Trending Papers

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

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.

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.

Multi-agent collaboration networks enhance collective intelligence, outperforming baselines across various topologies and showing emergent abilities earlier than neural scaling laws suggest.

A centralized orchestrator dynamically directs LLM agents via reinforcement learning, achieving superior multi-agent collaboration in varying tasks with reduced computational costs.

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.

Cross-Team Collaboration improves software quality by enabling multiple LLM agent teams to propose and communicate decisions.

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.

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.

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

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.

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

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.

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.

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.

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.

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.

LingBot-World is an open-source world simulator with high-fidelity dynamics, long-term memory capabilities, and real-time interactivity for diverse 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.

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.

MinerU is an open-source tool that enhances document content extraction using fine-tuned models and pre/postprocessing rules across diverse document types.

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.

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.

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

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.

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.

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.

Offline knowledge construction through structured methodological graphs enables more reliable and scalable autonomous scientific discovery by reducing reliance on real-time literature 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.

UI-TARS, a native GUI agent model using screenshots as input, outperforms commercial models in various benchmarks through enhanced perception, unified action modeling, system-2 reasoning, and iterative training with reflective online traces.

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

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.

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.

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

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.

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.

MotionCrafter is a video diffusion framework that jointly reconstructs 4D geometry and estimates dense motion using a novel joint representation and 4D VAE architecture.

A framework called Easy Dataset synthesizes fine-tuning data from unstructured documents using a GUI and LLMs, improving domain-specific performance of LLMs while maintaining general knowledge.

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.

Researchers introduce a new video understanding task and benchmark that evaluates models' ability to learn from few-shot demonstrations, along with a specialized MLLM architecture trained using a two-stage approach combining video supervision and preference optimization.

Transformer Explainer is an interactive visualization tool that allows non-experts to understand the inner workings of the GPT-2 model through real-time experimentation and visualization in a web browser.

DeepSeek-OCR 2 introduces DeepEncoder V2 that dynamically reorders visual tokens based on semantic content, enabling more human-like causal reasoning in 2D image understanding through cascaded 1D causal structures.

Vision-DeepResearch introduces a multimodal deep-research paradigm enabling multi-turn, multi-entity, and multi-scale visual and textual search with deep-research capabilities integrated through cold-start supervision and reinforcement learning.

The study reveals that in text-to-image generation, CFG Augmentation is the primary driver of few-step distillation in Distribution Matching Distillation (DMD), while the distribution matching term acts as a regularizer.

Z-Image, a 6B-parameter Scalable Single-Stream Diffusion Transformer (S3-DiT) model, achieves high-performance image generation with reduced computational cost, offering sub-second inference and compatibility with consumer hardware.

A human-curated benchmark (CodeArena) and a large synthetic instruction corpus (SynCode-Instruct) are introduced to evaluate code LLMs based on human preference alignment, revealing performance differences between open-source and proprietary models.

Researchers address the modality gap in multimodal learning by proposing a fixed-frame theory and a training-free alignment method that enables efficient scaling of multimodal models using unpaired data.

InternAgent-1.5 is a unified system for autonomous scientific discovery that integrates computational modeling and experimental research through coordinated subsystems for generation, verification, and evolution.

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.

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.