Trending Papers

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.

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

Monolingual ASR models trained on a balanced mix of high-quality, pseudo-labeled, and synthetic data outperform multilingual models for small model sizes, achieving superior error rates and enabling on-device ASR for underrepresented languages.

Moonshine, an encoder-decoder transformer architecture for speech recognition, uses Rotary Position Embedding, reducing compute requirements without decreasing accuracy.

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.

SceneSmith is a hierarchical agentic framework that generates simulation-ready indoor environments from natural language prompts through multiple stages involving VLM agents and integrated asset generation techniques.

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.

Agent Lightning is a flexible RL framework for training LLMs in various agents, using a hierarchical RL algorithm and decoupling execution from training to handle complex interactions.

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.

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

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.

IMO-Bench, a suite of advanced reasoning benchmarks, evaluates mathematical reasoning capabilities of foundation models using IMO-level problems and detailed grading guidelines, achieving gold-level performance with Gemini Deep Think.

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.

SkillRL enables LLM agents to improve through hierarchical skill discovery and recursive policy evolution, achieving superior performance on complex tasks while reducing computational overhead.

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.

A suite of open-source music foundation models is introduced, featuring components for audio-text alignment, lyric recognition, music coding, and large language model-based song generation with controllable attributes and scalable parameterization.

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts. While recent agentic frameworks improve alpha mining automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors through trajectory-level mutation and crossover operations. QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across mining iterations. During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code, while constraining the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on the China Securities Index 300 (CSI 300) demonstrate consistent gains over strong baseline models and prior agentic systems. When utilizing GPT-5.2, QuantaAlpha achieves an Information Coefficient (IC) of 0.1501, with an Annualized Rate of Return (ARR) of 27.75% and a Maximum Drawdown (MDD) of 7.98%. Moreover, factors mined on CSI 300 transfer effectively to the China Securities Index 500 (CSI 500) and the Standard & Poor's 500 Index (S&P 500), delivering 160% and 137% cumulative excess return over four years, respectively, which indicates strong robustness of QuantaAlpha under market distribution shifts.

A lightweight 5B unified multimodal model achieves competitive performance through hierarchical feature extraction, learnable think tokens, and progressive training strategies including alignment pre-training, joint supervised fine-tuning, and reinforcement learning with MR-GRPO.

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.

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.

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.

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.

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.

A fully end-to-end Transformer-based audio tokenizer architecture achieves high-fidelity reconstruction across diverse audio domains and enables superior text-to-speech and automatic speech recognition performance.

UI-Venus-1.5 is a unified GUI agent with improved performance through mid-training stages, online reinforcement learning, and model merging techniques.

EvoCorps is an evolutionary multi-agent framework that proactively addresses polarization in online discourse through dynamic social game coordination and closed-loop learning for real-time discourse governance.

MOVA is an open-source model that generates synchronized audio-visual content using a Mixture-of-Experts architecture with 32 billion parameters, supporting image-text to video-audio generation tasks.

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.

A unified Vision-Language Model, dots.ocr, achieves state-of-the-art performance on document layout parsing by jointly learning layout detection, text recognition, and relational understanding, validated on OmniDocBench and XDocParse benchmarks.

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

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.

Large language model agents trained in synthetic environments with code-driven simulations and database-backed state transitions demonstrate superior out-of-distribution generalization compared to traditional benchmark-specific approaches.

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.

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

IndexTTS, an enhanced text-to-speech system combining XTTS and Tortoise models, offers improved naturalness, enhanced voice cloning, and controllable usage through hybrid character-pinyin modeling and optimized vector quantization.

pySLAM is an open-source framework supporting Visual SLAM with monocular, stereo, and RGB-D cameras, incorporating classical and modern features, loop closure methods, volumetric reconstruction, and depth prediction models.

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

A vision-language-action model enhanced with world model-based reinforcement learning demonstrates improved performance and long-horizon execution capabilities for robotic manipulation tasks.

Researchers developed a discrete audio codec called ReasoningCodec that separates audio into reasoning and reconstruction tokens for improved understanding and generation, and created UniAudio 2.0, a unified autoregressive model trained on large-scale text and audio data that shows strong performance across various audio tasks and generalizes well in few-shot and zero-shot scenarios.

RPG-Encoder framework transforms repository comprehension and generation into a unified cycle by encoding code into high-fidelity Repository Planning Graph representations that improve understanding and reconstruction accuracy.

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.

ALMA is a framework that uses meta-learning to automatically discover memory designs for agentic systems, enabling continual learning without human engineering across diverse domains.

MolmoSpaces presents an open ecosystem with diverse indoor environments and annotated objects for large-scale robot policy benchmarking across multiple tasks and simulators.

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.

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.

Single-stream Policy Optimization (SPO) improves policy-gradient training for Large Language Models by eliminating group-based issues and providing a stable, low-variance learning signal, leading to better performance and efficiency.

Code2World enables autonomous GUI agents to predict next visual states through renderable code generation, achieving high visual fidelity and structural controllability while improving navigation performance.

Kimi K2.5 is an open-source multimodal agentic model that enhances text and vision processing through joint optimization techniques and introduces Agent Swarm for parallel task execution.

Step 3.5 Flash is a sparse Mixture-of-Experts model that achieves frontier-level agentic intelligence through efficient parameter utilization and optimized attention mechanisms, demonstrating strong performance across multiple benchmarks.

WMSS is a post-training paradigm that uses weak model checkpoints to identify and fill learning gaps, enabling continued improvement beyond conventional saturation points in large language models.