new

Get trending papers in your email inbox!

Subscribe

Trending Papers

byAK and the research community

Trending Papers
Submitted by
bupalinyu

The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction

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.

Edge0 Edge0 路 Sep 16, 2026
Submitted by
aaronjli

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

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

MicrosoftResearch Microsoft Research 路 Oct 15, 2026

PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

PaperOrchestra is a multi-agent framework that converts unstructured research materials into complete LaTeX manuscripts with literature synthesis and visual elements, outperforming existing autonomous writing systems in human evaluations.

  • 4 authors
路 Apr 6, 2026

TradingAgents: Multi-Agents LLM Financial Trading Framework

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.

  • 4 authors
路 Dec 28, 2024
Submitted by
ruiyaox

Harness^2: Recursive Agent Harnessing for an Open World

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

google Google 路 Oct 9, 2026
Submitted by
cherubicxn

Learning Heterogeneous Tactile Representation for General Dexterous Manipulation

LingBot-Touch is a tactile foundation model that learns a unified, extensible representation across heterogeneous tactile sensors, yielding plug-and-play tactile tokens that consistently enhance manipulation policies such as diffusion policy and VLA models.

robbyant Robbyant 路 Nov 9, 2026
Submitted by
akhaliq

Efficient Memory Management for Large Language Model Serving with PagedAttention

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

  • 9 authors
路 Sep 12, 2023
Submitted by
pbicho

MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

MACaQ is an MXFP4 W4A4 post-training quantization method that quantizes each linear layer independently using online activation transforms and Hessian-aware refinement, reducing cost while preserving accuracy across language and diffusion models.

Kronos: A Foundation Model for the Language of Financial Markets

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.

  • 7 authors
路 Aug 2, 2025
Submitted by
swa2n

e-means: outperforming k-means (in one-tenth the epochs)

Lloyd's k-means algorithm is a long-running standard for clustering, with applications in data analysis, retrieval, quantization and data curation. In this paper, we introduce an exponential moving average optimization procedure for k-means with mini-batch updates, powered by modern deep learning machinery and new insights. We also establish scaling laws on how decay rate and batch size impact final performance. This gives us a formulaic rule to fix them for multiple problem sizes and embedding datasets, without the need for any hyperparameter sweep. The resulting clustering algorithm, coined e-means, is much faster than Lloyd k-means and converges to lower losses, frequently even beating k-means++. On a wide array of embeddings datasets, it beats the loss of Lloyd k-means at 25 epochs in 1.4 to 2.6 epochs, which translates to 10-45x GPU wall-clock speedups compared to state-of-the-art k-means implementations. As an example, e-means partitions DINO10B, a dataset of 10 billion DINO embeddings, into 16 million clusters in only 2.5 epochs, reaching a loss below Lloyd's at 25 epochs.

meta Meta 路 Nov 6, 2026
Submitted by
akhaliq

OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

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.

  • 24 authors
路 Jul 23, 2024
Submitted by
akhaliq

Very Large-Scale Multi-Agent Simulation in AgentScope

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.

  • 8 authors
路 Jul 25, 2024
Submitted by
unilm

VibeVoice Technical Report

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

MicrosoftResearch Microsoft Research 路 Aug 26, 2025
Submitted by
taesiri

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

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.

  • 23 authors
路 Aug 22, 2025
Submitted by
andy-yang

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

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.

Submitted by
lhpku20010120

OmniEdu: Open Foundation Models for Learning and Teaching

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.

PekingUniversity Peking University 路 Sep 19, 2026
Submitted by
akhaliq

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

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.

  • 5 authors
路 Apr 28, 2025
Submitted by
RuofengYang

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

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.

HuggingFace's Transformers: State-of-the-art Natural Language Processing

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.

huggingface Hugging Face 路 Oct 9, 2019
Submitted by
taesiri

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

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.

  • 61 authors
路 Sep 26, 2025

A decoder-only foundation model for time-series forecasting

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

  • 4 authors
路 Oct 14, 2023
Submitted by
andito

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

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.

ibm-granite IBM Granite 路 Mar 14, 2025
Submitted by
dkliang

World In-Context Learning for Agentic Robot Manipulation

Trained action policies write manipulation skill into network weights, tying what is learned to the distribution it is learned from. In-context learning (ICL) avoids this coupling but has not matched trained policies, because a demonstration recorded in another scene carries no feedback from the world the robot currently faces. We observe that what an agent learns in context is semantic, recording task steps and object roles rather than visual appearance, so experience gathered in one world transfers to another. Based on this insight, we propose World In-Context Learning (WICL), a paradigm in which a frozen model starts from a demonstration, rehearses the task in a world such as a simulator, and writes the feedback into its context rather than its weights. We build RoboScript, a modular infrastructure that implements WICL for agentic manipulation. From a single demonstration, RoboScript learns each task through rehearsal in simulation, freezes the learned knowledge as a Task Memory, and deploys the frozen memory on new scenes with data isolation that ensures every deployment input is available on a real robot. On all 50 tasks of RoboTwin 2.0, RoboScript reaches 83.4% mean success across clean and randomized settings with one demonstration per task and no gradient updates, exceeding the strongest trained action policy by over 20 points. The method generalizes across visual distributions, improves through reflection, scales with the foundation model, and transfers to a physical dual-arm robot through cross-embodiment memory adaptation. With a world in the loop, a robot can learn a manipulation task in its context as well as it learns one in its weights. All code is available at https://github.com/ArcheOne-AI/RoboScript

ArcheOne-AI ArcheOne-AI 路 Nov 9, 2026
Submitted by
taesiri

Unlimited OCR Works

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.

baidu BAIDU 路 Jun 22, 2026
Submitted by
nielsr

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

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.

Ultralytics Ultralytics 路 Jun 2, 2026

PyTorch Distributed: Experiences on Accelerating Data Parallel Training

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.

  • 11 authors
路 Jun 28, 2020
Submitted by
BradNLP

Flide: Accelerating Decision Inference with Exact State Forking

Flide is an exact inference engine that accelerates decision-model LLM agents by decoupling logical request trees from physical execution and using ForkAttention to preserve exact branch evaluations.

Submitted by
wangzx1210

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

A decision model that acts poorly can still teach reinforcement learning policies effectively by judging complete action trajectories, improving success on ALFWorld and WebShop.

ZhejiangUniversity Zhejiang University 路 Nov 12, 2026
Submitted by
caizhongang

Has GPT-6-Astra Achieved Embodied Intelligence?

GPT-6-Astra achieves high performance across diverse robotic tasks via in-context learning, yet real-world deployment reveals gaps in demonstration cost, execution time, and practical embodied intelligence.

sensenova SenseNova 路 Oct 15, 2026
Submitted by
ChengCui

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

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.

PaddlePaddle PaddlePaddle 路 Jun 2, 2026
Submitted by
a43992899

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

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.

OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

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.

  • 9 authors
路 Oct 23, 2024
Submitted by
supra3d

SUPRA-TEX: 3D Generation with Super-Aligned Texture

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.

  • 8 authors
路 Oct 15, 2026
Submitted by
lgy0404

nanoMuse: An Open-Source Personal Agent for Every Device You Own

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.

zju Zhejiang University 路 Oct 6, 2026
Submitted by
kumboh

Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation

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

StanfordUniversity Stanford University 路 Oct 9, 2026

Native and Compact Structured Latents for 3D Generation

A new sparse voxel representation called O-Voxel enables high-quality 3D generative modeling with efficient inference and robust topology handling.

microsoft Microsoft 路 Dec 16, 2025
Submitted by
billhuang2001

Persistent Recursive Worlds Enable Autonomous Software Evolution

Genesis organizes long-horizon software development around a persistent project rather than persistent agents, enabling multi-day compiler construction and numerical module reimplementation with low cost and high performance.

Submitted by
dongguanting

ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents

ToolSpace constructs realistic multi-environment tool-use benchmarks by mining execution traces, clustering tool compositions, and validating tasks through replayable state-aware random walks.

Submitted by
Phospheneser

MOSS-Image Technical Report

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.

OpenMOSS-Team OpenMOSS 路 Oct 16, 2026
Submitted by
jaychempan

Duo: A Reciprocal World Model for Full-Duplex Interaction

A reciprocal world model enables real-time full-duplex audiovisual interaction by jointly modeling intent and realization using autoregressive reasoning, synchronized attention, and dual rollout distillation.

inclusionAI inclusionAI 路 Nov 11, 2026
Submitted by
CapitalLiu

Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

Web-facing AI agents repeatedly access webpages, documents, repositories, and tool responses, yet reading interfaces often expose entire objects when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute relevant evidence. We present SparseRead, a reusable reading control layer that governs content admission without modifying the agent model. Its Read Intent Protocol tracks evolving needs and source coverage; Adaptive Reader Backends select how evidence is located and exposed; and the Budgeted Read Gate bounds cumulative raw exposure per episode with faithful full-view fallback. A unified Reader interface supports interchangeable evidence acquisition across heterogeneous resources. Across six models, including Claude Opus 5, and five scenarios, SparseRead reduces total tokens by up to 92.9% and wall time by up to 89.0%, preserving or improving task quality in 97% settings. On Web deep-search tasks, it reduces tokens by 31.0--43.0% and task completion time by 23.0--37.0%. Ablations validate the three designs, while integration with three agent frameworks demonstrates portability.

Submitted by
ritianyu

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

SplatAnything applies Gaussian Spacing Normalization to canonicalize scene-level Gaussian spacing, yielding more consistent supervision and improved feed-forward 3D Gaussian Splatting under varying scene scales and viewpoints.

zju Zhejiang University 路 Nov 5, 2026
Submitted by
mocoV3

REMORY: Learning Residual Memory for Context Compaction

REMORY enhances long-horizon agent memory by adding learnable soft tokens to textual summaries, improving decision accuracy with minimal context usage.

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

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.

  • 5 authors
路 Jan 20, 2025
Submitted by
BinceQu

RoboHarness: A Simple Harness Outperforms VLA and World Action Models

RoboHarness enables LLM agents to perform embodied manipulation via a visual-geometric control interface, surpassing specialized vision-language-action models on robotics benchmarks.

zju Zhejiang University 路 Oct 16, 2026

Xiaomi-OCR-0 Technical Report

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.

  • 10 authors
路 Sep 28, 2026
Submitted by
taesiri

Qwen3-TTS Technical Report

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.

Qwen Qwen 路 Jan 22, 2026
Submitted by
henry-y1

G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

Discrete autoregressive models offer a scalable framework for image generation. However, they face a fundamental trade-off: long token sequences preserve representation quality but slow generation, while aggressive spatial compression reduces representation capacity. Based on product quantization, we show that, under a fixed nominal information budget, group size should scale quadratically with the per-axis spatial compression factor. Building on this principle, we propose GSTAR, a spatial--group co-scaling framework that enables \(32\times\) and even effective \(64\times\) compression while preserving strong reconstruction, understanding, and generation performance. Since larger groups introduce intra-group dependencies that must be modeled efficiently, we analyze their impact on inference latency and generation quality and introduce a semi-autoregressive decoder that combines parallel feature computation with lightweight causal modeling. With these designs, our highly compressed models perform competitively with leading models across five representative text-to-image benchmarks (GenEval, DPG-Bench, PRISM, LongText-Bench, and Qwen-Image-Bench). At \(1024\times1024\) resolution, our model delivers a \(20\times\) speedup over prior discrete autoregressive models, generating each image in 2.5 seconds on a single NVIDIA H200. Together, these results show that highly compressed discrete representations can enable high-quality autoregressive generation at low latency.

meituan-longcat LongCat 路 Nov 8, 2026

PDFMathTranslate: Scientific Document Translation Preserving Layouts

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

  • 4 authors
路 Jul 2, 2025

Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems

A real-time verification system for retrieval-augmented generation that processes long documents and balances latency constraints with comprehensive answer validation.

  • 5 authors
路 Mar 4, 2026