Trending Papers

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.

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.

The paper introduces Reward Forcing, which enhances video generation by updating sink tokens with EMA-Sink and using Rewarded Distribution Matching Distillation to prioritize dynamic content.

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.

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.

Semantic-First Diffusion (SFD) enhances image generation by asynchronously denoising semantic and texture latents, improving convergence and quality.

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

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.

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.

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

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

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.

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.

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.

WizardCoder, a Code LLM fine-tuned with complex instructions using Evol-Instruct, outperforms other open-source and closed LLMs on several code generation benchmarks.

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

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.

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.

OneThinker, an all-in-one multimodal reasoning model, unifies image and video understanding across various tasks using RL and demonstrates strong performance and knowledge transfer.

ARM-Thinker, an agentic reward model, uses external tools for verification, improving accuracy and interpretability in complex multimodal reasoning tasks.

STARFlow-V, a normalizing flow-based video generator, offers end-to-end learning, robust causal prediction, and high-quality video generation with practical sampling efficiency.

HunyuanOCR, a lightweight Vision-Language Model, achieves state-of-the-art performance in OCR tasks through a unified end-to-end architecture combining Vision Transformer and lightweight LLM, supported by data-driven and RL strategies.

MobiAgent, a comprehensive mobile agent system, achieves state-of-the-art performance in real-world mobile scenarios through its MobiMind-series models, AgentRR framework, and MobiFlow benchmarking suite, while also reducing data annotation costs.

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.

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.

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.

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.

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.

LatentMAS enables efficient, lossless collaboration among LLM agents in latent space, improving performance and reducing computational costs compared to text-based methods.

SteadyDancer, an Image-to-Video framework, ensures first-frame identity preservation and precise motion control through harmonized conditions, adaptive pose representation, and hierarchical training objectives.

GigaWorld-0 is a unified world model framework that integrates video generation and 3D modeling to produce high-quality, diverse, and physically plausible VLA data, enabling strong real-world performance in embodied AI without real-world training.

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.

PPTAgent, a two-stage approach, improves presentation generation by analyzing reference presentations and ensuring structural and content consistency, outperforming traditional methods across content, design, and coherence.

Light-X is a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control, outperforming existing methods in joint camera-illumination control and relighting.

CUDA-L2, a system combining large language models and reinforcement learning, optimizes Half-precision General Matrix Multiply CUDA kernels, achieving significant speedups over existing baselines in both offline and server modes.

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.

Stable Video Infinity generates infinite-length videos with high temporal consistency and controllable storylines by using Error-Recycling Fine-Tuning on the Diffusion Transformer.

Code2Video generates educational videos using a code-centric agent framework, improving coherence and interpretability compared to direct code generation.

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.

Step1X-Edit, an image editing model that uses multimodal LLM and diffusion image decoder, outperforms open-source models and approaches proprietary models in quality.

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

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

PosterCopilot enhances professional graphic design through a three-stage training strategy for LMMs, enabling geometrically accurate and aesthetically superior layouts with controllable iterative editing.

Tiny Recursive Model (TRM) achieves high generalization on complex puzzle tasks using a small, two-layer network with minimal parameters, outperforming larger language models.

PaperCoder is a multi-agent LLM framework that converts machine learning papers into functional code repositories through planning, analysis, and generation stages.

DEIMv2, an extended version of DEIM with DINOv3 features, achieves superior performance-cost trade-offs across diverse deployment scenarios, including GPU, edge, and mobile, by using Spatial Tuning Adapter and HGNetv2 with pruning.

EvoVLA, a self-supervised VLA framework, enhances long-horizon robotic manipulation by addressing stage hallucination through triplet contrastive learning, pose-based exploration, and long-horizon memory, achieving improved success rates and sample efficiency on both simulated and real-world tasks.

VLASH is an asynchronous inference framework for Vision-Language-Action models that achieves high speed and low latency without sacrificing accuracy, enabling precise robotic tasks like ping-pong and whack-a-mole.

A two-stage deterministic framework, Lotus-2, leverages diffusion models' world priors for high-quality geometric inference, achieving state-of-the-art results in monocular depth estimation and competitive surface normal prediction with limited training data.