Trending Papers

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.

Agents' Last Exam (ALE) is a benchmark for evaluating AI agents on long-term, economically valuable real-world tasks across 13 industry clusters with 1K+ tasks, revealing significant gaps between benchmark performance and practical deployment.

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.

DRPO improves LLM reinforcement learning stability by replacing hard masks with smooth regularization that provides continuous gradient corrections beyond trust-region boundaries.

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

SCAIL-2 enables end-to-end character animation by directly transferring motion from driving videos without intermediate representations, using unified task decomposition and synthetic data generation.

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.

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.

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.

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.

Latent spatial memory for video world models stores 3D scene information directly in diffusion latent space, eliminating pixel-space reconstruction overhead and achieving faster generation with reduced memory usage.

A 2B-parameter continuous autoregressive text-to-speech model trained on a multilingual corpus achieves state-of-the-art performance on multiple benchmarks while enabling efficient low-latency speech generation through specialized distillation techniques.

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.

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

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.

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.

A 20B search agent trained with reinforcement learning within a stateful search framework demonstrates superior retrieval performance across multiple domains by separating semantic decision-making from environmental bookkeeping.

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.

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.

A self-improving AI framework simultaneously updates both model weights and task-specific agent architecture through a language-model feedback agent across legal classification, GPU optimization, and biological data denoising tasks.

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.

WorldOlympiad presents a comprehensive benchmark for evaluating video-based world models across physical faithfulness, geometric consistency, and interaction fidelity, revealing significant gaps in current generative models' capabilities.

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.

Role-Agent framework enables LLM agents to function as both agent and environment through bootstrapped co-evolution, improving performance via environment-aware reasoning and targeted practice.

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.

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.

MMAE presents a comprehensive benchmark for instruction-based audio editing across multiple modalities and complexity levels, revealing significant gaps in current model capabilities.

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

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

OmniGameArena presents a unified benchmark for evaluating vision-language model agents in diverse game settings with a reflection-based improvement protocol that tracks performance evolution and skill generalization.

ABot-Earth 0.5 generates realistic 3D environments from satellite imagery using 3D Gaussian Splatting representation, enabling fast synthesis and real-time visualization for Embodied AI applications.

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

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.

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.

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.

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.

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.

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.

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.

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.

SkillClaw enables collective skill evolution in multi-user LLM agent systems by aggregating user interactions to autonomously update and improve reusable skills across the ecosystem.

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.

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

The Unitree G1 humanoid robot is vulnerable to BLE provisioning protocol exploits, exfiltrates sensor data, and can be repurposed for active cyber operations, highlighting the need for improved security standards in commercial robotics.

Autoregressive diffusion method for video-to-video lip synchronization achieves real-time performance through distillation and optimized inference schedules.

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.

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.

Unified vision-language models treat understanding and generation as integrated processes rather than separate tasks, demonstrating strong performance across multiple multimodal capabilities including image synthesis and action reasoning.

QGF is an RL algorithm that improves policies at test time by using a value gradient to guide a pre-trained flow policy, avoiding training-time instability while maintaining competitive performance.

UniSHARP extends SHARP for universal monocular rendering across different camera systems by aligning images in an omnidirectional latent space through joint feature and Gaussian space alignment.