization to achieve near-linear scalability.

InternVL3 is a multimodal pre-trained language model that jointly learns from both multimodal data and text, improving performance and scalability through advanced techniques and setting a new state-of-the-art in multimodal tasks.

SAM 3D is a generative model that reconstructs 3D objects from single images using a multi-stage training framework that includes synthetic pretraining and real-world alignment, achieving high performance in human preference tests.

TwinFlow is a 1-step generative model framework that enhances inference efficiency without requiring fixed pretrained teacher models or standard adversarial networks, achieving high performance on text-to-image tasks and scaling efficiently.

RealGen is a photorealistic text-to-image framework that uses an LLM for prompt optimization and a diffusion model for image generation, enhanced by a Detector Reward mechanism and RealBench for automated evaluation.

Visionary is an open web-native platform enabling real-time rendering of 3D Gaussian Splatting and meshes with efficient GPU-based inference, supporting dynamic content and generative models.

PaperDebugger is an in-editor academic writing assistant that integrates large language models, enabling direct interaction within LaTeX editors for document state management, revision, and literature search.

AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment.

Depth Anything 3 (DA3) uses a plain transformer for geometry prediction from visual inputs, achieving state-of-the-art results in camera pose estimation, any-view geometry, visual rendering, and monocular depth estimation.

MeshSplatting, a mesh-based reconstruction method, enhances novel view synthesis by optimizing geometry and appearance through differentiable rendering, improving quality and efficiency over existing techniques.

DeepAnalyze-8B, an agentic LLM, autonomously completes the data science pipeline from raw data to research reports using curriculum-based training and data-grounded trajectory synthesis.

Flawed-Aware Policy Optimization (FAPO) enhances reinforcement learning with verifiable rewards by penalizing flawed-positive rollouts, improving reasoning capability and training stability in large language models.

LucidFlux, a caption-free UIR framework using a diffusion transformer, achieves robust image restoration through adaptive conditioning and SigLIP features without text prompts.

Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases.

CLaRa enhances retrieval-augmented generation by introducing unified embedding-based compression and joint optimization, achieving state-of-the-art performance in QA benchmarks.

A framework called Easy Dataset synthesizes fine-tuning data from unstructured documents using a GUI and LLMs, improving domain-specific performance of LLMs while maintaining general knowledge.

NEO, a novel family of native Vision-Language Models, addresses fundamental constraints and integrates vision and language within a unified framework, achieving competitive performance with limited data.

HunyuanVideo 1.5 is a lightweight video generation model with state-of-the-art visual quality and motion coherence, using a DiT architecture with SSTA and an efficient video super-resolution network.

RF-DETR, a light-weight detection transformer, uses weight-sharing NAS to optimize accuracy and latency for real-time detection across diverse datasets.

DeepSeek-V3 is a parameter-efficient Mixture-of-Experts language model using MLA and DeepSeekMoE architectures, achieving high performance with efficient training and minimal computational cost.

DeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing.

mmGRPO, a multi-module extension of GRPO, enhances accuracy in modular AI systems by optimizing LM calls and prompts across various tasks.

Agent Lightning is a flexible RL framework for training LLMs in various agents, using a hierarchical RL algorithm and decoupling execution from training to handle complex interactions.