Trending Papers

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

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 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.

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.

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.

PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6.

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.

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.

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.

FastContext separates repository exploration from code solving in LLM agents using specialized exploration models that reduce token consumption and improve resolution rates.

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.

LMCACHE enables efficient KV cache management for large language models by storing caches outside GPU memory, supporting cache reuse across queries and inference engines while achieving significant throughput improvements.

A vision-language model operates continuously in real-time, making autonomous decisions about when to respond or delegate, enabling interactive systems that perceive and act upon environmental changes without user prompting.

VibeThinker-3B demonstrates that compact models can achieve state-of-the-art performance on verifiable reasoning tasks through specialized training techniques, challenging conventional scaling assumptions.

A lightweight image inpainting framework achieves high-fidelity results with significantly reduced parameters and inference time through novel local-global interaction blocks and adaptive distillation strategies.

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.

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

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.

PlanBench-XL evaluates large language model agents' ability to plan and adapt in complex tool-rich environments with limited visibility and dynamic disruptions.

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.

MeshFlow generates triangle meshes directly using equivariant optimal-transport flow matching models with improved inference speed over autoregressive methods.

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.

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.

Agentic Data Tailoring paradigm uses learnable data processing to structure high-entropy multimodal streams, with DataClaw_0-9B model achieving robust alignment through SFT and GRPO on a novel benchmark.

YOLO26 addresses real-time vision challenges through a unified model family with NMS-free inference, improved training strategies, and multi-task capabilities spanning detection, segmentation, and pose estimation.

PDFMathTranslate enables layout-preserving scientific document translation using large language models and precise layout detection, offering improved precision, flexibility, and efficiency.

EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single performance scores.

UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types.

RF-DETR, a light-weight detection transformer, uses weight-sharing NAS to optimize accuracy and latency for real-time detection across diverse datasets.

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.

mmGRPO, a multi-module extension of GRPO, enhances accuracy in modular AI systems by optimizing LM calls and prompts across various tasks.

Cosmos 3 is an omnimodal world model that processes and generates multiple data types through a unified mixture-of-transformers architecture, achieving state-of-the-art performance in various understanding and generation tasks.

An AI framework called Arbor enables autonomous scientific research by combining strategic coordination, isolated hypothesis testing, and a persistent knowledge tree to iteratively improve research outcomes across multiple domains.

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.

World Action Models are predictive-action systems that generate future states for decision-making, with designs balancing representational richness against computational constraints.

RecursiveMAS extends recursive scaling principles from single models to multi-agent systems, enabling collaborative reasoning through iterative latent-space computations with improved efficiency and accuracy.

Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.

SCAIL-2 enables end-to-end character animation by directly transferring motion from driving videos without intermediate representations, using unified task decomposition and synthetic data generation.

Person-grounded AI skills are automatically distilled from heterogeneous traces into inspectable, correctable packages that capture both capabilities and behavioral patterns.

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 RL training approach for terminal agents achieves superior performance using a simplified recipe and expanded dataset, enabling effective training with fewer parameters than previous methods.

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.

DreamX-World 1.0 is a interactive text/image-to-video model that generates long-horizon content with camera control and scene persistence using specialized encoding, training techniques, and optimization methods.

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.

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

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.

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.

Memanto presents a universal memory layer for agentic AI that eliminates computational overhead of hybrid semantic graph architectures through a typed semantic memory schema and information-theoretic search engine.