Trending Papers

PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6.

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.

Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.

SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.

Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset.

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

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.

GRAIL generates diverse humanoid manipulation and locomotion data through 3D asset composition and video foundation models, enabling effective sim-to-real transfer for robot control.

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.

OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks.

EverMemOS presents a self-organizing memory system for large language models that processes dialogue streams into structured memory cells and scenes to enhance long-term interaction capabilities.

Mixture of vision encoders and resolutions in multimodal large language models improves performance through concatenation of visual tokens and a Pre-Alignment mechanism, leading to superior results on benchmarks.

PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache.

ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.

Memanto presents a universal memory layer for agentic AI that eliminates computational overhead of hybrid semantic graph architectures through a typed semantic memory schema and information-theoretic search engine.

Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.

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.

MOSS-TTS is a speech generation model using discrete audio tokens and autoregressive modeling with capabilities for voice cloning, pronunciation control, and long-form generation across multiple languages.

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

AI-Trader presents the first fully automated live benchmark for evaluating large language models in financial decision-making across multiple markets with autonomous information processing.

KVarN is a calibration-free KV-cache quantizer that uses Hadamard rotation and dual-scaling variance normalization to reduce error accumulation during autoregressive decoding in large language models.

SmolDocling is a compact vision-language model that performs end-to-end document conversion with robust performance across various document types using 256M parameters and a new markup format.

Person-grounded AI skills are automatically distilled from heterogeneous traces into inspectable, correctable packages that capture both capabilities and behavioral patterns.

A unified streaming audio model is developed that combines offline task execution with real-time audio instruction following through an end-to-end framework supporting multiple audio interaction capabilities.

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.

LLM-based agents perform poorly on VibeSearch benchmark, which evaluates multi-turn dialogue search scenarios reflecting real user-agent collaboration rather than traditional single-turn query tasks.

GenericAgent is a self-evolving large language model agent system that maximizes context information density through hierarchical memory, reusable SOPs, and efficient compression to overcome long-horizon limitations.

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.

PDFMathTranslate enables layout-preserving scientific document translation using large language models and precise layout detection, offering improved precision, flexibility, and efficiency.

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.

Vision Language Models can be adapted for 3D understanding tasks through simple architectural modifications and text-based training, achieving performance comparable to specialized vision models without requiring complex designs or extensive data augmentation.

Stable-worldmodel provides a modular and standardized research framework for developing and evaluating world models with controllable environmental factors for robustness and continual learning applications.

MobileGym presents a browser-based mobile environment enabling deterministic evaluation and scalable reinforcement learning through JSON-based state management and parallel execution.

YOLO26 addresses real-time vision challenges through a unified model family with NMS-free inference, improved training strategies, and multi-task capabilities spanning detection, segmentation, and pose estimation.

Echo Infinity enables real-time infinite video generation using learnable evolving memory and unified relative RoPE to overcome limitations in existing autoregressive methods.

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

AgentFounder, a deep research agent model incorporating Agentic Continual Pre-training, achieves state-of-the-art performance in agentic tasks while maintaining strong tool-use ability.

WebShaper, a formalization-driven framework, synthesizes information-seeking datasets using set theory and Knowledge Projections to enhance reasoning structure and achieve top performance in open-sourced benchmarks.

LoomVideo presents an efficient 5B-parameter unified architecture for video generation and editing that reduces computational overhead through novel conditioning mechanisms and multi-modal alignment techniques.

WebWatcher, a multimodal agent with enhanced visual-language reasoning, outperforms existing agents in complex visual and textual information retrieval tasks using synthetic trajectories and reinforcement learning.

DataFlow is an LLM-driven data preparation framework that enhances data quality and reproducibility for various tasks, improving LLM performance with automatically generated pipelines.

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.

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

A comprehensive framework is presented for converting bidirectional video diffusion models into real-time interactive world models with controllable, causal, and low-latency capabilities through fine-tuning and distillation techniques.

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

OVO-S-Bench presents a comprehensive benchmark for evaluating streaming spatial intelligence in multimodal language models through human-annotated questions spanning multiple abstraction levels.

AutoFigure-Edit is an end-to-end system that generates editable scientific illustrations from text descriptions and reference images, supporting flexible style adaptation and efficient refinement.

A promptable 3D human mesh recovery model using a novel parametric representation and encoder-decoder architecture achieves state-of-the-art performance with strong generalization across diverse conditions.

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

AutoResearchClaw is a multi-agent autonomous research system that improves scientific discovery through structured debate, self-healing execution, verifiable reporting, human collaboration, and evolutionary learning, outperforming previous systems on a benchmark while maintaining human oversight.