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.

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.

Pixal3D introduces a pixel-aligned 3D generation approach that addresses fidelity issues in 3D asset creation by establishing direct pixel-to-3D correspondences through back-projection conditioning.

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.

DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.

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.

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.

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.

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.

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

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.

A novel framework for improving large language model performance through textual frequency analysis, including laws, distillation, and curriculum training approaches.

Flow-OPD addresses limitations in Flow Matching text-to-image models through a two-stage alignment approach combining on-policy distillation and manifold anchor regularization, achieving significant improvements in generation quality and alignment metrics.

RoboMemArena presents a large-scale robotic memory benchmark with diverse tasks and real-world evaluation, while PrediMem demonstrates improved memory management through a dual-system vision-language architecture with predictive coding.

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.

HumanNet presents a large-scale human-centric video dataset with rich annotations for embodied intelligence, demonstrating that egocentric human video can effectively replace robot data for training vision-language-action models.

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

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.

MiniCPM-o 4.5 enables real-time full-duplex multimodal interaction through Omni-Flow, a unified streaming framework that aligns inputs and outputs temporally for simultaneous perception and response.

MiniCPM-V 4.5, a 8B parameter multimodal large language model, achieves high performance and efficiency through a unified 3D-Resampler architecture, a unified learning paradigm, and a hybrid reinforcement learning strategy.

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.

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.

World models as predictive representations of environmental dynamics have become essential for robot learning, supporting policy learning, planning, and simulation across various embodied applications.

NanoResearch is a multi-agent framework that enhances research automation through personalized assistance by accumulating reusable skills, maintaining user-specific experience, and internalizing implicit preferences through co-evolving components.

LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.

MACE-Dance is a music-driven dance video generation framework that combines cascaded Mixture-of-Experts with diffusion models and specialized training strategies to achieve high-quality visual appearance and realistic human motion.

UI-TARS-2, a native GUI-centered agent model, addresses challenges in data scalability, multi-turn reinforcement learning, and environment stability, achieving significant improvements over its predecessor and strong baselines across various benchmarks.

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

A novel approach decouples auxiliary training objectives from standard supervised finetuning to enhance model capabilities while reducing computational overhead through capability vector merging and orthogonal regularization.

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.

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.

A lightweight memory mechanism called δ-mem enhances large language models by augmenting a frozen attention backbone with a compact associative memory state that provides low-rank corrections to attention computations.

A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities.

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.

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.

rStar enhances small language models' reasoning capabilities through a self-play mutual generation-discrimination process without fine-tuning, improving accuracy across various reasoning tasks.

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.

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

A method using 3D Gaussians for scene representation and optimized rendering allows high-quality, real-time novel-view synthesis at 1080p resolution.

EvoScientist is an adaptive multi-agent framework that enhances scientific discovery by continuously learning from past interactions through persistent memory modules.

HyperEyes is a parallel multimodal search agent that enables concurrent entity searches while optimizing inference efficiency through dual-grained reinforcement learning and a specialized benchmark for evaluating both accuracy and efficiency.

MolmoAct2 presents an open-action reasoning model for robotics that improves upon previous systems through specialized vision-language-model backbones, new datasets, open-weight action tokenizers, architectural redesign for continuous-action prediction, and adaptive reasoning for reduced latency.

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

AutoTTS automates test-time scaling strategy discovery by formulating it as controller synthesis over reasoning trajectories and probe signals, achieving improved accuracy-cost tradeoffs with minimal computational overhead.

OpenGame is an open-source agentic framework for end-to-end web game creation that uses specialized code models and evaluation benchmarks to overcome challenges in interactive application development.

Research investigates latent manifold properties for diffusion models and proposes a Prior-Aligned AutoEncoder that explicitly optimizes latent space structure for improved generative modeling.

LeWorldModel presents a stable end-to-end JEPA framework that trains efficiently from raw pixels using minimal loss terms while maintaining competitive performance in control tasks and encoding meaningful physical structures.

Direct corpus interaction enables more effective agentic search by allowing agents to query raw text directly, outperforming traditional retrieval methods in complex tasks.