Trending Papers

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.

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.

HY-World 2.0 is a multi-modal world model framework that generates high-fidelity 3D Gaussian Splatting scenes from diverse inputs using specialized modules for panorama generation, trajectory planning, world expansion, and composition, along with an enhanced rendering platform for interactive 3D exploration.

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.

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

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

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

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.

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.

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

A self-distillation framework converts implicit 3D knowledge from video diffusion models into an explicit 3D Gaussian Splatting representation, enabling 3D scene generation from text or images.

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.

The study analyzes Claude Code's architecture, identifying five motivating human values and tracing them through thirteen design principles to specific implementation choices, including a core while-loop architecture and supporting systems for safety, context management, and extensibility.

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.

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.

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.

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.

ClawGUI presents an open-source framework that addresses key challenges in GUI agent development through unified reinforcement learning, standardized evaluation, and cross-platform deployment capabilities.

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.

A retrieval-augmented LLM framework improves financial sentiment analysis by tuning LLMs for sentiment prediction and augmenting them with external context, outperforming traditional models and other LLMs.

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.

Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference 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.

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.

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.

The AI Scientist-v2 autonomously proposes hypotheses, performs experiments, analyzes data, and writes peer-reviewed scientific papers, marking the first fully AI-generated paper accepted by a conference.

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

SpatialEvo is a self-evolving framework for 3D spatial reasoning that uses deterministic geometric environments to provide objective feedback, enabling efficient training without relying on model consensus.

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.

GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering.

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.

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.

Feed-forward 3D reconstruction methods map images to 3D representations in a single forward pass, enabling efficient and generalizable reconstruction across scenes through shared architectural patterns and model design strategies.

_paperbanana is an agentic framework that automates the creation of publication-ready academic illustrations using advanced vision-language models and image generation techniques.

Bitnet.cpp enhances edge inference for ternary LLMs using a novel mixed-precision matrix multiplication library, achieving significant speed improvements over baselines.

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.

Being-H0.5 is a Vision-Language-Action model that enables robust cross-embodiment generalization through human-centric learning and a Mixture-of-Transformers architecture with specialized embodiment handling.

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.

OmniShow is an end-to-end framework for human-object interaction video generation that effectively integrates multiple modalities through unified conditioning and attention mechanisms while addressing data scarcity via decoupled training strategies.

GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.

Habitat-GS extends Habitat-Sim by integrating 3D Gaussian Splatting for photorealistic rendering and gaussian avatars for dynamic human modeling, enabling improved agent generalization and human-aware navigation in embodied AI.

LTX-2 is an open-source audiovisual diffusion model that generates synchronized video and audio content using a dual-stream transformer architecture with cross-modal attention and classifier-free guidance.

OmniWeaving is an open-source video generation model that unifies multimodal inputs and complex reasoning capabilities through large-scale pretraining and intelligent agent inference.

HY-Embodied-0.5 is a foundation model family for embodied agents featuring Mixture-of-Transformers architecture and iterative post-training for enhanced visual perception and reasoning capabilities.

CutClaw is an autonomous multi-agent framework that uses multimodal language models to automatically edit long video footage into rhythmic, narratively consistent short videos with synchronized audio and visual elements.

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.

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.

VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.

On-policy distillation dynamics in large language models depend on compatible thinking patterns between teacher and student models, with successful distillation characterized by alignment on high-probability tokens and requiring teachers to provide novel capabilities beyond student training data.