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.

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.

TriSplat is a feed-forward 3D reconstruction network that uses oriented triangle primitives to directly generate simulation-ready meshes from single images, bypassing expensive post-processing steps.

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.

SANA-Video, a small diffusion model, efficiently generates high-resolution, high-quality videos with strong text-video alignment using linear attention and a constant-memory KV cache, achieving competitive performance at a lower cost and faster speed.

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.

LongLive-2.0 presents an NVFP4-based parallel infrastructure for long video generation that addresses training and inference bottlenecks through sequence-parallel autoregressive training and diffusion model tuning.

Mega-ASR framework improves robustness in real-world speech recognition through compound-data construction and progressive acoustic-to-semantic optimization techniques.

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.

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.

Lance is a unified multimodal model that combines understanding, generation, and editing capabilities for images and videos through collaborative multi-task training and a dual-stream architecture.

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

WBench presents a comprehensive multi-turn benchmark for evaluating interactive world models across five dimensions using 289 test cases and 1,058 interaction turns with diverse scenarios and interaction types.

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

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.

Lens is a compact 3.8B-parameter text-to-image model achieving superior performance with reduced training compute through dense caption datasets, multi-resolution batching, efficient architecture, and optimization techniques.

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

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.

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.

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.

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.

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.

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.

ParaVT enables parallel video tool calling through multi-agent reinforcement learning, addressing limitations of sequential approaches and improving long-video understanding performance.

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.

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.

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.

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.

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.

Latent-to-Pixel transfer paradigm efficiently leverages pre-trained latent diffusion models to create pixel-space models with minimal training overhead and high-resolution generation capabilities.

Stable Audio 3 enables efficient variable-length audio generation and editing through latent diffusion models operating on a semantic-acoustic autoencoder, with adversarial post-training for improved speed and quality.

Gated DeltaNet-2 improves upon existing linear attention models by separating erase and write operations through distinct channel-wise gates, achieving superior performance in long-context language modeling and retrieval tasks.

PhysX-Omni presents a unified framework for generating simulation-ready 3D assets with physical properties across multiple categories using a novel geometry representation and evaluation benchmarks.

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

A Hierarchical Recurrent Model architecture with specialized training on instruction-response pairs achieves competitive language modeling performance with significantly reduced computational requirements compared to traditional Transformer-based approaches.

A Director-Reviewer-Reflector agent named PhotoFlow enables language-conditioned virtual photography by combining 3D spatial understanding with aesthetic judgment in arbitrary Blender scenes.

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.

OpenGuardrails is an open-source project providing a unified model for content-safety and model-manipulation detection, along with a separate NER pipeline for data-leakage identification, offering enterprise-grade deployment options.

GEPA, a prompt optimizer using natural language reflection, outperforms RL methods like GRPO and MIPROv2 with fewer rollouts by learning high-level rules from trial and error.

Native multimodal modeling advances beyond traditional fusion approaches by integrating modalities inherently within a unified transformer framework, enabling seamless understanding and generation across diverse input-output configurations.

SCOPE enables precise action response in FPS games by conditioning transformer blocks in video diffusion models to separate in-scope from out-of-scope visual effects without segmentation labels.

RTDMD is a two-stage framework that combines distribution matching distillation with reward-guided reinforcement learning to improve few-step image generation alignment with human preferences.

World Action Models unify predictive state modeling with action generation for embodied policy learning, forming a cohesive framework for understanding environment dynamics and action prediction.

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.

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.

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