Trending Papers

A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.

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 multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio.

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.

WeMM-Embedding is a family of universal multimodal embedding models that align text, images, videos, and interleaved inputs in a shared space, achieving state-of-the-art retrieval and recommendation performance across public benchmarks and large-scale WeChat applications.

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.

Code-as-World represents physical environments as executable code to enable quantitative reasoning and scalable supervision for vision-language models.

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.

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.

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.

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

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.

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

FunAudioLLM enhances voice interactions by integrating SenseVoice for multilingual speech recognition, emotion detection, and audio event detection with CosyVoice for natural speech generation across languages, timbres, and styles.

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.

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

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.

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.

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.

4DAnyone reconstructs 4D humans from monocular video by generating multiview-consistent videos and lifting them into 4D Gaussian Splatting, using reference and target context designs to overcome scaling bottlenecks.

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.

A method using 3D Gaussians for scene representation and optimized rendering allows high-quality, real-time novel-view synthesis at 1080p resolution.

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

StateM is a runtime system that improves long-horizon agent execution through durable states, recoverable runbooks, and enforceable procedural controls without altering model weights.

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.

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.

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

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.

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.

JIT-Agent is a trainable model that synthesizes adaptive agent harnesses for off-the-shelf LLMs, improving performance across diverse models and tasks.

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.

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.

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.

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.

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io

Trainable sparse attention (VSA) reduces computational cost in video diffusion transformers with minimal impact on performance, enabling efficient scaling of the models.

LLM-as-a-Verifier introduces a probabilistic verification framework that scales across multiple dimensions to improve solution correctness assessment and agent performance across various benchmarks.

Zero-WAM enables robotic manipulation of unseen tasks by conditioning a causal video-action model on in-context human video guidance, supported by an automatically generated dataset and a future-chunk prediction objective.

ContextPilot improves long-horizon agent reasoning by expanding context-editing tools and using reinforcement learning with branch sampling to identify critical context decisions.

SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.

MatrAIx is a large-scale simulated-user evaluation framework that uses diverse persona records and interactive environments to test AI systems across many domains.

LLM routing is formalized as a sequential decision process with a unified benchmark and modular infrastructure to compare and improve cost-effective model selection.

Speculative Decoding evaluation requires diverse workloads to accurately measure performance, which existing benchmarks lack, prompting the introduction of SPEED-Bench for standardized assessment across semantic domains and serving regimes.

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.

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.

DiffusionOPSD uses on-policy self-distillation to turn image-level rewards into explicit intermediate targets for diffusion models, improving alignment efficiency and enabling separate analysis of target construction and policy fitting.

EnvHarness and EnvRigger dynamically reshape static environments via programmable plugins to target agent weaknesses and improve reinforcement learning co-evolution.

StreamPI enhances single-frame vision-language-action models with streaming temporal reasoning via instruction-anchored attention and randomized interval training, improving robot manipulation without extra parameters.

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.