Trending Papers

TokenEconomizer reduces recurring token costs of coding agents across sequential real-world tasks by pruning irrelevant tools, injecting micro-skills, and interrupting failure loops.

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.

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.

Harness² improves agent execution harnesses through recursive task-level refinement and continual harness-level learning, boosting performance across benchmarks without ground-truth verifiers.

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.

Uni-robot-agent enables open-weight robot-use agents to surpass proprietary models in zero-shot manipulation and suggests joint development of four core capabilities for future training.

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.

This paper reviews the Kornia differentiable data augmentation module for both 2D and 3D tensors, integrating with PyTorch's autograd and optim, and benchmarks it against other frameworks.

Xiaomi-OCR-0 is a compact vision-language model that unifies document parsing and OCR understanding through automated data synthesis, progressive training with text anchoring and reinforcement learning, and achieves state-of-the-art results on multiple benchmarks.

WeVisOne-VL unifies object-level and pixel-level visual perception via structured token prediction, supporting detection, localization, counting, OCR, segmentation, and matting with a lightweight pixel decoder and multi-stage training.

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.

SpecPilot autonomously discovers deployment-specific algorithms and system optimizations to maximize speculative decoding speedups across diverse models, drafters, and serving regimes without quality loss.

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.

Edge0 enables efficient mixture-of-experts inference on consumer hardware by predicting expert routing ahead of time and using recovery adapters to maintain quality with minimal active memory.

HairDeck generates stylized hair cards and spring-bone animations as unordered token sets using a diffusion transformer, improving accuracy and speed over prior methods.

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

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.

CUA-Master uses nested recursive loops with open-world data and feedback-driven retries to continuously improve computer-use agents across diverse benchmarks.

Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a model, and until now had no open counterpart. This report defines the personal agent in five questions and three horizons. It reads how Muse is built from Meta's public record and a copy of its production prompt, each statement marked by its source. It then presents nanoMuse, the open-source counterpart under the GPL-3.0, one agent on every device a person owns, with hands on the phone's screen and the computer's. They share one conversation over a relay anyone can run; every action goes through a Sentinel, memory is files the person can read, and the model is their choice. Its size and cost are given as estimates. What is open, memory with provenance, an evaluation suite for the hands and an open model for them, is set out as a roadmap.

MOSS-Image is an open diffusion transformer that combines high-fidelity synthesis with intent-aware prompt enhancement to generate text-rich, layout-coherent images, achieving state-of-the-art open-weight results on long-form text and layout benchmarks.

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.

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.

CoworkOS is a long-horizon agent harness that separates strategy from execution, supports human-in-the-loop collaboration via shared artifacts, and improves model performance through sustained automated post-training.

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

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.

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.

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.

Intrinsic Distribution Matching improves few-step text-to-image generation by adding explicit moment constraints to distribution matching distillation, achieving state-of-the-art long-text rendering with minimal network evaluations.

Wave Forcing enables efficient continuous long-video generation with consistent appearance and natural motion through co-designed generation, training, and execution, achieving high throughput and quality.

ReLift improves dense 3D tracking by repairing and completing lifted trajectories using geometric trajectory refinement without requiring image-based training.

Investor's Last Exam evaluates financial agents on end-to-end equity research using frozen evidence, expert criteria, and dependency graphs, revealing that top models excel at research but fail at forecasting and investment judgments.

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.

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.

History Forcing improves long-range consistency in few-step autoregressive video generation by using historical context residuals to correct distillation targets.

YuE2 unifies symbolic and audio music generation via symbolic planning, producing readable scores and full-song audio with state-of-the-art quality and agentic editing capabilities.

Axion 1.0 is an open agent foundation model trained via a concise three-stage pipeline of supervised fine-tuning and reinforcement learning, achieving competitive agentic performance while fully releasing its data and training recipe.

SUPRA-Tex decouples visible-material estimation, surface alignment, and 3D completion to generate relightable 3D materials that preserve reference image details and complete unobserved surfaces.

NorthCUA scales computer-use agents via an experience flywheel, recursive self-improvement, staged learning, and reinforcement learning to achieve state-of-the-art open-source GUI and web interaction results.

A pipeline using sparse autoencoders extracts interpretable linguistic features from neural detectors, yielding more accurate and explainable AI-generated text classification.

PhotoGuider selects viewing directions and frames 360° panoramas using shared composition-aware tokens and produces camera-parameter outputs with explanation-conditioned scoring.

OmniEdu is a family of instruction-tuned educational foundation models that improve K-12 problem solving, curriculum understanding, and tutoring through capability-balanced training data.

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

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

Next-Concept Modeling uses hierarchical discrete codes and parallel level-wise generation to accelerate diffusion language models while improving quality and reasoning performance.

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.

Joint-embedding predictive architectures trained on aligned multi-modal observations converge to shared representations with far greater efficiency than next-token prediction, demonstrating that positive view design—not scale alone—drives cross-modal alignment.

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

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.

Hy-Nomas is a video world model that uses causal attention and structured conditioning to generate interactive, multi-turn video segments with text and camera control.