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.

YuE, a family of open foundation models based on LLaMA2, can generate long-form music with aligned lyrics, coherent structure, and appropriate accompaniment using innovative techniques in next-token prediction, conditioning, and pre-training.

Atria Dawn Preview is a foundation agentic language model trained through verified tool interactions that achieves strong benchmark results and demonstrates a shift toward human-AI project-level collaboration in scientific research.

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.

ZGCM-1 is a 7B open foundation model that combines internal reasoning with external tool use, trained via efficient architecture-system co-design, progressive long-context scaling, and autonomous agent workflows to achieve strong reasoning and efficiency.

Transformers library provides state-of-the-art Transformer architectures and pretrained models for natural language processing tasks with a unified API and emphasis on extensibility and robust deployment.

AutoResearch is a two-stage autonomous system that grounds research ideas through integrated generation and evidence-based execution to improve experimental reliability and measurable outcomes.

RSIAgent is a training-free multi-agent framework that enables recursive self-improvement via autonomous memory construction and broad-then-deep exploration to adapt digital agents to new environments.

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.

Apodex 1.1 improves sustained, verifiable progress on complex real-world tasks by scaling executable environments and training agents to coordinate long-horizon work with state maintenance and recovery.

AuK is an open-source foundational model that unifies speech generation and editing via natural-language instructions and audio context, using a multimodal language model, joint VAE, hybrid rectified-flow Transformer, and efficient distillation for fast inference.

FreeToken is an edge-native Mixture-of-Experts serving system that dynamically maps computation and model state onto heterogeneous local hardware to run large open-weight models on personal machines.

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

VoiceMem introduces a dual-brain streaming memory architecture for speech language models that improves retrieval accuracy, emotional personalization, and real-time efficiency.

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.

Marigold V2 repurposes diffusion transformers for monocular depth estimation via single-step flow-matching inference, semantic alignment, and a Sinkhorn-based two-stage fine-tuning protocol, yielding sharper out-of-distribution depth maps and strong results on related dense regression tasks.

Prime Agent is an open-source harness that uses recursive subagents, persistent computation, and agent-to-agent coordination to extend language models' long-horizon capabilities across coding and reasoning tasks.

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

Show-Harness links vision-language models to robot control via discrete semantic actions interpreted by embodiment-specific modules, enabling zero-shot and efficient fine-tuned deployment across robots and GUIs.

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.

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.

SAS improves sparse attention by training a selector end-to-end with language modeling loss via continuous gating inside attention softmax, yielding better context ranking under tight budgets.

NeoHorse-1 uses agentic post-training with intelligent routing, structured feedback loops, and curriculum-based distillation to improve model capabilities across agent benchmarks.

Dream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations.

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.

OpenWAM factorizes world-action pretraining into modular components to identify key design principles, yielding a scalable open model with strong simulation and real-robot performance.

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.

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.

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.

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.

MiniCPM4, a highly efficient large language model for end-side devices, achieves superior performance using innovations in sparse attention, pre-training datasets, training algorithms, and inference systems.

Gander is an end-to-end framework that integrates continuous multi-modal streaming, real-time full-duplex interaction, and agentic reasoning through a Cerebellum-Brain architecture and a chunk-level token stream design.

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.

PhysBrain 1.5 unifies physical environment understanding, action generation, and future state prediction via joint autoregressive training on discrete vision-language, motion, and visual target sequences, achieving state-of-the-art open-source embodied performance.

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.

Vidu S2 introduces real-time interactive avatar and video editing models that support high-resolution spatial video generation and dynamic reference updates.

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.

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

AI-Infra-Guard is an open-source framework that addresses AI infrastructure security through layered detection paradigms spanning infrastructure, protocol, agent behavior, and model layers.

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.

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

A benchmark requiring agents to programmatically reconstruct real-world videos in Blender reveals that current models achieve high perceptual similarity but struggle to retain spatiotemporal facts.

Zetta is a closed-loop embodied harness that evolves runtime critics and recovery skills online to govern physical execution at action frequency, achieving high success on robot benchmarks with faster inference and scaling self-exploration.

olmOCR is an open-source toolkit using a fine-tuned vision language model to process PDFs into clean text while preserving structure, optimized for large-scale batch processing.

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.

Multi-agent systems using reinforcement learning enable parallel information seeking with scalable orchestration, achieving performance comparable to larger single agents.

The abstract outlines a roadmap for recursive self-improvement in AI, from autonomy stages to meta-improvement, across domains like scientific discovery and software engineering, while identifying practical challenges.

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.

ABot-Recon achieves stable long-horizon streaming 3D reconstruction by using only local temporal context and frame-independent predictions composed sequentially, reducing drift via a lightweight temporal refiner and composition-aware pose loss.